video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2752
|
videos/HRA_part2/2752.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 whimsical scene, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1333
|
videos/HRA_part2/1333.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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The dog's jumping motion in the video is not coordinated."
}
] |
seed42_2282
|
videos/HRA_part0/2282.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 engineer clad in a grey jumpsuit and safety helmet walks through a lush, green landscape, holding a clipboard. In the background, a koala casually climbs down from a eucalyptus tree, its furry body contrasting against the vibrant vegetation. The engineer stops to observe the koala, crouching down to examine it closely, while still maintaining a professional demeanor. The scene is set under a clear blue sky, with sunlight filtering through the leaves, highlighting the interaction between the human and the wildlife in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The koala's actions of climbing down from the tree in the video are discontinuous and have sudden changes."
}
] |
seed42_281
|
videos/HRA_part0/281.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 fearless firefighter, clad in full gear and a yellow firefighting suit, interacts with a hyena at a unique wildlife sanctuary. The firefighter, helmet in hand, stands beside a swimming pool, while the hyena, sporting a brownish coat and black spots, looks on curiously. The two share a moment of connection, with the firefighter's reassuring presence and the hyena's inquisitive gaze, all set against the backdrop of a tranquil, water-filled pool. The scene highlights an unexpected bond between a protector of human safety and a wild animal, both seemingly at ease in each other's company.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's fingers are deformed, the firefighter's head is not generated, and there is an issue with the hyena's mouth."
}
] |
seed42_2492
|
videos/HRA_part0/2492.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: [On a futuristic space movie set, a dedicated nurse in a pristine white uniform tends to a unique patient—a green lizard-like alien with intricate facial features. She gently wipes the creature's face with a soft cloth, her compassionate expression conveying care and concern. The sterile environment is contrasted by the exotic presence of the alien, creating a captivating scene blending human kindness with otherworldly elements.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1815
|
videos/HRA_part0/1815.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 whimsical scene opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Normal. The koala's swimming movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_2272
|
videos/HRA_part1/2272.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 a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's arm is incompletely generated, and the face is blurry."
}
] |
seed42_1422
|
videos/HRA_part0/1422.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, clean-shaven male chef with short brown hair waves energetically with his right hand, standing in front of a vibrant green wall adorned with a pattern of white dots. He wears a traditional white chef's uniform with a black necktie, and his left hand rests comfortably in his pocket. The chef's warm smile and engaging demeanor convey a sense of welcome and enthusiasm, perfect for a cooking show introduction or a restaurant greeting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1765
|
videos/HRA_part0/1765.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 and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]"
},
{
"from": "gpt",
"value": "Bad. The deer's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1481
|
videos/HRA_part0/1481.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 brownish-black and white plumage, soars majestically over a serene lake at sunset, its piercing yellow eyes scanning the water below for fish. The bird, with its distinctive head pattern and curved beak, effortlessly glides through the air, its wings spread wide, casting a shadow on the calm water. Suddenly, it dives into the lake with remarkable speed and precision, emerging moments later with a wriggling fish clasped firmly in its talons. As the osprey ascends back into the sky, the fading sunlight illuminates its powerful form, highlighting the intricate feather patterns and the determination in its eyes.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2433
|
videos/HRA_part0/2433.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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2959
|
videos/HRA_part1/2959.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 director, distinguished with salt-and-pepper hair and a trimmed beard, stands in a dimly lit, cluttered bathroom. Dressed casually in a gray t-shirt, dark jeans, and a black jacket, he focuses intently on unclogging a blocked sink drain. His right hand grips a metal tool, while his left hand steadies the sink's rim. The scene captures his determination, with the bathroom's sparse details - a white toilet, a beige wall, and a small window - adding context to his solitary task. The director's serious demeanor and the bathroom's functional design emphasize the mundane yet necessary act of home maintenance.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1407
|
videos/HRA_part2/1407.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 clad in a blue shirt and gray pants is seen interacting with a chimpanzee in a laboratory setting. The chimpanzee, sitting upright on a chair, holds a wipe in its hand and begins wiping a surface, demonstrating tool use under the watchful guidance of the engineer. The scene captures the unique bond between human and primate in a research context, highlighting the chimpanzee's ability to mimic and perform tasks typically associated with human dexterity and intelligence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2405
|
videos/HRA_part1/2405.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 young student, wearing a yellow long-sleeved shirt and gray pants, diligently cleans a large fish tank located in the corner of a classroom, filled with various colorful fish. The tank is illuminated by overhead lights, casting a warm glow on the aquatic environment. The student, with short brown hair and glasses, carefully removes algae from the glass walls using a scraper, ensuring a clear view of the vibrant underwater world. The scene captures the student's focused determination and the peaceful coexistence of education and nature within the classroom setting.]"
},
{
"from": "gpt",
"value": "Bad. The student's hands and arms show deformities and distortions."
}
] |
seed44_1421
|
videos/HRA_part1/1421.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 chef, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The chef's sweeping motion is not continuous and has abrupt changes."
}
] |
seed42_1298
|
videos/HRA_part0/1298.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 scene, a waiter, dressed in a crisp white shirt, black vest, and black trousers, is seen playfully dancing with an otter. The otter, wearing a tiny bow tie, mirrors the waiter's movements, adding to the surreal atmosphere. The two are surrounded by a softly lit, elegant dining room, with tables set for dinner and fine art adorning the walls. The waiter, with his professional attire, and the otter, with its playful nature, create a harmonious and unexpected dance partnership, captivating the audience with their synchronized steps.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's arm is twisted, the hand is twisted, the face is twisted, and the legs are twisted."
}
] |
seed42_332
|
videos/HRA_part0/332.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 director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2035
|
videos/HRA_part2/2035.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 lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2822
|
videos/HRA_part0/2822.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 janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2216
|
videos/HRA_part1/2216.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 farmer wearing a dark green jacket, blue jeans, and brown boots stands in a lush, green meadow dotted with dandelions. He looks down with a slight smile as he spots a small vole. The vole, with its distinctive round ears and brown fur, leaps from one dandelion tuft to another in the foreground, creating a playful contrast against the serene farm landscape. The farmer watches the vole's antics with amusement, his stance relaxed and his hands resting on his hips, as the rural setting provides a peaceful backdrop to this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and there are sudden changes."
}
] |
seed44_2456
|
videos/HRA_part1/2456.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 through a clear blue sky, its wings spread wide, revealing its distinctive white-feathered head and brown body. It glides effortlessly over a vast, serene landscape, comprised of lush green forests and tranquil lakes, with distant mountain peaks forming a stunning backdrop. The eagle's piercing yellow eyes remain alert, scanning the terrain below for any sign of prey, as it embodies the spirit of freedom and strength in the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the bald eagle's head, claws, and tail feathers has issues."
}
] |
seed44_215
|
videos/HRA_part1/215.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 rugged firefighter, clad in full gear and a helmet, gently caresses a tiny, spiky hedgehog with a gloved hand, their eyes tenderly locked in a heartwarming connection. The scene is set against a backdrop of a partially extinguished fire, with billowing smoke and the remnants of flames, highlighting the contrast between the rough exterior of the firefighter and the delicate nature of the animal. The hedgehog, seemingly unharmed, nestles into the palm of the firefighter's hand, creating a poignant moment of compassion amidst the chaos.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's face is distorted in the video, and the character's face is slightly distorted."
}
] |
seed44_2419
|
videos/HRA_part1/2419.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 distinguished film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand, the antelope's head, and limbs are generated abnormally, and the antelope's head and tail suddenly switch positions in the middle frames."
}
] |
seed46_2604
|
videos/HRA_part2/2604.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 film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2120
|
videos/HRA_part1/2120.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, donning a white painter's smock and denim jeans, meticulously hangs a series of vibrant oil paintings on a gallery wall, the warm glow of spotlights illuminating each frame. The gallery space is vast, with high ceilings and pristine white walls, providing a stark contrast to the rich colors of the artwork. In another shot, the artist, now wearing a beret and glasses, carefully levels a large abstract piece, its bold strokes and dynamic composition capturing the essence of modern art. Finally, standing back, the artist admires the completed arrangement, a harmonious blend of creativity and craftsmanship, the gallery now transformed into a visual narrative of artistic expression.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2755
|
videos/HRA_part2/2755.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 artist, clad in a dark green jacket, beige pants, and brown shoes, walks across a grassy field under a clear blue sky, carrying an easel and a canvas. The focus shifts to reveal a majestic antelope standing in the distance, its silhouette framed by the golden hour sunlight. The artist stops, observing the antelope intently, before setting up the easel and beginning to sketch the graceful creature against the backdrop of a serene landscape. The artist's hands move skillfully over the canvas, capturing the essence of the antelope in motion, with the rolling hills and distant mountains providing a stunning natural setting for this artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's movement back and forth in the video is not continuous and smooth, there are discontinuities."
}
] |
seed44_3200
|
videos/HRA_part1/3200.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 lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Normal. The jackal's body is twisted, head is twisted, and legs are twisted."
}
] |
seed42_189
|
videos/HRA_part0/189.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 college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1117
|
videos/HRA_part2/1117.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 small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1969
|
videos/HRA_part1/1969.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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2922
|
videos/HRA_part1/2922.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 close-up view of a sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2953
|
videos/HRA_part0/2953.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 blue t-shirt and khaki shorts, runs across a vast desert landscape under a clear blue sky, with distant mountains providing a dramatic backdrop. The student, wearing a backpack and a cap, navigates the sandy terrain with determination, the camera capturing the texture of the dunes and the play of light and shadow. As the scene progresses, the focus remains on the runner, highlighting their stamina and resilience against the stark beauty of the desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2027
|
videos/HRA_part1/2027.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 lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the children in the video have generation issues, with distortion and deformation appearing in the middle frames."
}
] |
seed44_1223
|
videos/HRA_part1/1223.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 quiet, sunlit forest, a young woman who resembles a cashier from a local store embarks on a hike, dressed in hiking gear that includes a green jacket, khaki pants, and brown boots. She pauses to look at something intriguing in the distance, her hiking backpack visible. Moments later, she is seen walking confidently along the trail, her attire and equipment suggesting a preparedness for the outdoors. Then, she stops to rest, leaning against a tree trunk, her hiking poles propped up beside her, conveying a sense of peaceful contemplation. Finally, she continues her journey, walking away from the camera, her figure framed by the lush greenery and dappled sunlight, embodying the spirit of adventure and nature.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely distorted, and the walking stick beside them is also twisted."
}
] |
seed42_2212
|
videos/HRA_part0/2212.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 man in a silver spacesuit, reminiscent of a high-tech astronaut, walks across a vast, barren landscape under a twilight sky, reminiscent of a distant planet. A cobra, its scales shimmering with iridescent colors, slithers along the ground beside him, seemingly unphased by the alien environment. In the background, a massive deep space communication array rises into the sky, its dishes facing the cosmos, ready to transmit messages across the universe. The man stops, looking up at the stars, while the cobra rears up, mirroring his stance, both figures framed by the imposing silhouette of the communication array.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands, legs, and eyes in the video have generation issues."
}
] |
seed42_2031
|
videos/HRA_part0/2031.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 firefighter, clad in full gear and helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1122
|
videos/HRA_part1/1122.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 waiter, dressed in a black vest and white button-down shirt, kneels in a lush green meadow. He gently caresses a meerkat standing on its hind legs, which is perched on a small wooden table covered with a white cloth and decorated with a single red rose in a vase. The waiter's face is filled with a warm smile, his eyes softly gazing at the meerkat as he tenderly strokes its back with his right hand. The scene is peaceful and heartwarming, with the sun casting a golden glow over the meadow and the meerkat's curious expression adding to the charm of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The server's movements while petting the meerkat in the video are not smooth and coordinated, and the meerkat's movements are not smooth."
}
] |
seed46_1660
|
videos/HRA_part2/1660.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 waiter, dressed in a white shirt and black pants, carefully balances a tray of refreshments on his hands, offering it to a friendly mammoth. The mammoth, depicted with brown fur and large tusks, swims leisurely in a serene lake, its body half-submerged in the clear water. The waiter stands at the edge of the lake, extending the tray towards the mammoth, who reaches out with its trunk to gently take a drink. The sky is a vivid orange, suggesting either sunrise or sunset, adding a touch of magic to this extraordinary encounter between two unlikely companions.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, and it's hard to see the action of drinking with the nose."
}
] |
seed42_1946
|
videos/HRA_part0/1946.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 small brown rat is seen grooming itself meticulously, its paws lifting to wipe across its face and whiskers. Positioned against a neutral grey backdrop, the rat's actions are the focal point, as it carefully tends to its cleanliness, showcasing the natural behavior of self-care in rodents. The scene is intimate, with the rat's fur and whiskers detailed in high definition, emphasizing the texture and vibrancy of its coat against the monochromatic setting.]"
},
{
"from": "gpt",
"value": "Bad. The finger generation of the brown rat in the video is problematic."
}
] |
seed46_2293
|
videos/HRA_part2/2293.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 albatross soars through a vivid orange sunset, its expansive wings nearly touching the rippling water below. The bird's white plumage is highlighted by golden light, casting a serene shadow on the sea's surface. Against a dramatic sky, the majestic bird flies gracefully, occasionally gliding over gentle waves. Its wings, outstretched against the horizon, seem to embrace the vastness of the ocean, creating a captivating contrast between the bird's silhouette and the fiery sky.]"
},
{
"from": "gpt",
"value": "Bad. The albatross's flying movements in the video are not very continuous and there are inconsistencies."
}
] |
seed42_1843
|
videos/HRA_part0/1843.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 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 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": "Normal. The engineer's fingers appear deformed."
}
] |
seed42_3016
|
videos/HRA_part0/3016.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, clad in a khaki shirt and beige chinos, gently caresses a kangaroo in an Australian outback setting, surrounded by shrubbery and distant hills. The engineer, wearing safety goggles around his neck, interacts affectionately with the kangaroo, which stands on the ground, both under a clear blue sky. The kangaroo, with its distinctive marsupial pouch, is calmly accepting the engineer's touch, while the engineer's attire and demeanor suggest a blend of professionalism and compassion in this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2973
|
videos/HRA_part2/2973.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 quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3182
|
videos/HRA_part0/3182.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 professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1006
|
videos/HRA_part0/1006.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 whimsical scene, a police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_185
|
videos/HRA_part2/185.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 distinguished director, clad in a casual black jacket and gray trousers, runs energetically across a large, open room within a space-themed educational facility. The room is adorned with detailed models of the Apollo spacecraft and other historical rockets, highlighting the center's focus on space exploration. As he moves, the director passes by a group of attentive students seated at tables, each engaged with interactive exhibits about space missions. The vibrant atmosphere reflects the excitement and educational value of the space center, emphasizing its commitment to inspiring the next generation of astronauts and scientists.]"
},
{
"from": "gpt",
"value": "Bad. The director's limbs in the video are missing and deformed, the face is generated blurry, the student's face is deformed, and there are missing limbs."
}
] |
seed46_1063
|
videos/HRA_part2/1063.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 surprising scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and discontinuous, making it hard to see the running action."
}
] |
seed44_2895
|
videos/HRA_part1/2895.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 inventive engineer, donning a yellow hard hat and safety vest, stands beside a massive robotic mammoth at a pier, the structure's weathered wooden planks extending over the water. The mammoth, complete with tusks and a textured gray exterior, is connected to the engineer via cables and machinery. As seagulls fly overhead, the engineer leaps onto the mammoth's back, initiating an unexpected journey. The scene captures the juxtaposition of historical grandeur and modern engineering prowess, with the city skyline visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The mechanical mammoth's head is distorted, the engineer's hands are twisted, and the face is distorted."
}
] |
seed42_2270
|
videos/HRA_part0/2270.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 man named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate brown pants."
}
] |
seed42_2115
|
videos/HRA_part0/2115.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 film director, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The director's eyes and hands, and the wolf's limbs have generation issues in the video; there are frames where the wolf has three front legs, and the wolf's limbs suddenly disappear or reappear."
}
] |
seed42_1450
|
videos/HRA_part0/1450.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 brown bear, bristling with strength and agility, runs through a lush, green forest, its muscles rippling beneath thick fur. The bear's powerful strides propel it across the undergrowth, scattering leaves and twigs in its wake. Sunlight filters through the dense canopy overhead, dappling the forest floor and highlighting the bear's movement. The air is filled with the sounds of nature; birdsong, rustling leaves, and the heavy breathing of the bear as it continues its run, a testament to the raw power and grace of the wild.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's walking movements in the video are not smooth and coordinated."
}
] |
seed46_1279
|
videos/HRA_part2/1279.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, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3213
|
videos/HRA_part0/3213.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 surprising yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The server in the video moves slowly and is almost static."
}
] |
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 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, 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": "Bad. The female nurse's facial movements in the video are not smooth and her hand movements are uncoordinated."
}
] |
seed46_2434
|
videos/HRA_part2/2434.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 whimsical scene, a panda, donning a red-and-white striped shirt, black pants, and a green apron, works as a cashier in a grocery store decorated with Chinese lanterns and bamboo plants. The panda, complete with a name tag and a lanyard, interacts with customers at the register. Suddenly, the panda starts dancing joyfully, swaying to an unseen beat, captivating the shoppers with its playful antics. The panda continues to dance, moving around the store, engaging with various customers, who look on in amusement, while still managing to scan items and handle transactions with dexterity. Throughout the scene, the panda's infectious energy fills the store, creating a memorable and delightful shopping experience.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1773
|
videos/HRA_part2/1773.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, donning a yellow hazmat suit typically worn in industrial areas, paints a vivid mural featuring a graceful gazelle sprinting across a barren urban landscape. The scene is set against the backdrop of industrial zones, with the artist's focused expression and steady hand capturing the gazelle's dynamic movement on a large concrete wall. The artwork comes to life as the painter adds final touches, highlighting the gazelle's speed and agility, juxtaposed against the gritty industrial setting, while the artist, still in the yellow protective gear, steps back to admire the finished piece.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2410
|
videos/HRA_part1/2410.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 distinguished doctor, wearing a brown jacket over his white medical coat, shovels snow from the sidewalk outside his clinic on a cold winter day. His attire includes dark pants, brown boots, and a brown cap, providing contrast against the snow-covered landscape. He pauses to wipe his brow, revealing a sense of effort, before continuing to clear the path, demonstrating his commitment to his patients. Behind him, the clinic's sign is visible, adding context to the scene. Throughout, the focus remains on the doctor's actions and the snowy environment, highlighting his dedication amidst the wintry conditions.]"
},
{
"from": "gpt",
"value": "Bad. The doctor shoveling snow in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_2252
|
videos/HRA_part0/2252.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 creative writer, dressed in a green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1323
|
videos/HRA_part0/1323.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 whimsical scene, a costumed hamster, dressed as an astronaut with a small helmet and spacesuit, rides on the back of a miniature, Mars-themed horse moving across a red, sandy landscape, reminiscent of the Martian surface. The hamster then dismounts and begins to dance, executing playful, comical moves against the backdrop of a painted, starry sky, complete with a large, glowing moon. Throughout the sequence, the hamster wears its astronaut outfit, enhancing the surreal and humorous nature of the scenario.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2688
|
videos/HRA_part2/2688.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 experienced engineer, clad in a yellow hard hat, safety glasses, and a blue uniform, stands amidst the towering structures and pipelines of an oil refinery complex. He is seen wiping his hands on a cloth, perhaps after completing a task, with the industrial landscape of the facility stretching behind him. The scene captures the essence of hard work and maintenance in the heart of the oil industry.]"
},
{
"from": "gpt",
"value": "Bad. The person's face in the video is distorted, the hands are distorted, and the cloth in the hand is twisted."
}
] |
seed42_2756
|
videos/HRA_part0/2756.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 scene, a friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The moose's face is distorted in the video."
}
] |
seed44_2988
|
videos/HRA_part1/2988.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 surreal scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Normal. The antelope can be clearly seen using a green cloth to wipe the wooden counter in the video, the movements are basically normal but there is some lack of coordination."
}
] |
seed44_2020
|
videos/HRA_part1/2020.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 charismatic male musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The action of the male musician wiping sweat from his forehead with his right hand in the video is discontinuous and abrupt."
}
] |
seed44_2201
|
videos/HRA_part1/2201.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 whimsical scene, two young girls wearing colorful party dresses and headbands with attached animal ears are seen dancing joyfully in a room decorated with balloons and streamers. Amidst the celebration, a small, live hedgehog sits calmly on a table covered with a checkered cloth, surrounded by party snacks and a cake. The hedgehog occasionally moves its quills, seemingly joining in the festivities, as the girls continue their lively dance, their movements filled with laughter and the innocence of childhood joy.]"
},
{
"from": "gpt",
"value": "Bad. The video generated an extra girl, and the dancing girls in the video have incomplete limbs."
}
] |
seed42_2316
|
videos/HRA_part0/2316.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 distinguished musician, donning a gray turtleneck sweater and brown corduroy jacket, meticulously polishes silver cutlery using a white cloth, revealing a surprising domestic side. He sits at a large, cluttered wooden table, surrounded by an array of musical instruments, sheet music, and recording equipment, indicating his passion for music. The scene is set in a dimly lit room with vintage furniture, giving it a cozy, intimate atmosphere. The musician's focus is intense as he carefully cleans each piece of silverware, a task typically associated with waiters preparing for service, juxtaposed with his artistic profession.]"
},
{
"from": "gpt",
"value": "Bad. The musician's actions of wiping the silverware in the video are not very continuous and smooth, there is a lack of coordination."
}
] |
seed42_2804
|
videos/HRA_part0/2804.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 attractive male actor, donning a black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2492
|
videos/HRA_part2/2492.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: [On a futuristic space movie set, a dedicated nurse in a pristine white uniform tends to a unique patient—a green lizard-like alien with intricate facial features. She gently wipes the creature's face with a soft cloth, her compassionate expression conveying care and concern. The sterile environment is contrasted by the exotic presence of the alien, creating a captivating scene blending human kindness with otherworldly elements.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1599
|
videos/HRA_part2/1599.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 softly lit room painted a calming shade of blue, two young children, a boy and a girl, both wearing pajamas, sit on a large bed with white sheets. The girl, with her blonde hair in pigtails and clad in pink pajamas, cries with her mouth wide open, tears streaming down her cheeks, her hands covering her face. Beside her, the boy, wearing blue pajamas, leans forward with concern, placing a comforting hand on her back, his brown hair tousled and his eyes filled with empathy, offering a silent support amidst their shared distress.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2659
|
videos/HRA_part1/2659.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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's movements in the video are not smooth."
}
] |
seed42_1786
|
videos/HRA_part0/1786.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 small, vibrant green lizard, adorned with intricate patterns, traverses slowly across a weathered stone surface, basking in the warm sunlight that highlights its textured skin. Its movements are deliberate and methodical, showcasing the strength in its tiny limbs as it explores its ancient, sun-soaked environment. With each step, the lizard reveals the resilience and adaptability of nature, set against a backdrop of natural elements, including stones and plants, that have been shaped by time and the elements.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1105
|
videos/HRA_part0/1105.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 dark uniform with a badge clearly visible, traverses a vast wetland landscape, the lush greenery contrasting sharply with his authoritative attire. He is seen wading through shallow water, his boots partially submerged, indicating a purposeful journey through this natural terrain. Moments later, he is fully immersed in swimming, his uniform now soaked, navigating the intricate network of waterways under a cloudy sky. This scene captures the unexpected sight of a law enforcement figure engaging with the wild, uncharted environment of the wetlands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1449
|
videos/HRA_part0/1449.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 solitary crab, displaying a vibrant red and orange carapace, scuttles across a shallow, sunlit tide pool, surrounded by lush green seaweed and other marine life. The crab's claws, one significantly larger than the other, are prominently displayed as it navigates its environment, with the smaller claw delicately handling food. Its intricate shell pattern and the dynamic underwater setting provide a visually engaging scene, all captured in stunning detail against a backdrop of clear, blue water and a sandy ocean floor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2202
|
videos/HRA_part1/2202.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 lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the giraffe in the video are missing, and the facial generation is blurry."
}
] |
seed46_1697
|
videos/HRA_part2/1697.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, cartoon-like setting, a mongoose, dressed as a nurse in a white uniform, cap, and apron, is seen wiping the face of a young boy with a small towel. The boy, wearing a striped shirt, sits on a chair, looking up with wide eyes, as the animal nurse meticulously cleans him. The scene takes place in a room with white walls, and a painting of a ship hangs in the background, adding a touch of adventure to the otherwise ordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes, and the hand appears deformed. The towel in the hand suddenly disappears."
}
] |
seed42_1948
|
videos/HRA_part0/1948.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 innovative engineer, clad in a gray shirt and khaki pants, interacts with a sleek black jaguar at the edge of a tranquil pool. The engineer, displaying remarkable courage, gently touches the big cat's nose. Moments later, the jaguar, showcasing its powerful physique, leaps into the water, its muscles rippling beneath its glossy coat. The engineer watches with awe as the jaguar swims effortlessly, its fluid movements captivating against the serene aquatic backdrop. Throughout, the engineer remains composed, observing the majestic animal from a safe distance by the poolside.]"
},
{
"from": "gpt",
"value": "Normal. The movements are unsmooth."
}
] |
seed42_1959
|
videos/HRA_part0/1959.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 rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed, and the shovel is also distorted."
}
] |
seed46_1046
|
videos/HRA_part2/1046.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 diligent worker, clad in a high-visibility yellow vest, blue jeans, and a brown jacket, methodically rakes a large pile of autumn leaves into a meticulously organized heap. The scene is set in a spacious backyard, bordered by a wooden fence, with additional piles of leaves scattered throughout the yard, indicating a day of hard work. The worker's focus is intense, his movements efficient, as he tackles the task with determination, the vibrant colors of the fallen foliage contrasting beautifully against the green grass.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and the actions are not continuous."
}
] |
seed46_1716
|
videos/HRA_part2/1716.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 serene, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Bad. There is an extra man in the video."
}
] |
seed46_1207
|
videos/HRA_part2/1207.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: [On a vast, sandy beach, a waiter, dressed in a white button-down shirt and black pants, crawls towards a table set with fine dining ware, a bottle of wine, and two glasses, indicating an unusual yet intriguing service style. The waiter, wearing a name tag and sporting a neatly trimmed beard, continues crawling on the sand, his posture and facial expression suggesting determination. He crawls under a beach umbrella, highlighting the unique setting for this dining experience, with the calm sea and clear blue sky providing a picturesque backdrop. Finally, the waiter reaches the table, still crawling, as he prepares to serve the patrons, creating a memorable and unconventional beachside dining scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is deformed, and legs are twisted."
}
] |
seed42_1381
|
videos/HRA_part0/1381.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 woman with short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2535
|
videos/HRA_part0/2535.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, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3041
|
videos/HRA_part1/3041.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 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 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 driving actions of the character in the video are not continuous and there are sudden changes."
}
] |
seed46_2348
|
videos/HRA_part2/2348.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 man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2452
|
videos/HRA_part2/2452.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 engineer, clad in a yellow jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Bad. The hand shows deformities and mutations, and the object in the hand also becomes deformed. The arm is also elongated at one point."
}
] |
seed44_3213
|
videos/HRA_part1/3213.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 surprising yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1456
|
videos/HRA_part2/1456.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 man, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_270
|
videos/HRA_part0/270.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."
}
] |
seed44_1187
|
videos/HRA_part1/1187.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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Normal. The elephant in the video uses its trunk to playfully splash water, and the action is basically normal; however, the police officer's action of gently patting the elephant's head seems a bit uncoordinated."
}
] |
seed42_1904
|
videos/HRA_part0/1904.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 man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_1089
|
videos/HRA_part1/1089.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 dimly lit museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's movements are not smooth."
}
] |
seed44_2688
|
videos/HRA_part1/2688.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 experienced engineer, clad in a yellow hard hat, safety glasses, and a blue uniform, stands amidst the towering structures and pipelines of an oil refinery complex. He is seen wiping his hands on a cloth, perhaps after completing a task, with the industrial landscape of the facility stretching behind him. The scene captures the essence of hard work and maintenance in the heart of the oil industry.]"
},
{
"from": "gpt",
"value": "Bad. The engineer in the video wipes his hands very unsmoothly, and the movements are uncoordinated."
}
] |
seed42_19
|
videos/HRA_part0/19.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 underwater scene, a stunning coral reef thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals in different shapes and sizes, ranging from brain coral to staghorn coral, create a textured landscape. The colors are rich and saturated, featuring shades of orange, red, purple, and green. The reef is teeming with life, as schools of colorful fish, such as angelfish and clownfish, swim gracefully among the corals. In the foreground, a curious sea turtle glides by, adding to the dynamic beauty of this marine ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2946
|
videos/HRA_part1/2946.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 stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1687
|
videos/HRA_part0/1687.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 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 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. No obvious problems."
}
] |
seed42_2636
|
videos/HRA_part0/2636.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 thoughtful male writer sits in a cluttered office, adorned with a gray beanie, black jacket, and glasses, typing on a laptop placed on a wooden desk. The room is filled with books, a typewriter, and a calendar, creating a vintage atmosphere. His hands move swiftly across the keyboard as he focuses intensely on his work, surrounded by objects that inspire creativity, such as a globe, a lamp, and a framed picture. The scene conveys a sense of dedication and passion for writing, with the man deeply engrossed in his craft amidst a space that reflects his personality and interests.]"
},
{
"from": "gpt",
"value": "Bad. No calendar was generated, and the framed photos were missing."
}
] |
seed42_2485
|
videos/HRA_part0/2485.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 artist, donning a black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand is somewhat deformed, and the antelope's legs in the painting are deformed."
}
] |
seed42_142
|
videos/HRA_part0/142.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 close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1953
|
videos/HRA_part1/1953.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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the koala in the video are generated incorrectly, the facial features are missing, the backpack is distorted, and the ears are generated in the wrong position."
}
] |
seed44_2225
|
videos/HRA_part1/2225.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 man, wearing a gray jacket over a button-down shirt and black pants, meticulously mops the floor in a wide, empty corridor with high ceilings. His movements are deliberate as he pushes the mop back and forth, creating a rhythmic pattern on the wet floor. The lighting is bright, illuminating the space and highlighting the sheen on the freshly cleaned surface. In one shot, the janitor pauses, mop in hand, as he looks down the length of the hallway, assessing his work. Throughout, the focus remains on him and the task at hand, capturing the quiet dedication of his labor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2063
|
videos/HRA_part2/2063.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 teacher, wearing a green shirt and khaki pants, stands in a classroom filled with educational posters and bookshelves, holding a small hippopotamus toy. Behind her, a large window reveals Saturn's majestic rings in the distance, dominating the sky. The teacher gently tosses the hippo into a clear, indoor swimming pool, where it floats on the water's surface, creating ripples. The room is illuminated by soft, warm lighting, casting a serene atmosphere over the unique combination of elements.]"
},
{
"from": "gpt",
"value": "Bad. The movements are unsmooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.