video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3193
|
videos/HRA_part2/3193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic leopard, distinguished by its golden fur and intricate rosette patterns, sprints across a sun-drenched savanna. Its muscles ripple powerfully beneath its coat, demonstrating raw strength and agility. The leopard's piercing green eyes remain focused ahead, indicating determination and purpose in its stride. It bounds gracefully over the landscape, leaving a trail of displaced grass in its wake, embodying the essence of wild freedom and survival instinct.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a leopard sprinting on the grassland, but the movements are not very smooth and coordinated."
}
] |
seed46_2074
|
videos/HRA_part2/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_276
|
videos/HRA_part2/276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, two people clad in sportswear run side by side down a vibrant street, passing by towering skyscrapers that glisten under the bright sunlight. The runners, a man in a red shirt and black shorts, and a woman in a purple tank top and gray leggings, navigate through the urban landscape with ease. Pedestrians, some in business attire and others casually dressed, walk alongside them, creating a dynamic atmosphere. The towering buildings, adorned with reflective glass, cast long shadows across the street, adding depth and contrast to the urban setting. Throughout the video, the runners maintain their pace, their determination evident as they weave through the crowd and continue their journey among the impressive cityscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1485
|
videos/HRA_part0/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's body in the video is deformed, with a missing arm."
}
] |
seed42_1001
|
videos/HRA_part0/1001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2001
|
videos/HRA_part1/2001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged, bespectacled female teacher, wearing a gray turtleneck sweater and dark pants, sits at a desk in a classroom after school hours. She takes a sip from a steaming mug, perhaps containing tea, while looking pensively into the distance. Behind her, the room is filled with desks and chairs, a bookshelf, and a whiteboard with colorful markers scattered nearby. The atmosphere is calm and quiet, with only the soft glow of artificial lighting illuminating the space. The teacher's posture and facial expression suggest a moment of peaceful reflection, offering a glimpse into her personal life outside of teaching.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's hand in the video was generated abnormally."
}
] |
seed44_2845
|
videos/HRA_part1/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Normal. The crawling movements of the boy and girl in the video are basically normal, with slight lack of coordination."
}
] |
seed46_2849
|
videos/HRA_part2/2849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant desert landscape under a warm, golden sun, two people clad in traditional white robes stand beside a camel, which is kneeling obligingly in the sand. Moments later, these individuals mount the camel, which rises to its feet, ready to embark on a journey. Subsequently, the camel starts moving, walking steadily across the sandy dunes with the riders holding on. Finally, gaining momentum, the camel begins to run, carrying the passengers across the undulating desert terrain at an exhilarating pace, their white garments billowing in the wind.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the camels and people in the video are deformed, the facial features of the people and camels are not generated, and the body of the person in the middle is deformed."
}
] |
seed42_1391
|
videos/HRA_part0/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Normal. The character's walking in the video is not smooth."
}
] |
seed44_2843
|
videos/HRA_part1/2843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2808
|
videos/HRA_part2/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Bad. The actor's hand in the video is deformed, and the kangaroo's head did not generate ears."
}
] |
seed46_2807
|
videos/HRA_part2/2807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, an antelope, distinctively marked with white underbelly and brown coat, is shown crawling on its belly across the grassland, a behavior rarely observed. The scene opens with the antelope lying down, then it proceeds to crawl, its horns visible, as it moves slowly through the tall grass. Throughout the sequence, the antelope remains low to the ground, its body almost parallel to the earth, showcasing this unusual behavior in great detail against the backdrop of the African savanna.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's horns and nose in the video are generated unreasonably, and there are missing parts in the limbs generation."
}
] |
seed46_1276
|
videos/HRA_part2/1276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare sits on a sandy shore, the vast ocean stretching to the horizon behind it, with rolling waves gently lapping at the sand. The hare, with its large ears and curious expression, appears to be contemplating the serene seascape. Suddenly, the hare leaps into the shallow waters, its powerful hind legs propelling it forward in an unexpected swimming motion. The water splashes around it, creating ripples that extend outward, as the hare continues to swim, defying expectations in the coastal scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_13
|
videos/HRA_part2/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The moose's head is generated incorrectly, and the body is not generated."
}
] |
seed44_2823
|
videos/HRA_part1/2823.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent bird, identified as a golden eagle, soars gracefully against a clear blue sky, its wings spread wide to catch the wind. The eagle's piercing yellow eyes and powerful beak are visible as it glides effortlessly, surveying the vast landscape below. Its majestic plumage, featuring shades of brown and gold, contrasts beautifully with the azure heavens. In another shot, the eagle is seen perched on a rocky outcropping, its sharp talons gripping tightly as it turns its head, alert and watchful, against a backdrop of rolling hills and distant mountains.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the golden eagle's claws grabbing the rock as mentioned in the caption."
}
] |
seed46_1736
|
videos/HRA_part2/1736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A strong woman dressed in black pants, a black sports bra, and protective gear, including shin guards and arm pads, is seen in a well-lit gym. She delivers a powerful roundhouse kick, her body exhibiting grace and power, with boxing gloves on her hands and her hair tied back in a ponytail. Moments later, she throws a fierce punch, her face a mask of determination, showcasing her martial arts skills in a space adorned with punching bags and boxing posters. Finally, she executes a high kick, her form impeccable, against a backdrop of gym equipment and motivational wall art, encapsulating her strength and discipline.]"
},
{
"from": "gpt",
"value": "Bad. The girl's face and limbs in the video have generation issues, with her limbs twisting or suddenly disappearing and reappearing in middle frames."
}
] |
seed46_1435
|
videos/HRA_part2/1435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate musician, donning a dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_268
|
videos/HRA_part2/268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, male, walks through a dense, green forest, its large ears flapping gently. It carries small branches on its back, and its eyes, visible through the foliage, express a sense of peace. The elephant continues its journey, passing by a tree with lush leaves, highlighting the tranquility of its surroundings. It moves forward, its massive body displacing the undergrowth, leaving a path of disturbed vegetation in its wake, all under the shade of towering trees and a filtered light that adds to the serenity of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The African elephant in the video can be seen flapping its ears and moving forward, but the movements are not very continuous and there is slight disharmony."
}
] |
seed46_1390
|
videos/HRA_part2/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2313
|
videos/HRA_part2/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The golden jackal's jumping in the video is not smooth and uncoordinated."
}
] |
seed46_2854
|
videos/HRA_part2/2854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone coyote, with a gray and cream coat, runs across a sunlit prairie, its ears perked and tail held low. It bounds through the tall grass, leaving a slight dust cloud in its wake, indicating speed and purpose. The coyote's focused gaze and agile movements showcase its hunting prowess, as it navigates the open landscape under a clear blue sky. Moments later, it leaps over a small obstacle, demonstrating its agility and grace, all while maintaining its steady pace across the vast, golden plains.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3166
|
videos/HRA_part1/3166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a compassionate female doctor, wearing a white lab coat and blue surgical mask, gently caresses an injured elephant's trunk. They stand under a colossal, weathered stone bridge, its arches towering above them, providing a dramatic backdrop. The elephant, adorned with vibrant red and yellow decorations, hints at cultural significance, while the bridge's ancient stonework contrasts with the modern attire of the doctor, highlighting the juxtaposition of old and new. The tender interaction between the two, set against the imposing structure of the bridge, conveys a message of care and connection across species and time.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's trunk in the video is twisted, and the hands are distorted."
}
] |
seed46_1644
|
videos/HRA_part2/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Bad. The man's arm appears deformed, and the woman's arm appears misshapen."
}
] |
seed44_2060
|
videos/HRA_part1/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2381
|
videos/HRA_part2/2381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_270
|
videos/HRA_part1/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_14
|
videos/HRA_part0/14.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male teacher, wearing a gray sweater over a button-down shirt, yawns dramatically in a classroom filled with desks, capturing a candid moment during a school day. His eyes are closed, his mouth is wide open, and his right hand is holding a red pen, while stacks of papers and books clutter the desk in front of him. The walls are adorned with educational posters, and sunlight streams in from a nearby window, illuminating the room. This intimate scene portrays the relatable, unguarded moment of a dedicated educator succumbing to a yawn amidst his daily responsibilities.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video yawns not very smoothly, and the movements are not very coordinated."
}
] |
seed42_1881
|
videos/HRA_part0/1881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark gray shirt and light gray pants, crawls through a subtropical desert landscape, surrounded by a variety of cacti and succulent plants. The terrain features sandy soil and scattered rocks, with distant hills adding depth to the scene. The actor's body language conveys determination as he moves forward, his facial expression reflecting the intensity of the environment. The lush vegetation, including a large cactus, provides contrast to the arid setting, while the warm sunlight highlights the texture of the sand and the resilience of the desert flora.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and legs in the video have generation issues."
}
] |
seed42_1493
|
videos/HRA_part0/1493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant red swim cap and goggles, is seen playfully interacting with a curious fox at the edge of a serene, crystal-clear pool. The scene opens with the student, wearing a blue swimsuit, diving into the water with a graceful splash, while the fox watches attentively from the side. As the student swims, the fox paces alongside the pool, its interest piqued by the water. Later, the student emerges from the pool, shaking droplets from their swim cap, and reaches out a hand to the fox, which responds with a playful nuzzle, highlighting an unusual yet heartwarming bond between human and wild animal. Throughout the scene, the lush greenery surrounding the pool provides a peaceful backdrop, contrasting with the vivid red of the swim cap and the rich orange tones of the fox's fur.]"
},
{
"from": "gpt",
"value": "Normal. The fox's movement along the edge of the pond in the video is not smooth and coordinated."
}
] |
seed44_2343
|
videos/HRA_part1/2343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit prairie dotted with green shrubs and patches of tall grass, a large bison is rolling on its back in the dirt, surrounded by a cloud of dust. The bison, with its shaggy, brown fur and majestic horns, is enjoying a dust bath, rubbing vigorously against the ground. The camera captures the bison's content face as it lies on its side, legs kicking playfully in the air, creating a plume of dust that envelops its body. This behavior, known as 'dusting,' helps the bison remove parasites and excess oil from its coat, showcasing the creature's natural habits in a captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the bison in the video are missing, the head is generated incorrectly, and the tail is not generated."
}
] |
seed42_1924
|
videos/HRA_part0/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Bad. The director's face and hands, as well as the mysterious creature, are generated abnormally in the video."
}
] |
seed46_1843
|
videos/HRA_part2/1843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a miniature town setting, an engineer, dressed in a blue jumpsuit and safety helmet, crouches next to a tiny gerbil wearing a matching miniature outfit. The scene is set against a backdrop of small, detailed town models, with the engineer gently assisting the gerbil as it explores its environment. The focus is on the interaction between the engineer and the gerbil, emphasizing the care and attention given to the small creature within the context of the meticulously crafted townscape.]"
},
{
"from": "gpt",
"value": "Bad. No safety helmet was generated."
}
] |
seed42_3041
|
videos/HRA_part0/3041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, identifiable by her stethoscope and medical attire, navigates a lunar buggy across the moon's desolate surface, which is marked by craters and strewn with rocks. The buggy's wheels kick up fine lunar dust as it traverses the barren landscape. The doctor's face, visible through the helmet of her spacesuit, reflects determination and focus. In a close-up shot, a small, resilient insect-like creature crawls slowly across the moon's rocky terrain, its tiny legs moving deliberately against the stark, gray backdrop. The buggy continues its journey, passing near the crawling creature, emphasizing the contrasting scales of movement and life on the moon.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the doctor wearing a stethoscope and medical attire, and the lunar rover is not shown passing close to the small, resilient insect-like creature."
}
] |
seed44_1622
|
videos/HRA_part1/1622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a stark contrast of concepts, the scene begins with a majestic buffalo standing solitary in a vast, arid savanna under a clear blue sky, the landscape stretching out to distant mountains. Suddenly, the focus shifts to a cosmic illustration of a black hole, its singularity depicted as a swirling vortex of stars and galaxies being pulled into the abyss, emphasizing the immense gravitational pull. The scene then transitions to a visual metaphor of 'wiping,' showing a clean slate or a blank page, symbolizing the erasure or resetting of information, akin to the theoretical concept of information loss in a black hole scenario. Throughout, the buffalo, the black hole, and the wiping action are portrayed sequentially rather than interacting, due to the inherent incompatibility of these elements in a physical sense.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1092
|
videos/HRA_part1/1092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom, a teacher with short brown hair, wearing a gray top, instructs students about space travel, using a large screen displaying a galactic police chase between a red spaceship and several blue police cruisers. The chase unfolds against a backdrop of stars, planets, and asteroids. The scene then transitions to show the teacher leading her class on a field trip to an indoor swimming pool, where they swim and play water games under her watchful eye, all while wearing swimsuits and caps in various colors. The pool area features large windows offering views of the city skyline, creating a vibrant and engaging learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's arm is severed, and the appearance of a display in the swimming pool is unrealistic."
}
] |
seed42_1653
|
videos/HRA_part0/1653.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged director, balding with graying hair, stands on a vibrant red carpet at a film festival, his eyes welling up with tears. He wears a classic black tuxedo, complete with a bow tie and a white pocket square, his attire reflecting the formal event. In the next scene, he is seen wiping away tears with a handkerchief, his emotional response to a significant moment captured in high definition. Throughout the footage, the director's facial expressions convey a range of emotions, from initial composure to visible vulnerability, all set against the backdrop of the glamorous film festival setting.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the handkerchief mentioned in the caption."
}
] |
seed42_2138
|
videos/HRA_part0/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1844
|
videos/HRA_part1/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the cashier's apron pocket in the airport terminal gift shop are not smooth."
}
] |
seed46_1889
|
videos/HRA_part2/1889.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An eccentric artist, donning a vibrant red beret and a multicolored, patterned jacket, is depicted in a studio filled with artistic clutter, including paintings, brushes, and easels. The artist is engaging in a lively dance, accompanied by a curious monkey wearing a tiny blue hat, which mirrors the artist's movements, creating a whimsical scene of creativity and playfulness set against a backdrop of artistic chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted hands. The monkey's face is also distorted, as well as its arms."
}
] |
seed44_2165
|
videos/HRA_part1/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The turtle's movements in the video are slightly unsmooth."
}
] |
seed42_2849
|
videos/HRA_part0/2849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant desert landscape under a warm, golden sun, two people clad in traditional white robes stand beside a camel, which is kneeling obligingly in the sand. Moments later, these individuals mount the camel, which rises to its feet, ready to embark on a journey. Subsequently, the camel starts moving, walking steadily across the sandy dunes with the riders holding on. Finally, gaining momentum, the camel begins to run, carrying the passengers across the undulating desert terrain at an exhilarating pace, their white garments billowing in the wind.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1908
|
videos/HRA_part2/1908.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2472
|
videos/HRA_part2/2472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a chef's uniform comprised of a white double-breasted jacket and a black and white checkered apron, is seen rock climbing on a sunny day. He confidently grasps the rocks, displaying strength and determination, while his outfit, complete with a black cap, adds a unique twist to the typical rock climber's attire. The clear blue sky and lush greenery surrounding him provide a striking contrast to his chef's garb, making for an unexpected yet captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. Basically no problems."
}
] |
seed42_1484
|
videos/HRA_part0/1484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious, softly lit room with a neutral color palette, two children, a boy and a girl, both wearing pajamas, are seen playing together. The boy, wearing blue pajamas, crawls across the floor, while the girl, dressed in pink pajamas, manipulates a gravity control device, causing everyday objects to float around them. The floating items include a teddy bear, a toy car, and a book, creating a whimsical atmosphere. The children laugh and play among the floating objects, the girl adjusting the gravity device to move the items closer or further away, all within the cozy, safe environment of their playroom.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1074
|
videos/HRA_part1/1074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, clad in a white shirt and brown trousers, stands in the middle of a lush green field under a clear blue sky. He is in mid-action, throwing hay bales with ease and precision. His weathered hands grip a bale tightly as he winds up for the toss, muscles straining beneath his shirt. The hay bales are scattered around him, some neatly stacked, others awaiting his expert throw. The farmer's face is set in determination, eyes focused on the target, embodying the hard work and strength synonymous with farming life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1295
|
videos/HRA_part0/1295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a blue plaid shirt and black pants, sits cross-legged on a wooden floor, surrounded by a variety of eager pets. The room is dimly lit, with a single lamp providing a warm glow. The musician, with a friendly smile, gently strums an acoustic guitar, creating a soothing melody that fills the cozy space. Pets of different sizes and species gather around, their attentive faces showing enjoyment of the music and anticipation of being fed. A fluffy cat perches on the musician's lap, while a small dog sits patiently by a bowl of food, and a parrot watches from its cage. The scene conveys a sense of harmony and love between the musician and the pets, all sharing a special moment together.]"
},
{
"from": "gpt",
"value": "Bad. No bowl of food was generated, no bird's cage was generated."
}
] |
seed46_2613
|
videos/HRA_part2/2613.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, dressed in full gear and helmet, finds himself at the base of a towering space elevator, its sleek silver structure piercing the clouds. Against this futuristic backdrop, he begins to dance, his movements a surprising juxtaposition of grace and strength. The flames from a nearby controlled fire flicker and dance along with him, casting an orange glow on the space elevator's metallic surface. The firefighter's steps are lively and expressive, a mix of joy and determination, as he performs beneath the vast starlit sky, the space elevator standing tall and unwavering behind him.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed42_1662
|
videos/HRA_part0/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running motion in the video is not very smooth and coordinated; the hedgehog's movement is also very unsmooth and uncoordinated."
}
] |
seed46_2091
|
videos/HRA_part2/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed44_2137
|
videos/HRA_part1/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3025
|
videos/HRA_part2/3025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3092
|
videos/HRA_part0/3092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a dark blue button-down shirt and wearing glasses, sits at a modern desk, deeply focused on writing in a notebook with a black pen. The room is illuminated by a sleek desk lamp, casting a warm glow over the workspace cluttered with blueprints, a laptop, and various tools. Behind him, a large window lets in natural light, revealing a bustling city skyline in the background, symbolizing the urban environment where innovation thrives. The engineer's posture and intense concentration convey a sense of dedication and expertise in his craft.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_268
|
videos/HRA_part1/268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, male, walks through a dense, green forest, its large ears flapping gently. It carries small branches on its back, and its eyes, visible through the foliage, express a sense of peace. The elephant continues its journey, passing by a tree with lush leaves, highlighting the tranquility of its surroundings. It moves forward, its massive body displacing the undergrowth, leaving a path of disturbed vegetation in its wake, all under the shade of towering trees and a filtered light that adds to the serenity of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show small branches on the elephant's back."
}
] |
seed44_1468
|
videos/HRA_part1/1468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, smiling teacher stands in a classroom filled with sunlight, wearing a stylish outfit consisting of a striped top, dark jeans, and brown boots. Her warm smile radiates positivity as she looks down at a small child, who is sitting on a chair and wearing a gray jacket and gray pants. The child returns her smile, creating a heartwarming scene of connection and joy in the educational setting. The teacher's attire, the classroom environment, and the presence of the child all contribute to a sense of happiness and engagement in learning.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_272
|
videos/HRA_part0/272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a crisp uniform consisting of a navy shirt, badge, name tag, and matching pants, is seated on a step stool in a modern bathroom. The space is adorned with decorative tiles and features a gray sink cabinet with two drawers. The officer, hat removed, focuses intently on fixing a leaky faucet, demonstrating unexpected handyman skills amidst the bathroom's tidy environment. Tools are neatly spread across the countertop, including a wrench and screwdriver, as the officer leans into the task, sleeves rolled up to the elbows, revealing a tattoo on his right arm. The scene captures a moment of service beyond the call of duty, highlighting the officer's commitment to community care in a civilian's home.]"
},
{
"from": "gpt",
"value": "Normal. The hat, wrench, and screwdriver in the video are generated incompletely."
}
] |
seed44_1390
|
videos/HRA_part1/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Bad. The cormorant's spreading of its wings in the video is not smooth and coordinated, with abrupt changes in the wings' movements."
}
] |
seed46_3154
|
videos/HRA_part2/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2160
|
videos/HRA_part2/2160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling park setting, two children engage in playful pushing, wearing vibrant, colorful clothing typical of a sunny day. One child, dressed in a yellow shirt and blue shorts, playfully pushes another child, who is wearing a red shirt and green shorts, against the backdrop of lush green grass and clear blue skies. The interaction is filled with laughter and joy, capturing the essence of innocent childhood fun. The children's faces are beaming with delight, their eyes sparkling with excitement, as they enjoy each other's company in the heart of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, face, head, and legs of the person in the video are distorted."
}
] |
seed44_2545
|
videos/HRA_part1/2545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a natural, woody setting, a man with a beard, wearing a brown jacket, sits on the ground, gently caressing a gray wolf that lies calmly beside him, its head resting on the man's lap. The wolf appears relaxed and trusting, as if sharing a moment of mutual understanding with the man, who looks on with a soft, compassionate gaze, the lush forest and tall trees providing a serene backdrop to their connection.]"
},
{
"from": "gpt",
"value": "Normal. The man's actions of petting the gray wolf in the video are not very obvious, and the movements are not very continuous and smooth."
}
] |
seed46_1588
|
videos/HRA_part2/1588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah, two zebras engage in a tender moment, their striped bodies gently touching as they caress each other. One zebra, with its mane flowing in the breeze, nuzzles the face of another, their bond evident in the softness of their interaction. The scene is framed by distant acacia trees and a clear blue sky, emphasizing the intimacy shared between these majestic creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2360
|
videos/HRA_part0/2360.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in outdoor gear, including a brown jacket, beige pants, and brown shoes, crawls on hands and knees across a grassy landscape under a cloudy sky. Beside him, a massive bison, its shaggy coat and large horns distinct, grazes on the lush vegetation, seemingly unperturbed by the man's presence. The scene conveys a sense of harmony between the man and the wild animal in their shared natural environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1522
|
videos/HRA_part0/1522.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic gray wolf, marked by a distinct white-tipped tail, walks purposefully across a barren, rocky landscape under an alien sky filled with a Photon sail spacecraft, its large triangular sail illuminated by distant stars. The wolf, with piercing yellow eyes, continues its journey undeterred by the otherworldly sight above. The scene is set on an extraterrestrial terrain reminiscent of a moon or another planet, with the vast universe as the backdrop, highlighting the wolf's solitary trek and the intriguing presence of advanced technology in this desolate environment.]"
},
{
"from": "gpt",
"value": "Normal. The wolf's body is twisted, its face distorted, and its legs deformed."
}
] |
seed44_159
|
videos/HRA_part1/159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla in the video are twisted while dancing, and the fingers and toes are deformed. The mouth is also generated unreasonably."
}
] |
seed42_3045
|
videos/HRA_part0/3045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, exhibiting a gentle demeanor, caresses another smaller chimpanzee with its right hand, both sitting on a brown surface against a green background. The larger chimpanzee, with a caring expression, tenderly strokes the younger one, fostering a sense of intimacy and connection. This heartwarming scene captures the essence of compassion within the primate family, highlighting the nurturing bond between the two creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's hand is a bit deformed."
}
] |
seed44_1115
|
videos/HRA_part1/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The brown fur boots do not appear in the video, and the dancing man in the middle frame suddenly has a third hand."
}
] |
seed42_2508
|
videos/HRA_part0/2508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, wearing a brown jacket and wide-brimmed hat, walks purposefully across a vast, futuristic farm landscape, with a colossal space elevator looming in the distance, its massive cable stretching into the heavens. The farmer pauses, looking up at the awe-inspiring structure, a blend of hard work and advanced technology coexisting in this extraordinary setting. As he continues walking, the camera captures the juxtaposition of traditional farming life and the futuristic marvel towering over the horizon.]"
},
{
"from": "gpt",
"value": "Normal. Failed to generate the space elevator."
}
] |
seed46_1393
|
videos/HRA_part2/1393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1585
|
videos/HRA_part1/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Bad. The actors in the video dance very unsmoothly, with uncoordinated movements."
}
] |
seed42_291
|
videos/HRA_part0/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Bad. The doctor can be clearly seen jumping in the air in the video, but the movement is not very continuous and smooth, showing a lack of coordination."
}
] |
seed44_1375
|
videos/HRA_part1/1375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a rainbow trout fills the frame, its vibrant colors and intricate patterns captivating the viewer. The fish, partially submerged in crystal-clear water, showcases its beauty against a backdrop of smooth river stones and lush green vegetation. Its silver scales glisten in the sunlight, while its red and blue stripes stand out against the clear water. The trout's large, expressive eyes and delicate fins add to its charm, making it the undeniable star of the scene. The rippling water around it creates a sense of movement and life, immersing the viewer in the tranquil yet dynamic environment of a freshwater stream.]"
},
{
"from": "gpt",
"value": "Normal. The fish's mouth generation in the video has issues."
}
] |
seed46_1814
|
videos/HRA_part2/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Bad. The deer's movement in the video is not smooth, and the actions are uncoordinated."
}
] |
seed44_3186
|
videos/HRA_part1/3186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated teacher, clad in a yellow raincoat, blue jeans, and brown boots, leads a group of students on a nature walk through a grassy field. In the distance, a majestic bison stands tall, its presence adding to the educational experience. The teacher points toward the horizon, engaging the students in a lesson about wildlife, with the bison serving as a captivating visual aid. The scene is set against a backdrop of rolling hills and a clear blue sky, creating an idyllic setting for learning and exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2263
|
videos/HRA_part2/2263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a receding hairline and glasses, meticulously irons his shirt in a well-lit room. Dressed in a white button-down shirt, black pants, and black shoes, he focuses intently on his task. He then checks the collar of the shirt, which is already neatly pressed, before continuing to iron. Next, he carefully examines the sleeve, ensuring it is wrinkle-free, his attire reflecting professionalism. Finally, he pauses to adjust his glasses, revealing a wedding ring on his finger, all while maintaining a serious demeanor in the midst of his daily routine.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_213
|
videos/HRA_part0/213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a green shirt and brown overalls, tends to his crops at a resort-like farm, set against a backdrop of rolling hills and clear skies. A friendly hedgehog, nestled in the farmer's pocket, occasionally pops its head out to observe the surroundings. The farmer pauses to wipe his brow with a red bandana, revealing a content smile, as the hedgehog curls up comfortably in its makeshift home. The scene exudes tranquility and harmony between nature and human life, with the resort's luxurious amenities visible in the distance.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, and the hedgehog's body is twisted."
}
] |
seed46_301
|
videos/HRA_part2/301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin breaches the sparkling turquoise ocean, its sleek indigo body glistening in the sunlight. The fish soars through the air, its elongated rostrum pointed skyward, before plunging back into the sea with a splash. Surrounded by the vastness of the ocean, the marlin's powerful leap is captured against a backdrop of rolling waves and a cloud-dappled sky, showcasing the beauty and grace of this magnificent marine creature.]"
},
{
"from": "gpt",
"value": "Normal. The sailfish's tail and fins in the video have generation issues."
}
] |
seed42_1536
|
videos/HRA_part0/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Normal. The number of water buffaloes mentioned in the caption is excessive."
}
] |
seed44_225
|
videos/HRA_part1/225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a doctor, dressed in a crisp white lab coat, stands in an oil refinery, its towering structures and pipelines creating an industrial skyline. He gently caresses a small, clay hippopotamus sculpture, its smooth surface contrasting with the rough, metallic environment. The scene is lit by the warm glow of industrial lights, casting long shadows across the doctor and the miniature hippo, encapsulating an unexpected moment of tenderness amidst a typically harsh landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1676
|
videos/HRA_part0/1676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, attractive female nurse, wearing a white uniform and her hair in a bun, yawns widely while standing alone in a brightly lit hospital hallway. She is seen from different angles, first yawning with her eyes closed, then covering her mouth with her right hand, followed by a close-up of her face showing tired eyes. Lastly, she is captured yawning again, revealing her exhaustion, all within the sterile, well-lit corridor of the medical facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1471
|
videos/HRA_part2/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_131
|
videos/HRA_part1/131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a red checked shirt, brown overalls, and a wide-brimmed hat is seen in a whimsical setting, sharing an unexpected dance with a playful otter. They are surrounded by lush green fields and vibrant wildflowers, with a rustic barn in the background. The otter, holding a miniature top hat, playfully imitates the farmer's dance moves, adding to the charming and surreal atmosphere. The farmer's joyful expression and the otter's animated antics create a heartwarming scene that celebrates the unexpected connections between humans and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's dance moves in the video are not continuous, there are abrupt changes; the otter's imitation of the dance is not smooth and uncoordinated."
}
] |
seed46_1687
|
videos/HRA_part2/1687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures a mole crab, also known as a sand flea, burrowing in the wet sand of a tropical beach. Its sandy brown color perfectly camouflages it against the shoreline, and its shovel-like front legs dig rapidly into the granular substrate. The creature's round body and small size, about an inch long, make it appear as if it's almost melting into the sand, while its eyes, positioned on stalks, scan the environment for predators or prey. The video highlights the mole crab's unique adaptation for life in the intertidal zone, showcasing its survival tactics in the dynamic coastal ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2145
|
videos/HRA_part0/2145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a green swimsuit, sits on a sandy beach near a turquoise body of water, typing away on a laptop, while a small hedgehog perches on the writer's shoulder. The hedgehog has a tiny life jacket on, matching the writer's swimwear. In another scene, the writer is shown swimming in the clear waters, with the hedgehog floating alongside in its miniature life vest, both enjoying a peaceful day at the seaside under a bright, sunny sky.]"
},
{
"from": "gpt",
"value": "Bad. The writer's hand, hedgehog, and life jacket in the video have generation issues."
}
] |
seed42_2962
|
videos/HRA_part0/2962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male worker, wearing a gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_0
|
videos/HRA_part0/0.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint suburban neighborhood at golden hour, two casually dressed individuals walk their dogs on leashes, enjoying the warm, soft lighting. The first person, wearing a red jacket and blue jeans, walks a brown dog, while the other, in a gray hoodie and black pants, strolls alongside with a black dog. Both figures display relaxed body language, reflecting the peaceful ambiance. They pass by a row of identical houses, each with a small front yard and a white picket fence, creating a picturesque setting. The scene is completed by the presence of a third person, seen from behind, also walking a dog, as they all move down the street under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The black dog does not appear in the video."
}
] |
seed44_2539
|
videos/HRA_part1/2539.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]"
},
{
"from": "gpt",
"value": "Bad. The female server's hand appears deformed, and both men and women in the pool appear deformed. In the scene with the female server, a man from the pool suddenly appears."
}
] |
seed46_169
|
videos/HRA_part2/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's face and the runner's body in the video have generation issues."
}
] |
seed44_1242
|
videos/HRA_part1/1242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a waiter wearing a green apron and carrying a tray with refreshments walks through a temperate rainforest. Surrounded by lush greenery, moss-covered trees, and ferns, he moves along a narrow path. The environment is enhanced by the presence of a large tree trunk, its roots exposed, and the sound of a nearby waterfall. Sunlight filters through the dense foliage, casting dappled light on the forest floor, creating a magical atmosphere as the waiter continues his journey.]"
},
{
"from": "gpt",
"value": "Bad. In the end, the person's legs disappear, and deformities appear in the legs and face."
}
] |
seed46_2137
|
videos/HRA_part2/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Bad. The action of the osprey taking off and flying is not continuous and smooth, showing some inconsistency."
}
] |
seed42_1123
|
videos/HRA_part0/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1277
|
videos/HRA_part2/1277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed sports arena, a competitive badger, donning a silver helmet and red uniform, springs into action, leaping high above a futuristic, neon-lit track. The gravity-defying jump is set against a backdrop of stars and planets, with cheering spectators, also dressed in space gear, watching from the stands. The badger's powerful legs propel it through the air, creating a sense of dynamic motion, as it aims to clear a cosmic hurdle during this intergalactic sporting event.]"
},
{
"from": "gpt",
"value": "Bad. The badger in the video has a twisted body, twisted claws, a twisted face, and twisted legs."
}
] |
seed44_2099
|
videos/HRA_part1/2099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow hard hat, orange safety vest, and blue jeans, sits on a wooden crate at a bustling construction site. Surrounded by scaffolding, concrete mixers, and cranes, he meticulously draws architectural plans using a pencil and a large blueprint sheet laid out on a makeshift plywood table, illustrating his dual skills in both physical labor and design. The scene captures his focused expression and the gritty urban environment, highlighting the blend of creativity and labor in his work.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1561
|
videos/HRA_part2/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2155
|
videos/HRA_part0/2155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, clear sky, its powerful wings spread wide against a backdrop of fluffy white clouds and a vibrant blue horizon. The eagle's piercing golden eyes and distinctive white-feathered head stand out prominently. It effortlessly glides over a vast, pristine landscape, featuring lush green forests and shimmering lakes, with the distant silhouette of snow-capped mountains providing a breathtaking contrast. The eagle's strong, brown body and large, feathered tail complete the image of this awe-inspiring bird in flight.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the bald eagle's wings and claws in the video has issues."
}
] |
seed44_2097
|
videos/HRA_part1/2097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah leaps across the golden savanna, its body stretched in mid-air with power and grace. The sun illuminates the cheetah's spotted coat, highlighting the taut muscles beneath as it propels itself forward. In the background, acacia trees stand silhouetted against the horizon, their branches reaching towards the clear blue sky. The cheetah's eyes are fixed on its target, a burst of speed and agility encapsulated in this single, awe-inspiring moment.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's limbs are missing in the video, and the face generation is blurry."
}
] |
seed46_145
|
videos/HRA_part2/145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1262
|
videos/HRA_part2/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the head is twisted, the arms are twisted, and the legs are severely twisted."
}
] |
seed42_1833
|
videos/HRA_part0/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The head and body of the dove in the video were not generated when it was flying and about to fly, and the claws were not fully generated. The wings were generated too large during flight."
}
] |
seed46_2504
|
videos/HRA_part2/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_12
|
videos/HRA_part1/12.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and gun holster, leaps into the air in the middle of a vast, temperate grassland. The landscape is dominated by knee-high green grasses and a few scattered oak trees, with the horizon stretching far into the distance. The officer's feet leave the ground, capturing a moment of action and energy, as the rolling hills and clear blue sky provide a serene contrast to the dynamic scene. The officer's movements are sharp and decisive, embodying the spirit of law enforcement in the open, wild environment of the grasslands.]"
},
{
"from": "gpt",
"value": "Bad. No gun holster was generated, and the character suffered severe distortion and deformation."
}
] |
seed44_2694
|
videos/HRA_part1/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.