video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1657
|
videos/HRA_part1/1657.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 spacious living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1794
|
videos/HRA_part2/1794.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, wearing a brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3060
|
videos/HRA_part2/3060.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, wearing a white tank top, blue jeans, and black sneakers, meticulously cleans a car using a sponge and bucket filled with soapy water, under a clear blue sky. He begins by pouring water from a green hose nozzle onto the vehicle, the bubbles catching the sunlight. Next, he uses a sponge to scrub the car's hood, his focused gaze and dedicated posture conveying his commitment to the task. Then, he rinses the suds away with the hose, revealing the car's now gleaming surface. Lastly, he wipes down the clean car door with a cloth, the contrast between the dirty rag and the shiny paintwork highlighting the effectiveness of his efforts.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show black sneakers."
}
] |
seed46_3064
|
videos/HRA_part2/3064.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, middle-aged male doctor stands in a well-lit hospital corridor, wearing a stethoscope around his neck and a white lab coat over a crisp, button-down shirt and slacks. He holds a clipboard in his right hand, reviewing patient records intently. Behind him, the hallway is bustling with medical personnel and equipment, conveying the busy atmosphere of a healthcare facility. The scene captures the essence of a dedicated healthcare professional in the midst of his duties, surrounded by the sights and sounds of a working hospital.]"
},
{
"from": "gpt",
"value": "Normal. There is basically no other movement."
}
] |
seed42_1646
|
videos/HRA_part0/1646.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 janitor, wearing a brown jacket over a green shirt, leans over the railing of a pier to fish, with a small fishing rod in hand and a yellow bucket by his side. He is seen from behind, gazing intently into the water, the sun reflecting off his balding head and casting a warm glow on his upturned face. The pier is old and weathered, with faded paint and worn wooden planks, and the water below is calm and clear, dotted with the occasional ripple from a fish. In the distance, a city skyline can be seen, its tall buildings silhouetted against the bright blue sky, providing a stark contrast to the peaceful scene unfolding on the pier.]"
},
{
"from": "gpt",
"value": "Good. The fishing actions of the person in the video are basically normal."
}
] |
seed44_1471
|
videos/HRA_part1/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2467
|
videos/HRA_part1/2467.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, energetic ferret with a tan and black fur pattern leaps from a wooden platform in a spacious room, showing its agility and playfulness. The room is filled with natural light, highlighting the ferret's mid-air jump with a backdrop of a large window and potted plants. The ferret lands gracefully on another platform, part of a series of interconnected wooden structures designed for climbing and exploration. It pauses for a moment, looking curious and alert, before making another sudden leap, showcasing its lively spirit and acrobatic abilities against the serene indoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are not smooth."
}
] |
seed42_1845
|
videos/HRA_part0/1845.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 dimly lit, cavernous space, a small, brown bat gently caresses another bat with its wing, creating a tender, intimate moment. The bats are perched upside-down on a rocky surface, with water droplets visible in the background, adding to the natural, subterranean atmosphere. The scene is illuminated by a soft, warm light that highlights the texture of the bats' fur and wings, emphasizing the caring interaction between the two creatures.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_15
|
videos/HRA_part1/15.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 young, bespectacled Asian male cashier, wearing a red apron over a gray shirt, stands in a dimly lit grocery store. Behind him hangs a large, vintage television playing footage of the historic moon landing. Suddenly, the focus changes to reveal a majestic deer walking calmly down the aisle, seemingly unfazed by its unusual surroundings. The cashier looks on in mild surprise, his expression a mix of bemusement and acceptance, as the deer continues its leisurely stroll among the shelves.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's actions are not continuous."
}
] |
seed44_3129
|
videos/HRA_part1/3129.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, adorned in a red apron with a white floral pattern, sits on a wooden chair in a sunlit room filled with art supplies. She gently caresses a chicken, which is perched on her lap, its head adorned with a vibrant red comb. The room is decorated with colorful paintings, a large easel, and a variety of art tools, creating a warm and creative atmosphere. The artist's face, framed by curly brown hair, expresses love and connection as she interacts with the bird, highlighting the unique bond between the two.]"
},
{
"from": "gpt",
"value": "Normal. The artist's fingers are deformed in the video, the chicken's head is abnormally generated, and the claws are deformed."
}
] |
seed42_208
|
videos/HRA_part0/208.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 beautifully detailed brown trout swims gracefully in a clear, bubbling stream, its speckled skin shimmering beneath the water's surface. The trout's intricate pattern of spots and slashes is vivid against the backdrop of smooth river stones and aquatic plants. Sunlight filters through the water, highlighting the fish's movements as it navigates the current with effortless ease, a true testament to its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1612
|
videos/HRA_part0/1612.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 cheerful doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's laughing in the video is basically normal, with slight inconsistency."
}
] |
seed42_2573
|
videos/HRA_part0/2573.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: [Two young children, a boy and a girl, sit cross-legged on a wooden deck, surrounded by three small dogs. The boy, wearing a yellow shirt and blue shorts, carefully scoops kibble from a green bowl into his hand, offering it to a white and brown terrier who eagerly licks his palm. Meanwhile, the girl, clad in a pink dress, giggles as she holds out a piece of dog food to a black pug, who sniffs it before gently taking it from her fingers. In the background, a third dog, a golden retriever, patiently waits its turn, sitting attentively near the edge of the deck, as the siblings take turns feeding the pets under the warm glow of afternoon sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the people in the video are distorted, as well as the arms. The dog's face and legs are also distorted."
}
] |
seed44_2212
|
videos/HRA_part1/2212.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 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 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 walking movements in the video are not very continuous and smooth, showing slight disharmony; the cobra's movement actions are discontinuous, with abrupt changes."
}
] |
seed42_3216
|
videos/HRA_part0/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2631
|
videos/HRA_part0/2631.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 lawyer, evident from his refined facial features and confident posture, rakes leaves in an autumn backyard. He wears a brown jacket over a crisp white shirt, paired with khaki trousers, and brown shoes, presenting a polished appearance. The lush green grass, vibrant red leaves scattered about, and a large tree with a tire swing in the background create a warm, inviting atmosphere. The lawyer, possibly taking a break from his legal work, enjoys the simple pleasure of outdoor chores, his face expressing satisfaction and tranquility amidst the rich colors of fall.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_3005
|
videos/HRA_part2/3005.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 well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, legs, and the item in their hand are distorted in the video."
}
] |
seed46_1653
|
videos/HRA_part2/1653.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged director, balding with graying hair, stands on a vibrant red carpet at a film festival, his eyes welling up with tears. He wears a classic black tuxedo, complete with a bow tie and a white pocket square, his attire reflecting the formal event. In the next scene, he is seen wiping away tears with a handkerchief, his emotional response to a significant moment captured in high definition. Throughout the footage, the director's facial expressions convey a range of emotions, from initial composure to visible vulnerability, all set against the backdrop of the glamorous film festival setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2515
|
videos/HRA_part1/2515.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 male lion, identifiable by his large size and dark mane, crawls stealthily across a dry, grassy savanna landscape. His body is positioned low to the ground, his ears are forward, and his eyes are intensely focused on something beyond the frame, indicating a hunting scenario. The lion's powerful muscles ripple beneath his tawny fur as he moves quietly, demonstrating the predatory nature and hunting prowess of these apex predators. The scene is set against a backdrop of distant acacia trees and an endless sky, capturing the essence of the African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The lion's legs and face generation in the video have problems."
}
] |
seed46_1777
|
videos/HRA_part2/1777.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 bustling city square, under the soft glow of streetlights and the clear night sky, a diverse group of individuals, including a man with a beard, a woman with glasses, and another woman with a ponytail, are all looking intently at something above them. Their postures and facial expressions convey a sense of awe and wonder, suggesting they are captivated by an extraordinary sight in the urban landscape. Among them, a man with a beard and a woman with glasses stand side by side, both gazing upwards with intense focus. Beside them, a woman with her hair in a ponytail also looks up, her face reflecting a mix of surprise and fascination. All around, the city continues its nightly activities, but these people remain transfixed, united in their shared attention to an unseen marvel overhead.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2315
|
videos/HRA_part2/2315.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 lion, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]"
},
{
"from": "gpt",
"value": "Normal. The lion's mouth in the video has minor generation issues."
}
] |
seed42_1239
|
videos/HRA_part0/1239.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 African elephant, distinguished by its larger size and ears shaped like the continent, walks through an unexpected environment - an industrial zone. Its massive body moves with surprising grace among warehouses with corrugated metal roofs, concrete walls, and large steel containers. The elephant's gray skin, wrinkled and textured, contrasts sharply with the man-made structures. It strides on paved roads, passing by utility poles and electrical wires, creating an unusual juxtaposition of nature and industry. Despite the urban surroundings, the elephant maintains its majestic presence, walking with a purposeful gait, its trunk swaying gently as it navigates through this industrial landscape.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's legs are deformed with several extra legs, and the tusks have not been generated."
}
] |
seed46_1393
|
videos/HRA_part2/1393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, the face is distorted, the arms are twisted, the kangaroo's body is distorted, and the legs are twisted."
}
] |
seed42_1878
|
videos/HRA_part0/1878.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 man, possibly named Ray, stands in a sunlit room, wearing a stylish gray suit, white shirt, and patterned tie. He is seen from different angles, first with his back to the window, then with his profile illuminated by the sunlight, and finally facing forward, his confident expression captured in high definition. Throughout the sequence, he maintains a calm demeanor, his attire and the interplay of light and shadow creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video turns around basically normally, but there is a slight lack of coordination in the movements."
}
] |
seed46_1560
|
videos/HRA_part2/1560.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 warbler, a small songbird with yellow-green plumage, perches on a branch, its head turned to the side, revealing its distinct facial markings. It opens its beak to sing, showcasing its natural habitat among lush green leaves. The bird then takes flight, its wings flapping gracefully, before landing on another branch, where it continues its melodious song, surrounded by the vibrant foliage of a tree. Throughout, the focus remains on the warbler's lively movements and distinctive features, set against the backdrop of a verdant forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The bird's movements in the video are not smooth and coordinated."
}
] |
seed42_1022
|
videos/HRA_part0/1022.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, cheerful female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's flight in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_2052
|
videos/HRA_part1/2052.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, wearing swimming goggles and a yellow floatie, perched on the edge of a turquoise pool. It peers into the water with curiosity, its plush toy-like appearance adding charm. In the next shot, the koala, still in its floatie and goggles, is seen paddling in the shallow end of the pool, surrounded by clear, sparkling water. The camera then captures the koala as it floats on its back, appearing relaxed and content, with the floatie supporting it and the goggles keeping its eyes dry. Finally, the koala is shown sitting upright in the pool, holding onto the side with one paw, its other arm stretched out as if waving, all while maintaining its adorable and playful demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed44_2912
|
videos/HRA_part1/2912.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 dimly lit diner after hours, a weary waiter, attired in a crisp white shirt, black vest, and striped tie, rests his head on his hands atop a checkered tablecloth. He has removed his shoes and his black socks are visible, adding to the sense of weariness and relaxation. His nametag reads 'Eduardo', and he appears to have fallen into a peaceful slumber, surrounded by the quiet emptiness of the restaurant. A half-drunk cup of coffee sits beside him, a testament to the long night shift he's just completed. The scene is intimate and still, capturing a rare moment of rest for a hardworking individual.]"
},
{
"from": "gpt",
"value": "Normal. The video did not show the waiter's shoes being taken off, and the coffee cup was not half-full."
}
] |
seed44_3162
|
videos/HRA_part1/3162.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 vibrant scene unfolds where a musician, clad in a leopard-print jacket and dark sunglasses, passionately plays a saxophone under a spotlight. Nearby, a cheetah with a golden collar and bell, standing on its hind legs, dances gracefully to the music. The setting is a stage decorated with colorful neon lights, creating an electrifying atmosphere as the audience watches in awe. The musician's performance is captivating, and the cheetah's movements are fluid and expressive, both in perfect harmony with the upbeat jazz melody.]"
},
{
"from": "gpt",
"value": "Normal. The musician's saxophone playing actions are basically normal, with slight disharmony; the cheetah stands on its hind legs and dances gracefully to the music, but the movements are very discontinuous and there are abrupt changes."
}
] |
seed46_3108
|
videos/HRA_part2/3108.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 compassionate, middle-aged male nurse with short, dark hair and glasses, wearing a pale blue scrub top and pants, carefully lifts a frail elderly patient from a hospital bed. The patient, a thin woman with short gray hair, is dressed in a hospital gown and has an oxygen tube in her nose. The nurse, with a strong yet tender grip, supports her under her arms and legs, ensuring her comfort and safety throughout the transfer. The scene takes place in a well-lit, modern hospital room, with medical equipment and a window visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1316
|
videos/HRA_part1/1316.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 sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Bad. The child's hand appears deformed, and the lizard has undergone a mutation."
}
] |
seed46_2997
|
videos/HRA_part2/2997.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 tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's face is distorted, the child's face is distorted, and the hands are distorted."
}
] |
seed46_1809
|
videos/HRA_part2/1809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The facial and hand generation of the server in the video is abnormal, and the merging of two servers' bodies in the middle frame does not conform to reality."
}
] |
seed44_1435
|
videos/HRA_part1/1435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 passionate musician, donning a dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1142
|
videos/HRA_part2/1142.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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1554
|
videos/HRA_part1/1554.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 well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_274
|
videos/HRA_part2/274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a vast desert, two young children, a boy and a girl, clad in vibrant red shirts and denim shorts, leap into the air in unison, their silhouettes framed against the golden dunes and a clear blue sky. They jump from a sandy mound, their faces alight with joy and the wind tousling their hair, encapsulating the spirit of youthful adventure. Behind them, a series of similar sand dunes stretch towards the horizon, while the sun casts a warm glow over the entire scene, highlighting the texture of the sand and the children's animated expressions.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed42_3112
|
videos/HRA_part0/3112.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 industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, feet, mouse body, and head are distorted in the video."
}
] |
seed44_156
|
videos/HRA_part1/156.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-looking female cashier, wearing a green apron over a pink blouse and denim jeans, stands at a cash register in a grocery store that has been transformed into an aquatic environment. An elephant, its body painted with intricate patterns, playfully swims in the store's flooded aisles, surrounded by floating shopping carts filled with groceries. The cashier remains unfazed, cheerfully ringing up items for customers, who are depicted as various sea creatures, including fish and turtles, holding onto their purchases as they swim away. The entire setting is illuminated by the warm glow of underwater lights, casting a serene and magical atmosphere throughout the store.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, feet are deformed, the elephant's body is contorted, and the face is distorted."
}
] |
seed46_2686
|
videos/HRA_part2/2686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged female teacher, wearing a dark blue blazer over a white blouse and carrying a black handbag, walks purposefully down a wide hallway with high ceilings, resembling the interior of a university building. The walls are adorned with educational posters, and the floors are covered with brown carpeting. As she strides forward, the scene subtly transitions to reveal a large window behind her, displaying a breathtaking view of Neptune's turbulent atmosphere, filled with vivid blue and green clouds swirling majestically. This unique setting, combining the familiar environment of a school with the awe-inspiring backdrop of a distant planet, creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The generated female teacher in the video does not conform to reality."
}
] |
seed44_2700
|
videos/HRA_part1/2700.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 forest setting, a majestic gray wolf gently caresses a smaller, white wolf with its nose, demonstrating a tender moment of affection between the two creatures. The gray wolf, with piercing yellow eyes, a thick, shaggy coat, and a muscular build, leans its head down to touch noses with the smaller white wolf, which looks up with a similar intensity. Both wolves are standing in a grassy clearing within the dense forest, surrounded by tall trees and patches of sunlight filtering through the leaves, creating a serene atmosphere for this intimate interaction.]"
},
{
"from": "gpt",
"value": "Normal. The gray wolf's eyes and mouth generation have issues, and the white wolf's mouth and eyes generation have issues."
}
] |
seed46_1297
|
videos/HRA_part2/1297.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 chef, dressed in a traditional white uniform and toque, encounters a curious brown bear on a winding forest path. The chef, holding a large basket of freshly picked mushrooms, stops in surprise, maintaining a cautious yet calm demeanor. The bear, intrigued by the chef's presence, stands on its hind legs, sniffing the air with interest. The scene is set in a lush, green forest, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. The chef, with a look of determination, slowly backs away, keeping a steady eye on the bear, who watches intently, its ears perked up, before both continue on their respective paths, the chef returning to the kitchen and the bear disappearing back into the woods.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed46_1590
|
videos/HRA_part2/1590.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 charismatic male musician, dressed in a red shirt, black vest, and dark pants, stands on a dimly lit stage, pointing with his right hand. He wears a black beret and glasses, adding to his artistic flair. Behind him, a vibrant purple curtain complements the stage lights, which cast a warm glow on his face. His left hand rests on his hip, and he points emphatically with his right, engaging the audience in a dynamic performance. The background is blurred, emphasizing the musician's commanding presence as he points with passion and intensity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1913
|
videos/HRA_part1/1913.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 visionary writer sits at a contemporary desk, crafting stories about space exploration, surrounded by swimming gear and a large aquarium filled with exotic fish. The room is illuminated by a floor lamp with a large shade, casting a warm glow on the writer's face. They wear a black shirt and a necklace, their focus intense as they type on a laptop. Behind them, a window reveals a starry night sky, evoking a sense of wonder and adventure into the cosmos. Beside the desk, a modern painting in shades of blue and green adds a splash of color, reminiscent of water, perhaps reflecting the writer's love for swimming. The aquarium, visible in the background, features colorful fish swimming among plants and rocks, adding a dynamic element to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The face of the character in the video is slightly distorted, and the hands are twisted."
}
] |
seed46_1805
|
videos/HRA_part2/1805.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 capybara wearing a stethoscope and a lab coat, akin to a doctor, energetically jumps in slow motion against a vibrant green meadow background, capturing the joy and playfulness of the moment. The capybara's enthusiastic leap is highlighted by its joyful facial expression and the picturesque setting, blending elements of fantasy and nature.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's limbs generation in the video is problematic."
}
] |
seed42_1643
|
videos/HRA_part0/1643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic European ring-necked pheasant, with its vibrant plumage featuring striking shades of green, gold, and brown, struts confidently across a grassy field. Its iridescent feathers shimmer in the sunlight, accentuated by the lush green vegetation in the background. The pheasant pauses, its head held high, showcasing the distinctive white collar around its neck and the bold red wattles near its eyes. It then resumes its stately walk, tail feathers fanning out gracefully, embodying the elegance and beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The pheasant in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2206
|
videos/HRA_part2/2206.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 firefighter, clad in full gear and a yellow fire-resistant jacket, methodically mops the floor of a fire station common room, which features a pool table, a large flat-screen TV, and a couch. The mop bucket sits nearby, and the firefighter's focus and precision in cleaning contrast with the typically rugged image associated with firefighting. The scene highlights the everyday tasks and responsibilities of firefighters when they are not actively battling fires, emphasizing the importance of maintaining a clean and orderly living environment within the station.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's mopping action in the video is basically normal, but there is some lack of coordination."
}
] |
seed42_1921
|
videos/HRA_part0/1921.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 doctor, wearing a white lab coat over casual clothes, finds himself unexpectedly digging with a shovel in the middle of a large, empty lot overgrown with grass, as if searching for something specific. The contrast between his professional attire and the task at hand highlights the unusual nature of the situation. He pauses to wipe sweat from his brow, revealing a look of intense determination. In another scene, he continues to dig with the same shovel, now more dirt-stained, while the afternoon sun casts a warm glow over the desolate lot, emphasizing the solitary and strenuous nature of his endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_1924
|
videos/HRA_part2/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2227
|
videos/HRA_part0/2227.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 vibrant woman with a charming smile, wearing a casual graphic T-shirt and dark jeans, is laughing joyously. Her laughter is contagious as she throws her head back, her wavy brown hair cascading down her shoulders. The scene is set in a cozy living room with wooden floors and a white couch, adding to the warm and intimate atmosphere. Her joyful expression, complete with closed eyes and a wide grin, radiates happiness, making the viewer feel like they're sharing in her delight.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1975
|
videos/HRA_part2/1975.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 handsome waiter, dressed in a white shirt, black vest, and striped tie, walks through a bustling market, surrounded by vibrant stalls selling fruits, vegetables, and spices. The scene captures him navigating the lively crowd, his confident stride and focused gaze highlighting his purposeful movement. Market vendors and customers are visible in the background, adding to the dynamic atmosphere of the location. The waiter's attire contrasts with the colorful market environment, emphasizing his role as he moves through this energetic space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2459
|
videos/HRA_part0/2459.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 brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's action of cleaning the chimpanzee's face with white fabric is basically normal, but there is some lack of coordination."
}
] |
seed44_2448
|
videos/HRA_part1/2448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's mouth and hands in the video have generation issues; in the middle frame, the chimpanzee's body passes directly through a branch, and there are three forelimbs appearing."
}
] |
seed42_2041
|
videos/HRA_part0/2041.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, flat halibut fish is showcased on a wooden cutting board, its right side facing upward, displaying a clean, unblemished surface. The fish, with a length exceeding two feet, is set against a background of green herbs, lemon wedges, and a chef's knife, evoking a culinary preparation scene. The halibut's left eye is positioned prominently on the top side, indicating the fish's freshness, while its gills are slightly open, revealing the vibrant red color within. The overall setup, with the halibut as the central focus, is meticulously arranged to highlight the quality and size of the fish, perfect for a gourmet seafood dish.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3195
|
videos/HRA_part2/3195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform and badge, stands against a gray wall, his right hand visibly trembling. The scene is set in an urban environment, with a tall building in the background and a street sign visible, adding to the realism. The officer's face is tense, his eyes closed, indicating inner turmoil or stress. The shaky hand, holding nothing, is the focal point, conveying a sense of unease or emotion in this otherwise static setting.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand in the video is deformed, and the video overall does not conform to reality."
}
] |
seed44_2996
|
videos/HRA_part1/2996.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 director, wearing a black puffer jacket and dark cap, oversees a futuristic space sports event. He is surrounded by a vast, otherworldly landscape, with distant celestial bodies visible in the sky. Athletes in high-tech gear compete in zero-gravity, performing acrobatic maneuvers against the backdrop of a grandstand filled with spectators. The scene is dynamic, featuring fast-paced action and dramatic wipe transitions between shots, capturing the intensity and spectacle of the extraterrestrial competition.]"
},
{
"from": "gpt",
"value": "Normal. The director's facial generation in the video is uncoordinated, with the head and hands being distorted in the middle frames."
}
] |
seed46_1094
|
videos/HRA_part2/1094.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 space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1729
|
videos/HRA_part0/1729.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 adorable otter, with a round face and curious eyes, walks on its hind legs across a wooden boardwalk, holding a small fish in its front paws. It wears a tiny red scarf around its neck, adding a touch of whimsy to the scene. The otter's brown fur contrasts against the light wooden planks, while the lush greenery and calm water of a pond can be seen in the background, creating a serene and picturesque environment. The otter's confident stride and the fish it carries suggest it has just enjoyed a meal, making the scene both charming and heartwarming.]"
},
{
"from": "gpt",
"value": "Bad. The otter's hind legs move very awkwardly in the video, and its movements are not coordinated."
}
] |
seed44_1059
|
videos/HRA_part1/1059.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 artistic individual, adorned in a red jacket, blue jeans, and a white t-shirt, explores the vibrant streets of Tokyo, holding a sketchbook and pencil. The bustling cityscape surrounds him, featuring neon signs, crowded sidewalks, and eclectic architecture. Suddenly, the scene shifts to a serene indoor swimming pool, where the same artist is seen diving into the water, the reflection of the pool lights creating a mesmerizing pattern on the ceiling. The artist swims with grace and determination, their red swim cap standing out against the blue water, encapsulating a moment of tranquility amidst the urban chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not coordinated."
}
] |
seed42_1443
|
videos/HRA_part0/1443.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 surprising and surreal scene, a large, gray rhinoceros leaps into the air, defying expectations, with its powerful legs extended and body arched. This incredible moment is captured against a backdrop of a vast savanna landscape, dotted with trees and stretching to a distant horizon under a bright blue sky. The rhino, known for its heavy, armored skin and imposing horn, is shown mid-jump, creating a unique and unforgettable image that highlights the animal's unexpected agility and strength.]"
},
{
"from": "gpt",
"value": "Bad. The rhino's body in the video is abnormal."
}
] |
seed42_1107
|
videos/HRA_part0/1107.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 surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's head and paws in the video have generation issues."
}
] |
seed44_1257
|
videos/HRA_part1/1257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a red jacket, gray beanie, and blue jeans, hikes through a dense forest with sunlight filtering through the trees, casting dappled shadows on the trail. They pause to observe a small stream, the water gently flowing over rocks, before continuing on the path, notebook in hand, ready to capture inspiration from nature's beauty. The scene focuses on the writer's contemplative gaze, the vibrant colors of autumn leaves surrounding them, and the peaceful atmosphere of the woodland setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's hands and legs appear deformed."
}
] |
seed42_1683
|
videos/HRA_part0/1683.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 janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2589
|
videos/HRA_part2/2589.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 chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1305
|
videos/HRA_part0/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1981
|
videos/HRA_part2/1981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse environment filled with neatly stacked crates and industrial kitchen equipment, a chef clad in a white uniform and black trousers sprints down the aisles with determination. His arms swing energetically, and his gaze is set forward, indicating urgency and purpose. Behind him, the bustling activity of the kitchen continues, with chefs in white coats busily preparing meals. The chef races past stainless steel shelves stocked with food supplies, his black shoes pounding against the concrete floor, highlighting the dynamic energy of the scene. Throughout, the warehouse's high ceilings and industrial aesthetic provide a distinctive backdrop to the chef's energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has missing limbs and blurred facial features."
}
] |
seed42_2334
|
videos/HRA_part0/2334.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 teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1564
|
videos/HRA_part1/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Normal. The alpaca walks basically normally, but the movements are not smooth and coordinated."
}
] |
seed44_1300
|
videos/HRA_part1/1300.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 brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The artist's drawing movements in the video are not very smooth and coordinated."
}
] |
seed44_2022
|
videos/HRA_part1/2022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown plaid shirt and blue jeans, stands in the shallow end of a clear blue swimming pool, looking curiously at a squirrel perched on the edge. The squirrel, standing upright on its hind legs, holds a nut in its paws and peers intently into the water. Sunlight filters through the leaves of nearby trees, casting dappled shadows on the pool's surface and the green grass surrounding it. The farmer, with a straw hat tilted back on his head, seems to share a moment of mutual interest with the bushy-tailed creature, both pausing in their day's activities.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's movements in the video are not smooth."
}
] |
seed46_2632
|
videos/HRA_part2/2632.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 during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The capybara jumping mentioned in the caption does not appear in the video."
}
] |
seed46_2760
|
videos/HRA_part2/2760.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 with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_3034
|
videos/HRA_part2/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the actor pushing a snow removal tool to clear the snow on a suburban driveway, with basically normal movements, but there is some lack of coordination."
}
] |
seed42_2254
|
videos/HRA_part0/2254.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 janitor, middle-aged with short, neatly trimmed brown hair and a well-groomed beard, pauses in his cleaning duties. Dressed in a dark green uniform with a name badge, he rests a mop against a pristine white wall. His eyes meet the camera, and he gives a slow, deliberate nod, acknowledging an unseen presence. The setting is a spotless, modern school hallway, with large windows casting soft light onto the polished floor, highlighting the cleanliness maintained by the janitor.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed46_1288
|
videos/HRA_part2/1288.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 dingo, exhibiting a reddish-brown coat and alert demeanor, crawls near the base of a lush, cascading waterfall set within a dense, verdant forest. The waterfall, framed by towering trees and vibrant foliage, provides a dramatic backdrop as it plunges into a clear pool below, where the dingo stealthily approaches. The animal's cautious movement, combined with the serene yet powerful presence of the waterfall, creates a captivating scene of nature's raw beauty and untamed spirit.]"
},
{
"from": "gpt",
"value": "Bad. The dingo in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_2890
|
videos/HRA_part0/2890.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 doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2737
|
videos/HRA_part0/2737.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 tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]"
},
{
"from": "gpt",
"value": "Normal. The moose's mouth and antlers generation in the video have issues."
}
] |
seed42_1300
|
videos/HRA_part0/1300.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, clad in a brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's head is distorted, with twisted arms."
}
] |
seed42_1968
|
videos/HRA_part0/1968.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 lone coyote, characterized by its brown and gray fur, alert ears, and a bushy tail, traverses the lush rainforest floor. It walks purposefully among the vibrant green foliage, moss-covered logs, and fallen branches, creating a path through the dense undergrowth. The scene is set in a temperate rainforest, where the air is misty and moist, enhancing the rich greens and browns of the environment. The coyote's journey is filled with the sounds of dripping water and rustling leaves, as it explores this verdant, wet habitat.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated, and there are sudden changes."
}
] |
seed42_1262
|
videos/HRA_part0/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the legs are severely distorted."
}
] |
seed46_160
|
videos/HRA_part2/160.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 majestic manta ray glides effortlessly through crystal clear waters, its vast wingspan casting a shadow on the sandy seabed below. The graceful creature is adorned with a constellation of spots and lines, unique to each individual, as it moves with a serene, almost meditative quality. Sunlight filters through the surface, creating a mesmerizing play of light around the manta ray, which occasionally flips upside down to feed on plankton near the water's surface, showcasing its acrobatic abilities in the vibrant marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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 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": "Normal. The moose's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1550
|
videos/HRA_part1/1550.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 teacher, wearing a gray crew neck shirt, khaki pants, and black shoes, is seen from above, loading a stainless steel dishwasher in a well-lit kitchen. The kitchen features white cabinets, a white refrigerator, and a gray countertop. The teacher, with short brown hair and glasses, carefully places dishes into the lower rack of the dishwasher. In another angle, the teacher, now wearing a gray shirt and dark pants, continues loading the dishwasher, placing a cup in the upper rack. The room is brightly lit, with white walls and ceiling, and the teacher's focused expression conveys a sense of routine and responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1970
|
videos/HRA_part0/1970.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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Normal. The worker's finger generation in the video has minor issues."
}
] |
seed42_1758
|
videos/HRA_part0/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and arms are missing in the video, her face is poorly generated, and parts of her clothing are also missing."
}
] |
seed44_2899
|
videos/HRA_part1/2899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic gray wolf, framed by a moonlit night, runs through a dense forest, its powerful muscles rippling beneath thick fur. Its piercing yellow eyes glow with determination as it bounds over mossy logs and fallen branches, leaving a trail of displaced leaves in its wake. The wolf's large paws, equipped with sharp claws, grip the damp earth, propelling it forward with grace and strength. Surrounding the action, tall trees loom overhead, their branches swaying gently in the breeze, casting eerie shadows that dance across the wolf's path as it continues its relentless pursuit through the darkened woods.]"
},
{
"from": "gpt",
"value": "Normal. The gray wolf's movements in the video are slightly unsmooth."
}
] |
seed42_2757
|
videos/HRA_part0/2757.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 cartoon style, a cheerful nurse with rosy cheeks, bright eyes, and a traditional uniform is depicted mid-jump, with a small, friendly rat leaping alongside her. Both the nurse and the rat display exaggerated expressions of joy and excitement, capturing a sense of playful camaraderie. The nurse's outfit is crisp and clean, adding to the overall upbeat and carefree atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2223
|
videos/HRA_part0/2223.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 an unexpected scene, a mongoose, typically found in natural habitats, explores an industrial zone with caution, navigating through rusty pipes and concrete structures. Suddenly, it encounters a small pool of water, possibly from a recent rain, and surprisingly dips its paw in, showing curiosity about the liquid in this unusual environment. The mongoose then proceeds to swim gracefully, defying expectations of its usual terrestrial behavior, amidst the backdrop of industrial decay and urban grit. This juxtaposition highlights the animal's adaptability and resilience in an unorthodox setting.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_287
|
videos/HRA_part1/287.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 cheerful nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the nurse cleaning the window, with actions that are not continuous and smooth, showing a lack of coordination."
}
] |
seed44_1450
|
videos/HRA_part1/1450.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": "Bad. The movements are not smooth, there are sudden changes."
}
] |
seed44_2800
|
videos/HRA_part1/2800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through the crisp, blue sky, its powerful wings outstretched against a backdrop of puffy white clouds. The eagle's piercing yellow eyes and sharp, curved beak are sharply detailed. It effortlessly glides over a vast, serene lake, surrounded by lush, green coniferous trees and a rugged mountain range. The eagle's regal presence is highlighted by the sun's golden rays filtering through the clouds, casting a warm glow on the landscape below. The bird's brown and white feathers ruffle in the wind as it continues its graceful flight, embodying freedom and strength in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The bald eagle's flying movements in the video are not coordinated."
}
] |
seed44_2221
|
videos/HRA_part1/2221.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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Normal. Claws appear deformed and misshapen."
}
] |
seed46_2267
|
videos/HRA_part2/2267.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 waiter, clad in a white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2128
|
videos/HRA_part0/2128.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 woman, wearing a beige jacket and dark pants, walks her dog on a lead in a suburban neighborhood. She strolls along the pavement, passing by a row of neatly trimmed hedges and uniform houses with red roofs, creating a sense of domestic tranquility. The dog, a medium-sized brown and white spaniel, trots obediently beside her, its leash held gently in the woman's hand. As they walk, the afternoon sun casts long shadows, highlighting the peacefulness of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the dog's movements are not smooth."
}
] |
seed46_1683
|
videos/HRA_part2/1683.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 janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Bad. The face and hands of the character in the video have generation issues."
}
] |
seed42_3111
|
videos/HRA_part0/3111.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 creative writer, dressed in a gray sweater and blue jeans, steps out from a charming cottage, holding a small trash bag. She walks purposefully down a stone path, surrounded by lush greenery and flowers, to reach a large wooden bin. The scene is set in the golden hour, with soft sunlight filtering through the trees, casting a warm glow on the idyllic setting. The writer pauses for a moment, looking contemplative, before depositing the trash bag into the bin. The peaceful atmosphere and natural beauty of the surroundings provide the perfect backdrop for her daily routine, offering a glimpse into the simple yet meaningful moments in the life of an artist.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the writer walking on the stone path, with basically normal movements, but there is some lack of coordination."
}
] |
seed46_2057
|
videos/HRA_part2/2057.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 chimpanzee, with its fur darkened by water, swims gracefully in a lush, green outdoor enclosure, moving purposefully towards the camera. It shares the water with another chimpanzee, both navigating their environment with ease. In the next scene, the chimpanzee, now soaking wet, interacts playfully with another chimp in the water, highlighting their social bond. Finally, a lone chimpanzee, drenched from swimming, sits pensively at the edge of the water, offering a captivating close-up of its expressive face, all set against a backdrop of dense foliage and trees.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed46_3066
|
videos/HRA_part2/3066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2092
|
videos/HRA_part1/2092.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 charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs and facial features in the video are generated abnormally."
}
] |
seed46_1871
|
videos/HRA_part2/1871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]"
},
{
"from": "gpt",
"value": "Bad. The actions are discontinuous."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.