video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1757
|
videos/HRA_part0/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant woman wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show Lara holding a branch as mentioned in the caption."
}
] |
seed44_2597
|
videos/HRA_part1/2597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown vole walks purposefully across a lush, green meadow, its round body and short legs visible as it moves through the tall grass. The scene is set against a backdrop of vibrant flora, with the vole's movement drawing attention to its determination. Its fur is textured and rich in detail, and its eyes are alert and curious as it navigates the natural landscape. The vole's path is unobstructed, allowing for a clear view of its journey through the verdant field.]"
},
{
"from": "gpt",
"value": "Normal. The hamster walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed46_2610
|
videos/HRA_part2/2610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray suit with a blue shirt and striped tie, stands in a modern office space. He is attentively checking a smoke detector mounted on the ceiling, exhibiting a careful and professional demeanor. The office features a large window offering views of a city skyline, a desk with a laptop and documents, and a bookshelf filled with law books, creating a setting that blends professionalism with safety awareness. The lawyer's actions highlight the importance of routine safety checks in a workplace environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted in the video."
}
] |
seed46_2134
|
videos/HRA_part2/2134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, its body a rich tapestry of brown and orange hues, sprawls across a rocky reef, each of its eight muscular arms adorned with a series of suckers. Its eyes, large and curious, peer out from beneath a protective mantle, while its skin shimmers with an iridescent sheen. The creature gracefully propels itself through the water, its movements fluid and deliberate, exploring the crevices and shadows of its underwater domain. Surrounded by a vibrant ecosystem of coral and marine life, the octopus showcases its intelligence and adaptability, a true master of its environment.]"
},
{
"from": "gpt",
"value": "Bad. The octopus in the video is deformed."
}
] |
seed42_1595
|
videos/HRA_part0/1595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a receding hairline, glasses, and a gray beard, is depicted in a series of vignettes scrubbing various surfaces in a bathroom. In the first frame, he vigorously cleans the bathtub, wearing a black turtleneck sweater, khaki pants, and black shoes, his attire contrasting with the task at hand. Next, he is seen on his knees, scrubbing the floor tiles with the same intensity, his clothing now slightly disheveled. Then, he appears focused on cleaning the toilet bowl, his attire unchanged, showcasing his determination to tackle household chores. Lastly, he is shown wiping down the sink countertop, his attire still formal despite the domestic activity, highlighting the juxtaposition of his professional persona with the mundane task of bathroom cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The scene generated shows two men wiping."
}
] |
seed46_2384
|
videos/HRA_part2/2384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman named Martin, donning a black blazer over a gray turtleneck, sits in a high-end bar with wooden accents and modern light fixtures. He looks thoughtfully into the distance with a slight smile, holding a glass of whiskey, embodying a sense of sophistication and mystery. The bar, featuring plush red seats and a vibrant atmosphere, provides a contrast to Martin's introspective demeanor, highlighting his unique presence among the lively crowd.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2937
|
videos/HRA_part0/2937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling fire station, a seasoned firefighter, clad in a navy blue uniform and a yellow reflective vest, expertly operates a coffee machine. The walls are adorned with firefighting equipment and memorabilia, adding to the authenticity of the setting. The firefighter, with a rugged beard and a focused gaze, pours the freshly brewed coffee into a white mug with the fire department's emblem. The room is illuminated by natural light streaming in from a large window, casting a warm glow on the firefighter as he adds a touch of cream to his coffee, embodying a moment of calm amidst the high-stakes environment of emergency response.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2113
|
videos/HRA_part2/2113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray jacket over a white shirt and black pants, is hard at work unclogging a drain in a dimly lit room. He kneels on the floor, his focus intense as he uses a metal tool to clear the clog. The scene is framed by pipes and machinery, emphasizing the industrial setting. His work is meticulous, as he carefully removes debris from the drain, revealing the inner workings of the pipe. Throughout, his dedication to the task is evident, as he ensures the drain is thoroughly cleared, the water now flowing freely, with the satisfaction of a job well done apparent in his demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and the object in his hand undergo deformation and mutation, and the man's feet are not fully generated."
}
] |
seed42_2809
|
videos/HRA_part0/2809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a cunning weasel, dressed in a crisp white waiter's outfit with a black bow tie, gracefully crawls across a wooden floor, passing beneath a table draped with a pristine white cloth. The weasel's sleek body and sharp features are accentuated by the warm glow of candlelight, casting dramatic shadows as it moves stealthily, weaving between the legs of ornate chairs. Its eyes gleam with mischief, hinting at some secretive mission unfolding among the unsuspecting diners.]"
},
{
"from": "gpt",
"value": "Normal. The weasel in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_151
|
videos/HRA_part2/151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, iridescent green with a vibrant red throat, hovers over a cluster of pink flowers, its wings a blur of motion against the serene blue sky. It extends its slender beak into a flower, feeding on nectar, while perched on a thin branch. The bird then takes flight, moving gracefully from one flower to another, showcasing its agility against a backdrop of lush green foliage and clear, cloudless sky. Throughout, the hummingbird remains the focal point, its rapid wing beats and delicate features highlighted against the peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The bird's feet were not generated in the video."
}
] |
seed42_1
|
videos/HRA_part0/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the jackal in the video are missing."
}
] |
seed42_1003
|
videos/HRA_part0/1003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a sleek, form-fitting spacesuit, adorned with intricate details and a VR helmet, is seen in a futuristic, high-tech room filled with advanced equipment. He leaps into the air, seemingly weightless, as the virtual environment around him simulates the zero-gravity conditions of space. The room is illuminated by soft, ambient lighting, highlighting the man's movements as he trains for space missions, surrounded by screens displaying complex data and simulations. The focus remains on the astronaut in the center of the room, his body language conveying determination and excitement as he experiences the thrill of jumping in a virtual space environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and uncoordinated."
}
] |
seed44_2432
|
videos/HRA_part1/2432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, displaying strength and agility, leaps from a branch in a lush, green forest. The primate, with its dark fur and distinctive features, bounds through the air with a sense of freedom and vitality. As it lands, the chimpanzee's powerful muscles are evident, showcasing the raw energy and grace inherent in its movements. Surrounded by dense foliage and dappled sunlight, the scene captures the essence of life in the wild, focusing on the chimpanzee's leap as a symbol of untamed spirit.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee in the video has a twisted body, head, feet, legs, and arms."
}
] |
seed44_19
|
videos/HRA_part1/19.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning coral reef thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals in different shapes and sizes, ranging from brain coral to staghorn coral, create a textured landscape. The colors are rich and saturated, featuring shades of orange, red, purple, and green. The reef is teeming with life, as schools of colorful fish, such as angelfish and clownfish, swim gracefully among the corals. In the foreground, a curious sea turtle glides by, adding to the dynamic beauty of this marine ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1900
|
videos/HRA_part2/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Bad. The fox's legs appear deformed, and the book in its hands suddenly disappears."
}
] |
seed46_1910
|
videos/HRA_part2/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Normal. The position of the person's arm is incorrect."
}
] |
seed46_3159
|
videos/HRA_part2/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are distorted, and the cup in hand is distorted."
}
] |
seed46_2056
|
videos/HRA_part2/2056.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, sporting a clean-shaven face and a neatly tucked-in red shirt, diligently organizes items on a grocery store shelf. The store is devoid of customers, allowing him to focus on restocking with precision. He carefully places a can of beans onto the shelf, surrounded by other neatly arranged cans. His hands, free of gloves, handle each item with care, ensuring they are perfectly aligned. The well-lit supermarket aisle provides a clear view of the organized products, highlighting the cashier's attention to detail in his task.]"
},
{
"from": "gpt",
"value": "Normal. The restocking movements of the character in the video are not smooth."
}
] |
seed42_2657
|
videos/HRA_part0/2657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular build, wearing a blue shirt and dark pants, carefully hangs pictures on a living room wall. He uses a level tool to ensure perfect alignment, focusing intently on his task. Moments later, he steps back to admire the arrangement of frames, which include a variety of sizes and styles, creating a visually appealing gallery wall. The room is brightly lit, showcasing the art pieces against a neutral backdrop, with the man's satisfied expression indicating his pride in the finished display.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_160
|
videos/HRA_part1/160.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 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 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": "Normal. The manta ray swims basically normally in the video, but there is slight uncoordination in its movements."
}
] |
seed46_3028
|
videos/HRA_part2/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The artist's face and hands are distorted in the video."
}
] |
seed44_2532
|
videos/HRA_part1/2532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a blue and white checked shirt under his chef's jacket, walks through a dry scrubland with low vegetation, carrying a large branch over his right shoulder. The landscape is dotted with shrubs and small trees, with distant hills adding depth to the scene. The chef's casual attire, consisting of rolled-up sleeves and cargo pants, contrasts with his professional identity, creating an intriguing juxtaposition as he explores the rugged terrain.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers are missing in the video, the tree trunk is not generated on the shoulder, and the hand is not supporting the tree trunk."
}
] |
seed44_2167
|
videos/HRA_part1/2167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, typically a wild and elusive creature, is shown in an extraordinary scene, gently interacting with the sandy beaches of a coastal landscape. The bobcat, with its distinctive tufted ears and short tail, is depicted in a moment of unexpected tenderness, seemingly caressing the sand with its paw, a behavior rarely captured on camera. This unique encounter unfolds against the serene backdrop of a beach, where the gentle touch of the bobcat's paw on the sand challenges our perceptions of these usually solitary and fierce predators.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1244
|
videos/HRA_part1/1244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense, misty rainforest, a sleek black panther emerges from the undergrowth, its coat glistening with moisture. It pauses by a moss-covered tree trunk, the camera capturing every detail in high-definition clarity. The panther begins to groom itself, using its rough tongue to meticulously clean its fur, wiping away water droplets and debris, all against the lush, verdant backdrop of the rainforest environment. The focus is on the panther's self-cleaning behavior, highlighting the textures of its fur and the intricate patterns of the surrounding foliage.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the black panther's eyes in the video is problematic."
}
] |
seed44_2159
|
videos/HRA_part1/2159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a classic black vest and white shirt, serves a tray of colorful cocktails to a hyena lounging poolside. The hyena, wearing sunglasses and a lei, enjoys its day off from the wild, basking in the sun. Suddenly, the hyena leaps into the swimming pool with playful abandon, while the waiter looks on, amused yet professional, maintaining his composure despite the unexpected splash. The scene captures a surreal moment of relaxation and fun, blending elements of the exotic and the everyday.]"
},
{
"from": "gpt",
"value": "Normal. The hyena's movements in the video are not smooth."
}
] |
seed46_2947
|
videos/HRA_part2/2947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray sweatshirt with the sleeves rolled up, dark pants, and black gloves, stands on a ladder propped against a white house, cleaning the rain gutters. The scene is set in the backyard, with lush green grass and shrubs in the foreground. The artist's tools, including a trowel and a bucket, are visible as they scoop out debris from the gutters. The ladder leans against the house, providing support as the artist works diligently, the greenery and peaceful suburban setting creating a serene backdrop for this everyday task.]"
},
{
"from": "gpt",
"value": "Bad. The artist's movements to clear debris from the sink in the video are not smooth."
}
] |
seed42_2895
|
videos/HRA_part0/2895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An inventive engineer, donning a yellow hard hat and safety vest, stands beside a massive robotic mammoth at a pier, the structure's weathered wooden planks extending over the water. The mammoth, complete with tusks and a textured gray exterior, is connected to the engineer via cables and machinery. As seagulls fly overhead, the engineer leaps onto the mammoth's back, initiating an unexpected journey. The scene captures the juxtaposition of historical grandeur and modern engineering prowess, with the city skyline visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The mechanical mammoth's legs are twisted, and the engineer's hands are twisted."
}
] |
seed44_1393
|
videos/HRA_part1/1393.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 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, 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": "Normal. The actor in the video uses the towel to wipe their face in an unsmooth and uncoordinated manner."
}
] |
seed44_1362
|
videos/HRA_part1/1362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are unsmooth and somewhat uncoordinated."
}
] |
seed46_2506
|
videos/HRA_part2/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Bad. The camel's dancing movements can be clearly seen in the video, but the movements are not very continuous and smooth, and there is a lack of coordination in the camel's limbs."
}
] |
seed46_2367
|
videos/HRA_part2/2367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2992
|
videos/HRA_part1/2992.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman in a khaki safari outfit walks alongside a kangaroo in an Australian outback setting, both appearing relaxed and accustomed to each other's company. The kangaroo, with its distinctive marsupial pouch, hops gently beside her, while the woman, wearing a wide-brimmed hat and sunglasses, carries a walking stick and a backpack. They traverse a landscape dotted with eucalyptus trees and scrub, under a clear blue sky. The woman occasionally looks down at the kangaroo with a smile, highlighting the unusual yet harmonious companionship between human and wildlife in the vast, open wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2540
|
videos/HRA_part0/2540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a bustling metropolis, a police officer, clad in a navy uniform and cap, stands beside a large, friendly dog. The officer gently caresses the animal's head with a smile, forming a contrast against the urban backdrop of towering skyscrapers and busy streets. This tender moment between the law enforcer and the canine companion is captured against the steel and glass skyline, offering a glimpse of compassion amidst the city's concrete jungle.]"
},
{
"from": "gpt",
"value": "Bad. The caressing action is discontinuous, there are sudden changes."
}
] |
seed46_1287
|
videos/HRA_part2/1287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful swift bird, known for its agility, soars against a cloudy sky, its dark silhouette outlined by the bright horizon. It swoops and glides effortlessly, its wings and tail spread wide, navigating the air currents with precision. The bird's streamlined body, adapted for speed, cuts through the sky as it performs acrobatic maneuvers, demonstrating its remarkable flying skills. Against the vast, cloud-filled backdrop, the swift's aerial ballet continues, highlighting its unparalleled aerial prowess and freedom.]"
},
{
"from": "gpt",
"value": "Bad. The swallow's body is deformed, and its wings are twisted."
}
] |
seed42_2892
|
videos/HRA_part0/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Bad. The child's movements in the video are not smooth."
}
] |
seed44_2993
|
videos/HRA_part1/2993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single koala, with endearing dark eyes and a round face, clutches a branch of a eucalyptus tree with its sharp claws, its furry body swaying gently. It lovingly caresses the branch with its paw, displaying affectionate behavior typically seen between mother and joey. The koala's soft, thick fur and distinctive rounded ears are highlighted against the textured bark of the tree, creating a tender and captivating scene in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1801
|
videos/HRA_part2/1801.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy, wearing a gray jacket over a blue collared shirt, sits in a classroom with a concerned look on his face. He coughs into his elbow, drawing the attention of his peers. The room is filled with natural light, highlighting the concerned expressions of his classmates who are seated at their desks. A teacher, dressed in a dark blazer and light-colored shirt, stands nearby, watching the situation with a look of care and readiness to assist. The classroom is decorated with posters and artwork, giving it a homely and educational atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The boy in the video mostly hides his cough behind his hand, but there is some lack of coordination."
}
] |
seed44_104
|
videos/HRA_part1/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers were not fully generated."
}
] |
seed46_2322
|
videos/HRA_part2/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, hand is twisted, face is distorted, head is twisted, and legs are twisted."
}
] |
seed42_2562
|
videos/HRA_part0/2562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus with a grayish-brown body and long, flexible arms covered in small suckers rests on a rocky seabed. Its arms curl and extend as it explores its surroundings, demonstrating its intelligence and adaptability. The creature's large, curious eyes are visible as it interacts with the environment, showcasing its awareness and engagement. The octopus then changes color to blend in with the rocks, highlighting its remarkable camouflage abilities, all against the backdrop of an underwater world filled with various marine life and plants.]"
},
{
"from": "gpt",
"value": "Bad. The octopus's tentacles were generated abnormally, and there were issues with the head generation."
}
] |
seed42_2173
|
videos/HRA_part0/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2045
|
videos/HRA_part1/2045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, walks through a bustling cityscape filled with towering skyscrapers, neon signs, and busy streets. It navigates the urban environment with a curious yet calm demeanor, passing by modern architecture and city life, creating a surreal juxtaposition between nature and metropolis. The panda's presence among the high-rise buildings and urban hustle highlights an unexpected encounter between wildlife and the human-built world.]"
},
{
"from": "gpt",
"value": "Bad. The panda's head and limbs in the video have generation issues, with the limbs suddenly disappearing or reappearing in middle frames."
}
] |
seed42_3117
|
videos/HRA_part0/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2832
|
videos/HRA_part1/2832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow vest and hard hat, finds an unexpected moment of joy as he dances alongside a graceful antelope in a vast, sunlit prairie. The worker, dressed in blue jeans, a white t-shirt, and sturdy boots, moves with surprising agility, mirroring the antelope's leaps and bounds. The antelope, with its distinctive horns and russet coat, engages in this whimsical dance, seemingly unfazed by the unusual partnership. Together, they create a surreal and delightful scene against the backdrop of a clear blue sky and distant rolling hills.]"
},
{
"from": "gpt",
"value": "Bad. In the video, workers and antelopes can be seen dancing, but the movements are not continuous and smooth, with sudden changes in the limbs of the worker in between frames."
}
] |
seed46_1296
|
videos/HRA_part2/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2255
|
videos/HRA_part2/2255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, clad in a brown jacket, gray beanie, and khaki pants, dances gleefully in a grassy field under a partly cloudy sky, with rolling hills in the background. An ibex, standing nearby, observes the farmer's antics with curiosity. The farmer, his face etched with lines from years of hard work, performs a series of playful dance moves, his boots kicking up tufts of grass. The ibex, its horns curving gracefully upward, seems to mimic the farmer's movements, creating an unexpected yet charming duet between man and animal. Throughout the scene, the farmer's joyful expressions and the ibex's inquisitive gaze capture the essence of an unlikely friendship forged in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1567
|
videos/HRA_part2/1567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant garden filled with vibrant flowers and greenery, two young children, a boy and a girl, are happily engaged in gardening activities under a clear blue sky. The boy, wearing a red shirt and khaki shorts, attentively waters plants with a small watering can, while the girl, clad in a pink dress and white shoes, diligently digs soil using a tiny shovel. They both wear wide-brimmed hats to shield them from the sun. Nearby, a wooden bench sits beside a stone walkway, and a white picket fence surrounds the garden, completing the idyllic scene of youthful enthusiasm and nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The boy's movements are not smooth."
}
] |
seed44_2236
|
videos/HRA_part1/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the wild dogs playing and swimming in the pool are not very continuous, and the male cashier's hand movements while processing transactions are also discontinuous."
}
] |
seed46_1497
|
videos/HRA_part2/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2929
|
videos/HRA_part2/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are not smooth."
}
] |
seed42_2921
|
videos/HRA_part0/2921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet harmonious scene, a veterinarian, dressed in a khaki safari outfit, carefully tends to a young rhinoceros in a spacious, fenced enclosure, with lush greenery visible in the background. The compassionate doctor gently examines the rhino, which is lying on a sandy surface, seemingly at ease. The rhinoceros, displaying signs of improvement, attempts to crawl forward on its front legs, indicating a recovery from a recent ailment or procedure, all under the watchful eye of the dedicated wildlife doctor.]"
},
{
"from": "gpt",
"value": "Bad. The veterinarian's movements in the video are not smooth."
}
] |
seed44_1668
|
videos/HRA_part1/1668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sweeping natural landscape, a large bison is rolling on the ground, seemingly wiping itself in the dirt, surrounded by tall grass and distant mountains under a clear blue sky. The bison, with its shaggy brown fur, is seen from various angles, including a close-up of its face as it looks up, showing its rugged features and expressive eyes. Another shot captures the bison from above, highlighting its massive size and the texture of its coat against the sandy ground. Lastly, the bison is shown standing, shaking off the dust, its powerful body and majestic presence commanding respect in its wild habitat.]"
},
{
"from": "gpt",
"value": "Normal. In the scene where the buffalo stands and raises its head, there is an issue with the generation of the buffalo's head."
}
] |
seed42_3025
|
videos/HRA_part0/3025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2046
|
videos/HRA_part0/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face and hands in the video have generation issues."
}
] |
seed44_2919
|
videos/HRA_part1/2919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a bobcat is gently caressing a gray cat on a sandy arena floor, both animals seated facing each other. The bobcat, displaying unusual friendliness, reaches out with a paw to touch the cat's face, while the cat responds with a curious gaze. The sandy arena floor provides a textured backdrop, emphasizing the unique interaction between these two feline species. Moments later, the bobcat leans in closer to the gray cat, its paw still extended in a tender gesture, as if sharing a moment of mutual understanding within the sandy enclosure.]"
},
{
"from": "gpt",
"value": "Bad. The cat's head generation in the video has problems, and the paws are deformed."
}
] |
seed42_2647
|
videos/HRA_part0/2647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, textured flounder fish lies on a bed of ice, its right eye large and prominent, gazing upwards. The fish is positioned diagonally, with its tail fin pointing towards the bottom right corner of the frame and its head facing upwards. Its skin exhibits a mottled pattern of brownish-grey tones, providing a realistic representation of the marine creature. The icy surface beneath the fish reflects a cool, bluish tint, adding depth and texture to the composition. Surrounding the flounder are shards of ice, creating a natural and authentic setting for the seafood display.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1631
|
videos/HRA_part1/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The dance moves of the teacher wearing a yellow dress and a hat in the video are basically normal, with slightly uncoordinated movements."
}
] |
seed44_2124
|
videos/HRA_part1/2124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, donning a high-tech suit and goggles, operates a gravity manipulation device in a sleek, futuristic lab. He sprints across the room, defying gravity as he runs upside-down on the ceiling, his movements fluid and purposeful. The device, a compact, intricate mechanism attached to his back, emits a soft glow, highlighting its active state. Around him, the lab is filled with advanced equipment and screens displaying complex data, emphasizing the cutting-edge nature of his work. Throughout the sequence, the engineer's confident expression and dynamic actions showcase the thrilling potential of gravity-altering technology.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, head, feet, legs, and arms."
}
] |
seed42_2668
|
videos/HRA_part0/2668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and black vest, crawls across a vibrant boardwalk, his face a mask of determination. Wooden planks stretch out beneath him, dotted with colorful umbrellas and lively beachgoers. The scene is bathed in warm sunlight, casting dramatic shadows from the boardwalk's railings and nearby beachside cafes. The waiter's unusual mode of transport draws curious glances from passersby, creating a surreal and engaging moment against the backdrop of a bustling seaside promenade.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2353
|
videos/HRA_part0/2353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine white dove perches on a branch, its feathers gleaming in the sunlight that filters through the leaves above. The bird turns its head, revealing one bright, alert eye. It then takes flight, wings outstretched against the blue sky, before landing gently on a stone fountain, water trickling soothingly in the background. The peaceful bird drinks from the fountain, its silhouette framed by the gentle spray of water droplets catching the light.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1089
|
videos/HRA_part2/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1329
|
videos/HRA_part1/1329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, dressed in a dark green shirt and brown trousers, sits on a wooden stool under the shade of a tree, engrossed in playing a portable keyboard. Nearby, a majestic elephant, adorned with intricate patterns on its body, stands calmly, its trunk reaching down to touch the musician's head in a tender gesture. The scene takes place in a lush, grassy environment, with the elephant's legs slightly bent, as if it were gently swaying to the music. The musician's fingers dance across the keys, creating a harmonious melody that seems to captivate both the human and the elephant alike.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1088
|
videos/HRA_part0/1088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic space library illuminated by soft, ambient lighting, a diligent worker clad in a sleek, form-fitting silver suit with integrated tech panels runs along a moving walkway. The vast shelves of books and digital archives tower above, reflecting the movement. The worker's focused gaze and the dynamic motion of running contrast with the static, orderly environment. Nearby, a robotic arm extends from the shelving to retrieve a book, highlighting the integration of technology and human effort in this advanced setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_3185
|
videos/HRA_part1/3185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 set within a dense boreal forest, a janitor, dressed in a brown jacket, khaki pants, and a gray cap, diligently wipes a transparent pane that seemingly divides the wilderness. Behind this glass, a majestic leopard prowls within its enclosure, observing the man with curiosity. The forest's lush greenery and tall coniferous trees envelop the surroundings, creating a vivid contrast against the man-made structure. The janitor, focused on his task, occasionally glances at the leopard, acknowledging the unusual juxtaposition of his cleaning duties amidst the wild environment.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements while wiping the glass in the video are not smooth."
}
] |
seed44_2866
|
videos/HRA_part1/2866.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with badge and name tag, black tactical vest, and duty belt adorned with various gear, is seen dancing joyously on a wooden deck. In his right hand, he holds a small hedgehog, which is safe and secure in a clear plastic container with air holes. The hedgehog, with its distinctively spiky quills and curious demeanor, peers out from within the container. Behind the officer, a lush garden with green hedges and vibrant flowers provides a lively backdrop, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are not smooth."
}
] |
seed46_1055
|
videos/HRA_part2/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted."
}
] |
seed44_1212
|
videos/HRA_part1/1212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild salmon, exhibiting vibrant hues of silver, red, and green, swims gracefully in a crystal-clear river, its scales shimmering under the natural sunlight filtering through the water. The salmon's powerful body and forked tail are showcased as it propels itself upstream against the current, highlighting its determination and strength in nature's challenging environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3196
|
videos/HRA_part2/3196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black tank top, dark jeans, and a silver necklace, stands against a backdrop of a sandy beach and clear blue skies. He jumps into the air, guitar in hand, against the stunning landscape of palm trees and a pristine shoreline. His silhouette is highlighted by the golden hour sunlight, casting a warm glow over the scene. The camera captures the moment of mid-air suspension, emphasizing the dynamic energy of the performance, with the tranquil beach serving as a picturesque contrast to the vibrant action.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2493
|
videos/HRA_part2/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1496
|
videos/HRA_part0/1496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, wearing a brown shirt and denim overalls, drives a futuristic lunar buggy across a vast, barren moon landscape, dotted with craters and boulders under a starlit sky. Suddenly, the scene transitions to a serene, earthbound setting where the same farmer is seen leisurely floating on an inflatable raft, fully clothed, in the middle of a tranquil, crystal-clear lake surrounded by lush greenery. The peaceful atmosphere is punctuated by the occasional splash as the farmer gently moves through the water, enjoying a refreshing break from his daily chores.]"
},
{
"from": "gpt",
"value": "Bad. In the Earth scene, the proportions of the farmer's face and hands are incorrect."
}
] |
seed46_2215
|
videos/HRA_part2/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1596
|
videos/HRA_part0/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1838
|
videos/HRA_part0/1838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 somber space funeral setting, a lone janitor, dressed in a black suit and tie, leaps gracefully over a floating row of mops and brooms that are held aloft by unseen forces, against the backdrop of a distant, glowing nebula. His face is marked with determination, and his movements are fluid and controlled, as if dancing among the stars. The funeral attendees, dressed in various mourning attire, watch him in awe, their expressions a mix of grief and admiration. The scene is both surreal and poignant, capturing the unique juxtaposition of everyday duties and extraordinary circumstances in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2934
|
videos/HRA_part2/2934.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, wearing a dark suit and carrying a leather briefcase, walks with purpose across a dimly lit, gritty urban environment. Simultaneously, a CGI weasel, also dressed in a miniature lawyer's outfit complete with a bow tie and a tiny briefcase, scurries alongside the human lawyer. Both characters navigate through the cityscape, which features brick walls, fire escapes, and a sense of the urban jungle. The juxtaposition of the human lawyer and the anthropomorphized weasel lawyer adds a layer of whimsy and metaphor to the scene, suggesting themes of cunning and legal maneuvering.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2786
|
videos/HRA_part0/2786.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged student, wearing a gray t-shirt and apron, stands in a small, dorm-like kitchen filled with natural light. They are preparing a meal, chopping vegetables on a cutting board placed on a countertop cluttered with cooking utensils and ingredients. The student, with a look of concentration, moves with practiced ease, flipping a pan on a stove top where steam rises from a pot. The atmosphere is casual and homely, with posters and notes adorning the walls, giving a glimpse into the student's daily life. Throughout, the student's enthusiasm for cooking is evident in their animated expressions and gestures, creating a vibrant and engaging scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed46_1617
|
videos/HRA_part2/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2707
|
videos/HRA_part2/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Bad. The otter handling coins and banknotes behind the cash register in the video has discontinuous actions, and there is a mutation in the otter's paws."
}
] |
seed46_2720
|
videos/HRA_part2/2720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over casual attire, skillfully prepares dinner in a modern kitchen with stainless steel appliances and granite countertops. He expertly chops vegetables on a wooden cutting board, using a sharp chef's knife, while a pot simmers on the stove, releasing aromatic steam. The kitchen is illuminated by soft overhead lights, casting a warm glow over the scene. Behind him, a large window displays an urban skyline at twilight, adding a touch of sophistication to the domestic setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1487
|
videos/HRA_part2/1487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a realistic zebra, complete with black and white stripes, finds itself crawling under a barrier typically found at train stations. The striped animal moves slowly and carefully, its body almost touching the ground, as it navigates beneath the yellow and black-striped barrier. The train station's typical features, such as tracks, platforms, and overhead signs, are visible in the background, adding to the surreal nature of the scene. The zebra's unusual behavior in this urban setting creates a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_318
|
videos/HRA_part2/318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged female teacher waves energetically with both hands, standing against a classroom backdrop filled with educational posters and a whiteboard. Dressed in a vibrant red blouse and dark pants, she wears a welcoming smile, her wavy brown hair framing her face. Her enthusiastic gesture conveys warmth and inclusivity, inviting students into the learning environment. The classroom setting includes rows of desks, a bookshelf, and a large window allowing ample natural light, enhancing the sense of openness and engagement.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's waving in the video is basically normal, but there is a slight lack of coordination in the movements."
}
] |
seed42_1721
|
videos/HRA_part0/1721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful firefighter, clad in full gear, including a red coat, yellow reflective strips, and a helmet, dances energetically on a busy Shanghai street. The urban landscape, featuring modern skyscrapers and bustling city life, provides a stark contrast to his joyful movements. Pedestrians and traffic, including cars and a bus, surround him, highlighting the unexpected nature of his dance. Despite the urban chaos, he moves freely, a bright spot in the gray cityscape, his figure standing out against the backdrop of tall buildings and moving vehicles.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3173
|
videos/HRA_part1/3173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with a coat of dark fur and a muscular build, sprints across a lush, green savanna landscape, kicking up small clouds of dust with each stride. The chimp's powerful limbs propel it forward with agile determination, showcasing its natural athleticism in a vivid display of movement. As it runs, its eyes are fixed ahead, ears pressed back, and mouth slightly open, revealing a tongue panting from exertion. The background features tall grass swaying in the breeze and scattered acacia trees under a vast, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1197
|
videos/HRA_part1/1197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 plush koala toy, donning a red pilot's cap and a blue jacket, is placed on a model airport set, complete with miniature airplanes and runways. Suddenly, the koala begins to dance, swaying side to side with its arms raised, against a backdrop of a bustling airport terminal, filled with travelers and overhead announcements. The stuffed animal continues its lively jig, spinning around on the toy runway, surrounded by small figurines of people and luggage carts, capturing the imagination and playfulness of travel and adventure.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated, and there are sudden changes."
}
] |
seed42_3211
|
videos/HRA_part0/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is not smooth."
}
] |
seed44_1115
|
videos/HRA_part1/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The man's dance moves in the video are not fluid, there are abrupt changes, and the continuity of the mammoth's movement is poor."
}
] |
seed46_248
|
videos/HRA_part2/248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand movements are not continuous, there is a sudden change."
}
] |
seed46_1901
|
videos/HRA_part2/1901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows that the teacher's action of changing the battery of the electronic timer is not smooth and continuous; in one frame, the electronic timer suddenly turns into a stack of papers."
}
] |
seed42_2541
|
videos/HRA_part0/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2892
|
videos/HRA_part2/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Bad. The child's face is distorted, hands are twisted, and arms are twisted."
}
] |
seed44_260
|
videos/HRA_part1/260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a yellow t-shirt and khaki shorts, sits at a wooden desk in a rural backyard, typing on a laptop while referencing notes about wormhole travel. Nearby, a brown chicken pecks at the ground, seemingly curious about the writer's work. The scene then shifts to show the writer swimming in a clear blue pool, contemplating the mysteries of the universe and wormhole navigation. The camera captures the water droplets on the writer's face, hinting at the fluidity of time and space, while the chicken watches from the poolside, adding a touch of whimsy to the intellectual exploration.]"
},
{
"from": "gpt",
"value": "Normal. The writer is missing the wooden desk and the notebook. The chicken is missing the scene of pecking at the ground."
}
] |
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 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": "Normal. The character's actions of wiping the control machine in the video are basically normal, with some minor inconsistencies."
}
] |
seed44_1033
|
videos/HRA_part1/1033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young Asian student, wearing a yellow jacket and khaki pants, walks down a city street with a pet gerbil peeking out of his jacket pocket. The gerbil, visible from the side, has small ears and a round body, adding a touch of whimsy to the scene. The student's attire includes a dark shirt under the yellow jacket, and his pants are neatly tucked into white socks and brown shoes. The urban setting features a crosswalk and pedestrians in the background, providing context to the student's journey.]"
},
{
"from": "gpt",
"value": "Normal. The dark shirt, white socks, and brown shoes of the person in the video, and the pedestrians did not appear."
}
] |
seed46_2516
|
videos/HRA_part2/2516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike sequence, a lone firefighter, clad in full gear and helmet, is engaged in an interpretive dance within a vast, subtropical desert landscape. The horizon showcases a blend of orange and purple hues, reminiscent of a dramatic sunset. Suddenly, a majestic bison emerges from the distant dunes, its silhouette outlined against the fading light. It watches the dancing firefighter with a curious gaze, as if understanding the emotive performance unfolding before it in the midst of the arid, desolate environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the firefighters and the buffalo in the video are not smooth."
}
] |
seed46_1274
|
videos/HRA_part2/1274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2546
|
videos/HRA_part2/2546.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, and the face is slightly distorted."
}
] |
seed42_1019
|
videos/HRA_part0/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1144
|
videos/HRA_part2/1144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a diverse group of four people, two women and two men, collaborate on preparing a feast. One woman, wearing a patterned apron over a floral dress, chops vegetables on a wooden cutting board placed on a granite countertop. Beside her, a man in a chef's jacket stirs a large pot on a professional stove, steam rising from the simmering contents. Another woman, donning a red bandana and denim jacket, carefully seasons a dish with herbs and spices, while the last man, clad in a checkered shirt, monitors the grill, flipping sizzling meats with tongs. The atmosphere is lively, with laughter and clinking utensils adding to the sense of camaraderie and shared purpose among the cooks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3153
|
videos/HRA_part2/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's head generation in the video is abnormal."
}
] |
seed46_257
|
videos/HRA_part2/257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mesmerizing cuttlefish, displaying a captivating array of color patterns, gracefully hovers in its underwater environment. It exhibits intricate skin textures and hues, from rich purples to vibrant yellows, against a dark blue ocean backdrop. Its large, expressive eyes and eight arms, adorned with suckers, are prominently featured. The cuttlefish then changes its coloration to mimic the sandy seafloor, showcasing its remarkable camouflage abilities, all within the serene, deep-sea habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2580
|
videos/HRA_part1/2580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are basically normal, but there is slight disharmony."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.