video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2988
|
videos/HRA_part2/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2445
|
videos/HRA_part0/2445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene grassland setting under a clear blue sky, a police officer, clad in a standard uniform with a badge and gun holster, kneels by a small, clear pond. He watches intently as a group of children joyfully splash and swim in the water, their laughter echoing across the open landscape. The officer's presence is both protective and relaxed, creating a harmonious scene where law enforcement and community enjoyment coexist peacefully amidst the natural beauty of the vast, green grasslands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2587
|
videos/HRA_part2/2587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and whimsical scene, a Bactrian camel with two humps, typically found in desert environments, is seen swimming in crystal-clear waters. The camel, with its shaggy brown coat and large, curious eyes, moves gracefully through the water, its head held high above the surface. The backdrop features lush greenery and palm trees, contrasting the camel's usual habitat. The setting sun casts a warm glow over the landscape, creating a surreal and captivating moment where desert meets sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1955
|
videos/HRA_part0/1955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket, a diverse group of people, including a young woman with long brown hair tied in a bun, wearing a black jacket over a gray shirt and black leggings, and a man in a red shirt and blue jeans, are joyfully dancing to an upbeat tune. Amidst the aisles filled with groceries, a person dressed in a comical weasel costume joins the impromptu dance party, adding to the festive atmosphere. The weasel, with its oversized head and expressive features, moves energetically among the dancers, who are all smiling and enjoying the spontaneous fun in the brightly lit store.]"
},
{
"from": "gpt",
"value": "Bad. The faces and limbs of people in the video are distorted."
}
] |
seed46_1802
|
videos/HRA_part2/1802.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a red and white striped shirt, dark pants, and a vibrant tiger head costume, energetically dances in front of a large crowd at a lively pep rally. The atmosphere is electric, filled with cheering fans and the spirit of school pride. The young man, donning the mascot's full-body suit complete with furry orange and black stripes, performs dynamic dance moves to the beat of an upbeat marching band, captivating the audience with his animated antics. Surrounded by enthusiastic supporters waving banners and flags, the scene pulses with excitement and unity, perfectly capturing the essence of collegiate spirit.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted legs."
}
] |
seed44_2356
|
videos/HRA_part1/2356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a white lab coat over a blue shirt and khaki pants, sneezes dramatically while working in a clean, well-lit laboratory filled with advanced technology and scientific equipment. The scene captures the unexpected moment as he leans over a workstation, his glasses momentarily fogging up, surrounded by computers and high-tech machinery, emphasizing the contrast between the precision of his work and the human element of a simple sneeze.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers and facial features in the video have generation issues."
}
] |
seed46_1427
|
videos/HRA_part2/1427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded musician wearing a brown cap, gray jacket, and blue jeans ascends a rocky cliff face, demonstrating his adventurous spirit. He skillfully plays a small drum-like instrument called a tambourine, attached to his harness, merging his passion for music with his love for climbing. The scene captures his fearless determination, with the tambourine adding a unique touch to his climbing gear, as he conquers the steep rock formation against a dramatic, cloudy sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1612
|
videos/HRA_part1/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's laughing in the video is basically normal, with slight inconsistency."
}
] |
seed46_1061
|
videos/HRA_part2/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Bad. The student's hands were not generated in the video."
}
] |
seed44_2075
|
videos/HRA_part1/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's limbs and tusks are missing in the video."
}
] |
seed44_2388
|
videos/HRA_part1/2388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bearded chef, donning a red baseball cap, a gray t-shirt, and green apron over his attire, is seen energetically cleaning a car in a vibrant, sunny setting. He begins by rinsing the vehicle with a hose, water spraying from the nozzle. Then, he proceeds to wash the car using a large sponge, applying soapy suds to its surface. Next, he uses a squeegee to remove excess water, ensuring a streak-free finish. Lastly, he dries the car with microfiber towels, his movements demonstrating thoroughness and care, all while maintaining his lively demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The chef's hand in the video has issues, and the pipe is not generated."
}
] |
seed46_2699
|
videos/HRA_part2/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1013
|
videos/HRA_part2/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2687
|
videos/HRA_part0/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The female engineer's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_2983
|
videos/HRA_part1/2983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a hyena leaps gracefully over pipes and machinery in an industrial oil refinery, backlit by the golden glow of sunset. The animal, wild and untamed, seems momentarily suspended in mid-air above the cold, metallic structures. Its spotted coat contrasts starkly with the urban landscape, highlighting the unusual and unexpected nature of this scene. Despite the hard edges of the refinery, there's a sense of fluid motion as the hyena propels itself forward, embodying a blend of natural agility and industrial might.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3196
|
videos/HRA_part1/3196.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, 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": "Bad. In the video, it is clearly visible that the musician jumps into the air while holding a guitar, but the movements are very discontinuous and unsmooth, with the musician's limbs suddenly changing and flying around in the middle frames."
}
] |
seed42_2226
|
videos/HRA_part0/2226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a peaked cap, kneels in a park surrounded by green grass and trees, gently caressing a small brown hare with soft, comforting strokes. The officer's compassionate expression and careful handling of the hare, which sits calmly in the palm of his hand, convey a sense of tenderness and care. The peaceful setting, with the lush vegetation and clear sky, adds to the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_254
|
videos/HRA_part1/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The workers mentioned in the caption do not appear in the video."
}
] |
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 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, 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": "Bad. The limbs of the chimpanzee in the video are generated twisted and deformed, and the face is generated blurry."
}
] |
seed44_1670
|
videos/HRA_part1/1670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, lit by neon lights, a diverse group of reality TV contestants from the show 'Mongoose' gather in the communal area. One contestant, a young woman with a purple mohawk, gently caresses a small, robotic mongoose, designed to mimic Earth wildlife. The robot mongoose, covered in metallic fur, responds with affectionate whirrs and beeps. The background features sleek, metallic surfaces and screens displaying space vistas, creating an atmosphere of high-tech comfort. The other contestants, dressed in colorful, futuristic outfits, watch with curiosity and amusement, their expressions a mix of fascination and relaxation.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is slightly distorted, the hands are distorted, the small robot's body is distorted, the face is distorted, and the arms are distorted."
}
] |
seed44_2114
|
videos/HRA_part1/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2354
|
videos/HRA_part0/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1504
|
videos/HRA_part1/1504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate teacher, wearing a gray shirt and dark pants, sits cross-legged on a green yoga mat placed atop a lush lawn, gently caressing a small vole. She holds the tiny creature in her right hand, her face reflecting warmth and care, as she looks down at it lovingly. The vole, nestled in her palm, seems relaxed and comfortable, its presence offering a tender moment of connection between human and nature, under the shade of a large tree.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1655
|
videos/HRA_part2/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit in the video has missing limbs, multiple eyes, and a broken tail."
}
] |
seed46_3193
|
videos/HRA_part2/3193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 leopard, distinguished by its golden fur and intricate rosette patterns, sprints across a sun-drenched savanna. Its muscles ripple powerfully beneath its coat, demonstrating raw strength and agility. The leopard's piercing green eyes remain focused ahead, indicating determination and purpose in its stride. It bounds gracefully over the landscape, leaving a trail of displaced grass in its wake, embodying the essence of wild freedom and survival instinct.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2832
|
videos/HRA_part2/2832.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. The video shows workers and antelopes dancing, with movements that are not continuous and smooth, and there is a lack of coordination."
}
] |
seed44_2107
|
videos/HRA_part1/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, body, and the item in their hand are distorted in the video."
}
] |
seed42_1433
|
videos/HRA_part0/1433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene, two children, a boy and a girl, sprint across a grassy area with wide smiles, dressed in casual play clothes—a red T-shirt and blue shorts for the boy, and a floral dress for the girl. Suddenly, the focus is on the boy as he runs with gleeful determination. Then, the girl takes center stage, her pigtails bouncing as she races forward. The action culminates with both children laughing and running together, their eyes filled with joy, all while a gorilla statue stands watchfully in the background, adding a touch of whimsy to the playful atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed44_2348
|
videos/HRA_part1/2348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate brown sandals."
}
] |
seed44_2718
|
videos/HRA_part1/2718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a busy city bus stop, two cheerful children wearing swimsuits and holding floaties wait alongside their mother, who wears a yellow dress. The scene is vibrant, with the bus stop shelter adorned with colorful graffiti and the city skyline visible in the background. Suddenly, a double-decker bus approaches, its exterior painted with a striking zebra pattern. As the bus pulls up, the children look up in awe, their excitement palpable as they prepare to board for what seems like an adventurous day ahead.]"
},
{
"from": "gpt",
"value": "Good. There are no obvious problems."
}
] |
seed42_2517
|
videos/HRA_part0/2517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a white shirt, beige pants, and a traditional headscarf, is seen wiping the face of a brown camel with a white cloth. The action takes place in a sandy environment, with other camels standing in the background, creating a scene that highlights the care and connection between the worker and the animal. The worker's focused expression and gentle touch convey a sense of respect and familiarity, while the setting sun casts a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand in the video is distorted, the item in their hand is distorted, and the camel's face is distorted."
}
] |
seed46_1651
|
videos/HRA_part2/1651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a costume reminiscent of the 1920s, complete with a flapper dress and feather headband, dances gracefully amidst the lush greenery of a temperate rainforest. Sunlight filters through the dense canopy, casting dappled shadows on the forest floor. The actor performs a series of fluid movements, twirling and leaping with the elegance of a seasoned performer, while the vibrant flora and fauna of the rainforest provide a stunning natural backdrop. The atmosphere is one of enchantment and vitality, as the dancer's artistry harmonizes with the beauty of the ancient woodland.]"
},
{
"from": "gpt",
"value": "Bad. The body movements of the person in the video are not coordinated."
}
] |
seed42_1517
|
videos/HRA_part0/1517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_2095
|
videos/HRA_part0/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1112
|
videos/HRA_part2/1112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Bad. The leg generation of the brown male wild in the video is problematic."
}
] |
seed42_2779
|
videos/HRA_part0/2779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1846
|
videos/HRA_part1/1846.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a red flannel shirt, blue jeans, and brown boots, runs alongside a spirited golden retriever in a lush green park. Both the musician and the dog display expressions of pure joy and freedom. The musician, equipped with a backpack, is in mid-stride, while the dog bounds ahead, tail wagging. The scene captures the essence of a carefree day in the park, with the musician's attire and the dog's enthusiastic demeanor setting the tone for a playful and energetic outing.]"
},
{
"from": "gpt",
"value": "Normal. The arms, hands, and legs of the person in the video are twisted, as well as the dog's legs."
}
] |
seed44_113
|
videos/HRA_part1/113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker in a power plant environment is seen wiping down a large turbine with a yellow cloth, dressed in a navy blue uniform, complete with a shirt, trousers, and safety shoes. The scene captures the maintenance aspect of power generation, with the worker focused on cleaning the metallic surface of the turbine. The power plant's interior is visible, featuring high ceilings, large machinery, and industrial pipes, all bathed in artificial lighting. The worker's attire, which includes a hard hat and protective gloves, emphasizes safety protocols in the industrial setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1955
|
videos/HRA_part1/1955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 supermarket, a diverse group of people, including a young woman with long brown hair tied in a bun, wearing a black jacket over a gray shirt and black leggings, and a man in a red shirt and blue jeans, are joyfully dancing to an upbeat tune. Amidst the aisles filled with groceries, a person dressed in a comical weasel costume joins the impromptu dance party, adding to the festive atmosphere. The weasel, with its oversized head and expressive features, moves energetically among the dancers, who are all smiling and enjoying the spontaneous fun in the brightly lit store.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_1371
|
videos/HRA_part1/1371.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic display, a snake charmer clad in a richly colored red robe and matching turban leans forward, engaging intently with a king cobra emerging from a traditional wicker basket. The snake, adorned with intricate patterns, rises dramatically from the basket, its hood spread wide. The charmer's hands, decorated with silver bracelets, gently caress the serpent's body, emphasizing the bond between human and animal. The scene is set against a vibrant, patterned cloth, adding to the exotic atmosphere, with the charmer's face expressing both respect and control as he interacts with the majestic creature.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are twisted, the cobra's body is deformed, and the arms are twisted."
}
] |
seed44_2602
|
videos/HRA_part1/2602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in the sunlight, showcasing shades of green and purple against a blurred background of lush green foliage. The bird's beady eye and curved beak are sharply detailed, while its body language suggests alertness. Moments later, it takes flight, wings spread wide, revealing the full spectrum of its plumage's colors against the clear blue sky. The video concludes with a close-up of the starling's head, its distinctive features and vibrant feathers displayed prominently against a softly blurred green backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]"
},
{
"from": "gpt",
"value": "Bad. The towel in the actor's hand is deformed, and the kangaroo's head is distorted."
}
] |
seed44_2979
|
videos/HRA_part1/2979.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1739
|
videos/HRA_part1/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3208
|
videos/HRA_part1/3208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a red neckerchief and a brown apron, stands in a modern kitchen. He holds a large, open recipe book in his hands and writes with a silver pen, his face expressing deep concentration. The kitchen is filled with stainless steel appliances and shelves stocked with various cooking ingredients, creating a professional culinary atmosphere. The chef's sleeves are rolled up, revealing a watch on his wrist, and he occasionally glances up from the book, likely checking the progress of dishes being prepared in the bustling kitchen environment.]"
},
{
"from": "gpt",
"value": "Normal. The chef's actions of writing with a silver pen in the video are basically normal, with slight disharmony."
}
] |
seed46_2050
|
videos/HRA_part2/2050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a futuristic silver jacket and dark pants, races across the barren, rocky terrain of Mars under a stunning night sky filled with stars and two moons. The landscape features red soil and distant Martian mountains, with the Milky Way galaxy prominently visible above. The writer pauses mid-stride, gazing upwards in awe and inspiration, before continuing the run with determination, the dynamic scene capturing the essence of stargazing from the Red Planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1852
|
videos/HRA_part2/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2101
|
videos/HRA_part0/2101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome, young male actor sprints through a bustling train station, wearing a dark blue coat, khaki pants, and brown shoes, his face a mask of urgency and determination. The vibrant, crowded setting provides a dynamic backdrop, filled with diverse individuals going about their day. His intense gaze and focused posture convey a sense of high stakes, while the surrounding architecture and the moving crowd add depth and realism to the scene. The camera captures his swift movement from multiple angles, highlighting his purposeful stride and the energy emanating from him as he weaves through the throngs of travelers.]"
},
{
"from": "gpt",
"value": "Bad. There are problems with the generation of people in the background and the actor's arms in the video, with the actor's arms being distorted and deformed in the middle frames."
}
] |
seed42_1152
|
videos/HRA_part0/1152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are uncoordinated."
}
] |
seed44_2382
|
videos/HRA_part1/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, and there is an issue with the arm generation."
}
] |
seed44_32
|
videos/HRA_part1/32.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, complete with a tailored suit, tie, and leather briefcase, finds himself in an unexpected scenario: cleaning windows. With a microfiber cloth in hand, he meticulously wipes a large, clear window pane, revealing a cityscape beyond. The scene is set in a spacious office with modern decor, where natural light illuminates the room, highlighting the lawyer's dedication to detail in an unconventional task. Despite his professional attire, he approaches the chore with the same seriousness and precision as his legal work.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the lawyer can be clearly seen wiping the transparent window glass, with discontinuous movements and sudden changes."
}
] |
seed46_1817
|
videos/HRA_part2/1817.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 falcon soars through a cloud-filled sky, its piercing eyes and hooked beak sharply defined against the light. It dives gracefully, wings tucked, chasing an unseen prey over lush green fields dotted with wildflowers. The bird, adorned with a leather hood and jesses, lands on a gloved hand, presenting its fierce gaze and powerful talons. Its plumage, a mix of brown, white, and black, contrasts beautifully with the serene landscape, creating a stunning portrait of nature's hunter against a backdrop of rolling hills and a clear blue horizon.]"
},
{
"from": "gpt",
"value": "Bad. The action of the falcon folding its wings and landing on a gloved hand in the video is very discontinuous and unsmooth."
}
] |
seed44_1647
|
videos/HRA_part1/1647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean landscape fills the screen, with crystal clear water revealing a sandy bottom far below. Sunlight filters through the surface, casting dappled light on the scene. Suddenly, a magnificent manta ray enters the frame, its massive wings spanning wide as it glides effortlessly through the water. The creature is a stunning sight, its dark top and white underbelly contrasting beautifully against the blue surroundings. It performs an elegant somersault, showcasing its agility and grace, before continuing on its serene journey across the vast underwater expanse.]"
},
{
"from": "gpt",
"value": "Normal. The manta ray's body is generated disharmoniously, the head is not generated, and there are shadows on the sea surface."
}
] |
seed42_1330
|
videos/HRA_part0/1330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, stands on a small green step stool. He is in the process of screwing in a light bulb into a fixture, which is attached to a pale yellow ceiling. The room is sparsely decorated, featuring a white table, a beige office chair, and a bookshelf filled with books and binders. The doctor, with short brown hair and glasses, focuses intently on the task at hand, his sleeves rolled up to his elbows. The scene is lit by other functional light fixtures in the room, casting a warm glow over the doctor and his makeshift ladder.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed46_1057
|
videos/HRA_part2/1057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit studio, an artist sits at a desk, engrossed in sketching detailed cosmic phenomena, specifically the explosive aftermath of a white hole, depicted on a large sheet of paper. On the desk, a gerbil runs playfully, its movements occasionally distracting the artist. The artist, wearing a black beret and glasses, looks up pensively, perhaps inspired by the gerbil's antics. Then, the artist gently caresses the gerbil, which is now sitting still, as if bonding with the small creature, all while the cosmic illustration continues to take shape in the background.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's limb generation is problematic when running in the video, and there are sudden scene transitions in the middle frames."
}
] |
seed42_3185
|
videos/HRA_part0/3185.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal 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": "Good. Basically correct."
}
] |
seed42_2625
|
videos/HRA_part0/2625.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with hurried travelers, a dedicated doctor, clad in a white lab coat over a navy blue dress shirt and khaki pants, leaps energetically over a small gap between the platform and the train car. The scene captures the doctor's agility and determination amid the urban chaos, with the train's bright lights and the station's high ceilings providing a dramatic backdrop. Passengers watch in awe as the doctor, holding a brown leather briefcase, executes a perfectly timed jump, symbolizing the balance between professionalism and unexpected challenges in daily life.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements in the video are not smooth."
}
] |
seed46_2517
|
videos/HRA_part2/2517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a white shirt, beige pants, and a traditional headscarf, is seen wiping the face of a brown camel with a white cloth. The action takes place in a sandy environment, with other camels standing in the background, creating a scene that highlights the care and connection between the worker and the animal. The worker's focused expression and gentle touch convey a sense of respect and familiarity, while the setting sun casts a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted, the face is slightly distorted, the item in hand is distorted, and the camel's face is distorted."
}
] |
seed46_1083
|
videos/HRA_part2/1083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jungle setting, a group of intrepid explorers clad in khaki safari gear navigate a narrow, foliage-lined path, their expressions a mix of determination and awe. They pause momentarily, observing a majestic silverback gorilla ambling nearby, its powerful form moving gracefully through the underbrush. The gorilla, seemingly undisturbed by the presence of humans, continues its journey, highlighting the peaceful coexistence between wildlife and respectful visitors in this pristine natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the characters in the video are not smooth, and the actions are uncoordinated."
}
] |
seed42_1091
|
videos/HRA_part0/1091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-themed wedding set against a cosmic backdrop filled with stars and galaxies, a charming hedgehog, adorned with a tiny top hat and bow tie, serves as the ring bearer. The ceremony takes place on a floating platform amidst a zero-gravity environment. During the reception, the hedgehog enjoys a unique swimming experience in a clear, spherical water tank, effortlessly paddling with its limbs while maintaining its adorable appearance, all while the celebration continues around it.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's movements in the video are not smooth."
}
] |
seed46_1851
|
videos/HRA_part2/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1834
|
videos/HRA_part0/1834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic spacesuit, leisurely walks through the pristine, metallic corridors of a bustling space station habitat, illuminated by soft, ambient lighting. He pauses to gaze intently at the vibrant Earth through a large observation window, perhaps seeking inspiration. Continuing his stroll, he passes various crew members engaged in their duties, highlighting the station's active community. The writer then stops at a console, where he interacts with advanced technology, possibly researching or gathering information for his work. Throughout the scene, the space station's interior is depicted in high detail, emphasizing its functional yet sophisticated design.]"
},
{
"from": "gpt",
"value": "Normal. The head of the creative writer is deformed, and the crew members in the background appear distorted and deformed."
}
] |
seed42_2098
|
videos/HRA_part0/2098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin, distinguished by its long, pointed bill and sleek, torpedo-shaped body, gracefully glides through the clear, vibrant blue waters of the open ocean. Its striking silver scales glisten as sunlight filters through the water, illuminating its form. The marlin's powerful tail propels it forward with effortless ease, while schools of smaller fish scatter in its wake, highlighting the apex predator's presence in the underwater ecosystem. Against the vast, deep-blue backdrop, the marlin's silhouette is both awe-inspiring and a testament to the beauty and power of marine life.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a group of small fish scattering and fleeing behind a sailfish, but this scene does not appear in the video."
}
] |
seed42_2721
|
videos/HRA_part0/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1695
|
videos/HRA_part2/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. No smoke alarm was generated, the coffee table is white; the person in the video is not standing on a chair, and the guitar is not hanging around the person's neck."
}
] |
seed44_2407
|
videos/HRA_part1/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Normal. Failed to generate green forest."
}
] |
seed46_1507
|
videos/HRA_part2/1507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the boy and girl touching the camel's legs in the video are not smooth and coordinated, and the girl's hand suddenly disappears in the middle frame."
}
] |
seed44_2143
|
videos/HRA_part1/2143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crystal-clear waters, a vibrant butterfly fish, marked by striking black, yellow, and white patterns, gracefully hovers near a coral reef bustling with life. Sunlight filters through the water, casting a warm glow on the fish and its surroundings. The butterfly fish, known for its intricate design featuring a bold black stripe through the eye and a false eye spot on its tail, explores the nooks and crannies of the reef. It flutters among the corals, which are home to various sea creatures, adding to the dynamic underwater scene. Against this rich backdrop, the butterfly fish's fluid movements and striking colors stand out, creating a captivating display of marine beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1113
|
videos/HRA_part1/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The gray wolf's legs in the video are not fully generated."
}
] |
seed46_2059
|
videos/HRA_part2/2059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor kneels in a lush green forest, attentively examining a small, injured deer lying on the mossy ground. The deer, with its distinctive brown coat and white underbelly, looks up at the doctor with trusting eyes. The scene is peaceful, with sunlight filtering through the trees, casting dappled shadows on the forest floor. The doctor, wearing a green field jacket and khaki pants, gently touches the deer's leg, showing care and concern. Nearby, other deer stand watch, their ears perked, observing the interaction from a safe distance.]"
},
{
"from": "gpt",
"value": "Bad. The faces and limbs of the characters in the video are distorted, as well as the face and legs of the deer."
}
] |
seed46_3179
|
videos/HRA_part2/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3192
|
videos/HRA_part0/3192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed sports arena, a young female cashier, wearing a white apron over her outfit, diligently wipes down the countertop with a cloth. The background is vibrant, featuring neon lights and digital screens displaying scores from ongoing cosmic games. The cashier's actions are methodical, her focus intense, as she ensures the counter is spotless for the next customer in this bustling, intergalactic sports hub. Behind her, patrons in diverse alien attire wait patiently, adding to the dynamic atmosphere of this extraterrestrial venue.]"
},
{
"from": "gpt",
"value": "Bad. The female cashier's fingers are deformed, and the customer is generated abnormally in the video."
}
] |
seed44_3026
|
videos/HRA_part1/3026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a navy blue t-shirt and beige cargo pants, meticulously organizes his cluttered garage, transforming it into a space of efficiency and order. The scene opens with him standing amidst a disorganized mess, shelves packed with tools and miscellaneous items. He begins by sorting through the chaos, creating piles of items to keep, donate, or discard. As the process unfolds, the garage gradually becomes a well-ordered workspace, with tools neatly arranged on pegboards, shelves neatly stocked, and the floor cleared of debris. The engineer, now in a clean environment, proudly surveys his accomplishment, the once chaotic garage now a testament to his organizational skills.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's movements in organizing the garage in the video are not continuous and smooth, showing a lack of coordination."
}
] |
seed44_2641
|
videos/HRA_part1/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and the napkin disappears and reappears."
}
] |
seed46_269
|
videos/HRA_part2/269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, misty forest setting, a majestic bull moose with a full rack of antlers tenderly nuzzles a smaller female moose, both enveloped in the early morning light filtering through the trees. Their interaction is gentle and intimate, showcasing the softer side of these typically solitary creatures. The male's large, furry body and impressive antlers contrast with the delicate nature of their caress, highlighting the bond between them. The scene is set against a backdrop of lush vegetation and tall trees, creating a peaceful and private moment in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1829
|
videos/HRA_part0/1829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, captivating squid floats in the deep sea, its body a mesmerizing blend of purples and pinks, illuminated by bioluminescent lights. The creature's eyes are large and expressive, conveying intelligence and curiosity. Its tentacles, adorned with suckers, gracefully undulate in the water, while its two feeding tentacles extend forward, ready to capture prey. The intricate patterns on its skin shift and change, creating an otherworldly display as it moves through the dark, mysterious depths of the ocean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_204
|
videos/HRA_part0/204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled woman stands in a dimly lit classroom, adorned with scientific posters and models, wearing a blue shirt, black pants, and sneakers, holding a book titled 'Dark Matter'. She speaks passionately about dark matter research, gesturing toward a whiteboard filled with complex equations and diagrams. Suddenly, she transitions into a swimming instructor, standing poolside at an indoor swimming facility. Dressed in a blue swimsuit and cap, she demonstrates proper swimming techniques, her movements fluid and confident, as students watch attentively from the water. Throughout the scene, educational elements and swimming gear are prominently displayed, blending the worlds of academia and aquatic sports seamlessly.]"
},
{
"from": "gpt",
"value": "Bad. The classroom scene did not generate a middle-aged woman wearing a blue shirt, black pants, sneakers, holding a book titled 'Dark Matter,' and wearing glasses."
}
] |
seed46_1559
|
videos/HRA_part2/1559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_3156
|
videos/HRA_part1/3156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood, a majestic moose stands near a residential street, its large frame contrasting with the mundane setting. The creature is seen wiping its antlers on a tree branch, possibly marking its territory. The scene is set against a backdrop of houses and greenery, giving the impression of wildlife encroaching upon human living spaces. The moose, with its shaggy fur and imposing stature, interacts with its environment in a display of natural behavior, despite the suburban backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The moose in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed44_205
|
videos/HRA_part1/205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 renowned actor, wearing a brown costume resembling a moose, dances gleefully in a large, empty studio with high ceilings and exposed pipes. The overhead lights cast a warm glow on the wooden floor, highlighting the actor's animated expressions and exaggerated movements. The studio walls are adorned with abstract paintings and vintage movie posters, adding a whimsical touch to the scene. As the actor continues to dance, their enthusiasm is contagious, bringing a sense of joy and playfulness to the space.]"
},
{
"from": "gpt",
"value": "Bad. The video actor's limbs are missing, and the face and body generation are distorted."
}
] |
seed44_1350
|
videos/HRA_part1/1350.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, with its distinct black and white striped face and grey fur, walks purposefully across a lush, green meadow under the dappled shade of tall trees. It pauses for a moment, standing on all fours, to sniff the air with its keen sense of smell. Then, it continues its journey, moving with a slight waddle due to its sturdy build, leaving behind a trail in the soft grass. The scene is set in the peaceful serenity of nature, with the badger as the sole focus, highlighting its natural habitat and behavior.]"
},
{
"from": "gpt",
"value": "Normal. The badger in the video doesn't walk smoothly, and its movements are not very coordinated."
}
] |
seed46_1981
|
videos/HRA_part2/1981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse environment filled with neatly stacked crates and industrial kitchen equipment, a chef clad in a white uniform and black trousers sprints down the aisles with determination. His arms swing energetically, and his gaze is set forward, indicating urgency and purpose. Behind him, the bustling activity of the kitchen continues, with chefs in white coats busily preparing meals. The chef races past stainless steel shelves stocked with food supplies, his black shoes pounding against the concrete floor, highlighting the dynamic energy of the scene. Throughout, the warehouse's high ceilings and industrial aesthetic provide a distinctive backdrop to the chef's energetic run.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3186
|
videos/HRA_part1/3186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dedicated teacher, clad in a yellow raincoat, blue jeans, and brown boots, leads a group of students on a nature walk through a grassy field. In the distance, a majestic bison stands tall, its presence adding to the educational experience. The teacher points toward the horizon, engaging the students in a lesson about wildlife, with the bison serving as a captivating visual aid. The scene is set against a backdrop of rolling hills and a clear blue sky, creating an idyllic setting for learning and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's fingers in the video are deformed, and the bison's head is distorted."
}
] |
seed42_1889
|
videos/HRA_part0/1889.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An eccentric artist, donning a vibrant red beret and a multicolored, patterned jacket, is depicted in a studio filled with artistic clutter, including paintings, brushes, and easels. The artist is engaging in a lively dance, accompanied by a curious monkey wearing a tiny blue hat, which mirrors the artist's movements, creating a whimsical scene of creativity and playfulness set against a backdrop of artistic chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is distorted, with twisted facial expressions, arms, legs, and hands."
}
] |
seed42_1862
|
videos/HRA_part0/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's two ears in the video are of different sizes, the paws are missing, the whiskers are not generated, and the face is blurry."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a 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": "Good. No obvious problems."
}
] |
seed46_1045
|
videos/HRA_part2/1045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his handsome features and casual attire of a gray T-shirt and khaki pants, rakes a pile of autumn leaves in a backyard, surrounded by lush greenery and a wooden deck. He pauses to gaze thoughtfully into the distance, the rake resting on his shoulder, before resuming his task with renewed vigor. The scene is bathed in the warm, golden glow of late afternoon sunlight, casting long shadows across the yard and highlighting the vibrant colors of the fallen leaves. Throughout, the actor's expressive face conveys a range of emotions, from determination to contemplation, all while engaging in the simple, everyday activity of raking leaves.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_146
|
videos/HRA_part1/146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, sun-dappled deciduous forest during autumn, several joyful people gather for an impromptu dance party. The scene opens with a close-up of a smiling woman in a floral dress, her arms raised as she twirls under the golden leaves. Next, a group of friends, dressed in casual fall attire like sweaters and jackets, laugh and dance together, surrounded by tall trees and colorful foliage. The camera then captures a couple slow dancing romantically, their embrace tender and intimate, with the forest's warm hues providing a romantic backdrop. Lastly, the entire group comes together, forming a circle as they dance energetically, their laughter and the rustling leaves blending into a symphony of happiness in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are twisted."
}
] |
seed44_1353
|
videos/HRA_part1/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_1217
|
videos/HRA_part2/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1821
|
videos/HRA_part0/1821.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and body of the meerkat in the video are generated unreasonably, and the claws are not fully formed."
}
] |
seed46_3165
|
videos/HRA_part2/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hands and the brush in her hand appear deformed."
}
] |
seed46_2180
|
videos/HRA_part2/2180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast school of silver sardines elegantly maneuvers through the clear blue ocean, their synchronized movements creating mesmerizing patterns as they navigate around a large, rocky coral reef structure. Sunlight filters through the water, illuminating the fish and highlighting their metallic scales against the vibrant coral and lush underwater flora. The sardines' fluid dynamics and the contrast between their silvery bodies and the colorful marine environment create a stunning visual display in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The video shows too many silver fish, and some fish appear deformed."
}
] |
seed42_2021
|
videos/HRA_part0/2021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge, hat, and tactical vest, stands under a dimly lit streetlamp on a quiet, empty urban street at night. The officer's face is contorted in anguish, tears streaming down their cheeks, highlighting the emotional weight they carry. Their eyes are closed, and they're holding a tissue in one hand, indicating a moment of vulnerability amidst their duty. The scene conveys a powerful message about the human side of law enforcement, emphasizing the emotional toll it can take on those who serve.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2126
|
videos/HRA_part1/2126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a shimmering silver outfit reminiscent of celestial bodies, performs an interpretive dance against a backdrop of the Uranus aurora. The aurora, with its vivid green and purple hues, illuminates the scene with an ethereal glow. The actor's movements are fluid and expressive, capturing the essence of cosmic energy and the mystical atmosphere of the distant planet. As the dance progresses, the auroral lights pulsate and swirl, creating a mesmerizing visual harmony between the performance and the celestial phenomenon. Throughout the video, the focus remains on the captivating dance, with the Uranus aurora serving as a breathtaking and dynamic canvas for the actor's artistry.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, face, and body of the person in the video are distorted."
}
] |
seed46_3191
|
videos/HRA_part2/3191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, its woolly coat dark and shaggy, is seen wading through a cold, icy lake during the last Ice Age. Its large body creates ripples in the water, and it moves with a surprising grace for its size. The mammoth uses its tusks to navigate through the submerged branches and logs, demonstrating its adaptability to aquatic environments. Despite the freezing temperature, the mammoth appears comfortable, showcasing its ability to thrive in harsh conditions. The backdrop is a lush, green landscape with distant mountains, highlighting the diversity of habitats these ancient creatures inhabited.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2639
|
videos/HRA_part2/2639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a costumed individual, dressed as a rhinoceros, leaps dynamically across a vast, cosmic landscape, dotted with floating celestial orbs. Simultaneously, in a corner of this otherworldly setting, a solemn, space-themed funeral procession takes place, with attendees dressed in futuristic attire, paying their respects. Amidst this surreal backdrop, a figure, dressed as a stereotypical grocery store cashier, complete with a checkered shirt and name tag, stands at an unconventional checkout counter, processing transactions for the peculiar gathering, adding an element of mundanity to the extraordinary event.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2073
|
videos/HRA_part1/2073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2812
|
videos/HRA_part1/2812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green prehistoric landscape under a soft, cloudy sky, a large woolly mammoth tenderly caresses a smaller mammoth with its trunk. The smaller mammoth, likely a calf, stands close by, its body gently leaning into the larger mammoth, both enveloped in a moment of affection. The setting, with its rich vegetation and distant hills, provides a vivid backdrop for this intimate scene between two members of this ancient species.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's face and legs are distorted in the video."
}
] |
seed42_1037
|
videos/HRA_part0/1037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.