video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1561
|
videos/HRA_part1/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's fingers in the video are not fully generated, and the leg rotation is too large."
}
] |
seed44_1469
|
videos/HRA_part1/1469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_121
|
videos/HRA_part0/121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene indoor scene opens with a close-up of a calm, gray tabby cat sitting on a wooden floor next to a white wall. The cat, adorned with a blue collar, gazes intently at the camera. Suddenly, a human hand enters the frame from above, gently stroking the cat's head, evoking a relaxed response. The camera then captures the affectionate interaction from various angles, showcasing the cat's contentment and the tender touch of the unseen person, all within the cozy confines of a home environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video petting the cat is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_2383
|
videos/HRA_part1/2383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A thoughtful writer, clad in a brown jacket and blue jeans, traverses the sunlit chaparral landscape, his attire complemented by brown shoes and a backpack. He pauses to gaze into the distance, the vast expanse of shrubland stretching before him. Continuing his journey, he walks among the low-lying vegetation, the golden grasses swaying gently in the breeze. Occasionally, he stops to jot down notes, his focus intense, capturing the essence of his surroundings in his leather-bound journal. Throughout his walk, the chaparral scenery provides a serene backdrop, punctuated by the rustling of leaves and the distant call of birds.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the part mentioned in the caption where the person stops to take notes."
}
] |
seed44_1020
|
videos/HRA_part1/1020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, dressed in a navy pea coat, beige trousers, and brown shoes, is gracefully dancing in a large, empty room with polished wooden floors and high ceilings. In the background, a magnificent cat leaps playfully, its silhouette outlined by the warm glow of the rising sun, which streams through a window, casting a soft light on a potted plant. Mercury, visible as a bright star in the twilight sky outside, adds a celestial touch to the scene. The director's dance moves, captured in a series of fluid poses, convey a sense of joy and creative inspiration, while the cat's energetic jumps mirror the director's movements, creating a harmonious connection between the two.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and legs appear deformed and cut off, and the facial expressions of the human face have not been fully generated. The cat has two tails."
}
] |
seed44_1481
|
videos/HRA_part1/1481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An osprey, a large bird of prey with brownish-black and white plumage, soars majestically over a serene lake at sunset, its piercing yellow eyes scanning the water below for fish. The bird, with its distinctive head pattern and curved beak, effortlessly glides through the air, its wings spread wide, casting a shadow on the calm water. Suddenly, it dives into the lake with remarkable speed and precision, emerging moments later with a wriggling fish clasped firmly in its talons. As the osprey ascends back into the sky, the fading sunlight illuminates its powerful form, highlighting the intricate feather patterns and the determination in its eyes.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the osprey in the video is unreasonable, the wings are incomplete, and the claws are not fully generated."
}
] |
seed42_2890
|
videos/HRA_part0/2890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and the object in hand is also distorted."
}
] |
seed46_1101
|
videos/HRA_part2/1101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, clad in a simple white towel, stands poised at the edge of a natural hot spring, nestled amidst lush, green foliage. He leaps gracefully into the air, his body forming a perfect arc against the backdrop of steam rising from the water's surface. The sunlight filters through the leaves overhead, casting dappled shadows on the rippling water as he soars, suspended in a moment of weightless exhilaration before plunging into the warm, mineral-rich waters below.]"
},
{
"from": "gpt",
"value": "Bad. The diving in the video is very unsmooth, and the movements are quite uncoordinated."
}
] |
seed42_3220
|
videos/HRA_part0/3220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a janitor, clad in a yellow high-visibility vest and dark pants, walks alongside an antelope in a vast, grassy landscape. The two figures move in unison across the screen, the janitor pushing a red cleaning cart, while the antelope, with its distinctive horns and russet fur, trots gracefully beside him. The scene is bathed in golden sunlight, casting long shadows from both the janitor and the antelope as they traverse the serene environment together. Behind them, a row of tall, green trees provides a striking contrast to the open field, further highlighting the unusual companionship between the janitor and the wild animal.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1465
|
videos/HRA_part2/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2117
|
videos/HRA_part0/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers are missing in the video, and there are issues with the generation of his eyes, as well as problems with the generation of the porcupine's eyes and mouth."
}
] |
seed42_1684
|
videos/HRA_part0/1684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dingo, displaying its signature reddish-brown fur, crawls on all fours near the edge of a lush, green waterfall. The scene is set in a dense rainforest, with vibrant ferns and mossy rocks surrounding the cascading water. The dingo, appearing alert and curious, is framed against the mist rising from the falls, creating a dramatic contrast between the wild animal and the serene, powerful force of nature. The waterfall's roar provides a dynamic soundscape, further immersing the viewer in this untamed wilderness environment.]"
},
{
"from": "gpt",
"value": "Bad. The dingo in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2948
|
videos/HRA_part1/2948.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray t-shirt and blue jeans is kneeling beside a large aquarium, meticulously cleaning the glass with a scrubbing tool, his focus unwavering. The room is softly lit, casting a warm glow over the scene. Behind him, a bookshelf filled with various items can be seen, adding a sense of home to the environment. As he works, his dedication is evident in the careful strokes of the brush against the glass, ensuring every inch of the tank is spotless for the aquatic life within.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand in the video is deformed."
}
] |
seed44_2744
|
videos/HRA_part1/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The spectacled cobra's skin generation in the video is unnatural."
}
] |
seed44_2675
|
videos/HRA_part1/2675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, resembling Chris Hemsworth, waters plants in a lush, green backyard garden filled with various potted plants and trees. He wears a simple white tank top, brown cargo shorts, and brown flip-flops, giving off a casual, laid-back vibe. The scene is set during the day, with bright sunlight illuminating the vibrant greenery and highlighting the actor's chiseled physique. As he tends to the plants, he occasionally pauses to smile at the camera, showcasing his charming personality and the peaceful atmosphere of the garden.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_1247
|
videos/HRA_part0/1247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear with a helmet, runs with focused determination across a dimly lit urban landscape, carrying a baseball bat. The scene is set at night, with the firefighter's outfit illuminated by the glow of city lights. His face is obscured by a breathing apparatus, adding to the sense of urgency and mystery. The baseball bat, an unexpected accessory, swings in his grip as he sprints with purpose, the background filled with the blurred shapes of buildings and streetlights, creating a dynamic and compelling image.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_1397
|
videos/HRA_part1/1397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diverse group of characters gathers in a lush meadow under a clear blue sky. A male musician, dressed in a casual striped shirt, plays a ukulele, seated on a small wooden bench. Nearby, an animated gorilla, also wearing a striped shirt, energetically jumps into the air with excitement. The vibrant green grass and colorful flowers surrounding them add to the playful atmosphere, creating a harmonious blend of music, nature, and unexpected companionship.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the gorilla wearing a striped shirt as mentioned in the caption."
}
] |
seed46_1149
|
videos/HRA_part2/1149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 coral reef ecosystem teeming with life, a pair of butterfly fish, one black and one yellow, swim gracefully among the intricate coral formations. The black butterfly fish, adorned with white polka dots and a striking yellow tail, explores a crevice in the coral. Meanwhile, the yellow butterfly fish, featuring intricate black markings, hovers nearby. The scene is illuminated by the warm sunlight filtering through the clear blue water, casting a mesmerizing play of light and shadow on the diverse marine landscape.]"
},
{
"from": "gpt",
"value": "Normal. The mouth and eyes of the yellow butterfly fish were not fully generated."
}
] |
seed44_3055
|
videos/HRA_part1/3055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush green meadow, two majestic moose gently caress each other with their large, velvety noses, expressing tenderness and affection. They stand side by side, their dark coats contrasting beautifully against the vibrant flora surrounding them. One moose looks intently at its companion, while the other closes its eyes, savoring the intimate moment. Their antlers, impressive and intricate, frame their faces as they share this loving gesture, all captured in stunning high definition. The background is a harmonious blend of nature, with tall grass swaying gently in the breeze, creating a peaceful and idyllic setting for this touching wildlife interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2305
|
videos/HRA_part2/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The student's finger generation in the video has issues."
}
] |
seed42_2827
|
videos/HRA_part0/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2764
|
videos/HRA_part1/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's movements are not smooth."
}
] |
seed44_2339
|
videos/HRA_part1/2339.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3021
|
videos/HRA_part1/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Normal. The dog's movements in the video are not smooth."
}
] |
seed44_3106
|
videos/HRA_part1/3106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed46_2199
|
videos/HRA_part2/2199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1907
|
videos/HRA_part0/1907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark, rugged feathers, perches on a branch in a barren tree set against a cloudy sky. The bird's sharp eyes scan the surroundings, while its large wings remain folded, ready for flight. In the next scene, the vulture takes off, its powerful wings propelling it into the air as it begins to circle above the landscape, searching for carrion. The video then focuses on the vulture in mid-flight, its wings spread wide, gliding effortlessly through the air with a backdrop of rolling hills and distant mountains. Finally, the bird lands gracefully on a rocky outcropping, where it stands alert, surveying its territory with a commanding presence.]"
},
{
"from": "gpt",
"value": "Bad. The vulture's wings and claws appear deformed."
}
] |
seed42_1770
|
videos/HRA_part0/1770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistically dressed woman, adorned with face paint resembling a buffalo, performs an interpretive dance against a vibrant, textured backdrop reminiscent of theater curtains. Her ensemble includes a brown top, khaki pants, and brown shoes, complemented by the buffalo-inspired face art. She gracefully moves through a series of dance poses, her body language conveying emotion and storytelling. Behind her, the theater curtain texture adds depth and drama to the scene, encapsulating the essence of performance art.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2691
|
videos/HRA_part1/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted in the video."
}
] |
seed46_2892
|
videos/HRA_part2/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the video are slightly unsmooth."
}
] |
seed44_1706
|
videos/HRA_part1/1706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the surreal landscape of Neptune's gaseous atmosphere, rendered in vivid purples and blues, a meerkat stands alert amidst floating islands of icy material. The meerkat, wearing a small spacesuit with a clear helmet, wipes its face with a tiny cloth, perhaps to clean away condensation or space dust. The contrast between the meerkat's terrestrial behavior and the alien environment creates a whimsical and unexpected scene. Behind the meerkat, the swirling clouds of Neptune provide a dramatic backdrop, emphasizing the creature's isolation and the vastness of its surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat is missing the spacesuit and towel mentioned in the caption."
}
] |
seed44_1799
|
videos/HRA_part1/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Normal. The corner generation of the road in the video is problematic, and there is slight distortion in the facial features."
}
] |
seed42_1192
|
videos/HRA_part0/1192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_2671
|
videos/HRA_part2/2671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grey suit, white shirt, and patterned tie, walks purposefully across a grassy field under a twilight sky, carrying a large, transparent bag. In the distance, a comet streaks across the night sky, its tail glowing brightly. The lawyer pauses, turning his head to gaze up at the celestial phenomenon, his expression a mix of awe and determination. Despite the extraordinary sight, he continues his steady walk, the comet's light illuminating his path forward.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's walking movements in the video are basically normal, with slight disharmony."
}
] |
seed44_2095
|
videos/HRA_part1/2095.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit 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": "Good. Basically correct."
}
] |
seed42_1702
|
videos/HRA_part0/1702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with a thick, shaggy coat, powerful legs, and piercing yellow eyes, swims through a serene, crystal-clear lake surrounded by lush greenery. Its head is raised, showcasing determination, while water droplets glisten on its fur. The wolf's body, well-muscled and agile, propels it forward in the water, highlighting its surprising aquatic prowess. The landscape around the lake is lush and verdant, with tall trees providing a picturesque setting for this unexpected scene of a wolf navigating the water with ease and grace.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the gray wolf with multiple legs, and the mouth is generated slightly larger."
}
] |
seed42_1438
|
videos/HRA_part0/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2813
|
videos/HRA_part2/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's face is generated blurry, fingers are deformed, the water buffalo's head is abnormally generated, and in the middle frame, the police officer's hand goes straight through the water buffalo's mouth."
}
] |
seed42_2811
|
videos/HRA_part0/2811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a traditional conical hat and simple clothing, guides a strong water buffalo through a shallow, muddy waterway by holding onto its rope halter. The buffalo, with its large, curved horns and powerful body, crawls on its belly through the mire, demonstrating its strength and endurance. The farmer, with a focused look on his face, carefully navigates alongside the animal, highlighting the bond between man and beast in rural life. The scene takes place against the backdrop of lush green fields, emphasizing the agricultural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1150
|
videos/HRA_part0/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's body undergoes deformation and mutation during movements, and sometimes deformities appear."
}
] |
seed44_2783
|
videos/HRA_part1/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teenage girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video uses the sewing machine basically fine, but her movements are slightly uncoordinated."
}
] |
seed44_2395
|
videos/HRA_part1/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2528
|
videos/HRA_part2/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's head and limbs are generated abnormally in the video, with its limbs twisting, deforming, or suddenly disappearing in the middle frames."
}
] |
seed46_3016
|
videos/HRA_part2/3016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige chinos, gently caresses a kangaroo in an Australian outback setting, surrounded by shrubbery and distant hills. The engineer, wearing safety goggles around his neck, interacts affectionately with the kangaroo, which stands on the ground, both under a clear blue sky. The kangaroo, with its distinctive marsupial pouch, is calmly accepting the engineer's touch, while the engineer's attire and demeanor suggest a blend of professionalism and compassion in this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2232
|
videos/HRA_part2/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_188
|
videos/HRA_part1/188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, a species of wild mountain goat, is shown crawling on all fours across a rocky terrain. The scene is set in a mountainous region, with steep cliffs and rugged landscape providing a challenging environment for the animal. The ibex is depicted in a vulnerable position, moving slowly and deliberately as it navigates the uneven surface. Its body is in a low, crawling stance, highlighting its agility and strength in adapting to harsh conditions. The camera captures this intimate moment in high definition, focusing solely on the ibex as it crawls, emphasizing the creature's resilience and survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The goat in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1965
|
videos/HRA_part2/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Bad. The hawk's wings in the video have issues, and the claws and eyes were not generated."
}
] |
seed42_2440
|
videos/HRA_part0/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Normal. The chicken's head is not fully generated."
}
] |
seed44_2743
|
videos/HRA_part1/2743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, equipped with a backpack, ascends a lush, green mountain trail, pausing occasionally to jot down thoughts in a small notebook. He wears a gray t-shirt, brown shorts, and sturdy hiking boots, while his glasses reflect the sunlight as he looks up at the dense forest canopy above. With a determined look, he continues climbing, passing by a wooden signpost indicating various trails. At one point, he stops to admire the view, taking in the breathtaking scenery of rolling hills and distant mountains, before resuming his upward journey, the camera capturing the vivid colors of nature surrounding him.]"
},
{
"from": "gpt",
"value": "Normal. The writer's face in the video is generated blurry, fingers are deformed, and there are issues with the feet."
}
] |
seed46_325
|
videos/HRA_part2/325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the chimpanzee leaping on a wooden structure, with discontinuous movements and abrupt changes."
}
] |
seed46_202
|
videos/HRA_part2/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Normal. The girl's fingers, toes, and face generation have issues, and the boy's finger generation also has problems."
}
] |
seed46_1588
|
videos/HRA_part2/1588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vast, sunlit savannah, two zebras engage in a tender moment, their striped bodies gently touching as they caress each other. One zebra, with its mane flowing in the breeze, nuzzles the face of another, their bond evident in the softness of their interaction. The scene is framed by distant acacia trees and a clear blue sky, emphasizing the intimacy shared between these majestic creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The zebra's movements are not smooth."
}
] |
seed44_2512
|
videos/HRA_part1/2512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a black suit and white shirt, complete with a bow tie and name tag, holds a silver serving tray with a glass of red wine as he runs swiftly through a vast, meticulously maintained cemetery. The grass is neatly trimmed, and the tombstones are lined up in perfect rows, extending into the horizon under a clear blue sky. Suddenly, a cheetah appears, running alongside the waiter, matching his pace effortlessly. Both the waiter and the cheetah continue their run through the peaceful graveyard, the cheetah's spots contrasting against the greenery, while the waiter remains composed, maintaining a professional demeanor despite the unusual circumstances.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2027
|
videos/HRA_part0/2027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the children in the video have generation issues, with distortion and deformation appearing in the middle frames."
}
] |
seed46_2459
|
videos/HRA_part2/2459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_1986
|
videos/HRA_part2/1986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning a gray t-shirt and black tactical pants, meticulously assembles a wooden dresser in a sparsely decorated room. Sunlight filters through a nearby window, casting warm shadows across the scene. The firefighter, complete with a gray tank top, dark tactical pants, and a muscular build, expertly constructs the furniture piece, showcasing his versatility beyond firefighting. The focus is on his hands as they skillfully tighten screws and align panels, revealing a side of firefighters' capabilities often unseen. Against a backdrop of a partially painted wall, the firefighter continues to assemble the dresser, demonstrating precision and care typically associated with his primary occupation.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1585
|
videos/HRA_part1/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Normal. The actor in the video has missing limbs generation, fingers are not fully generated, and eyes are not generated."
}
] |
seed44_3211
|
videos/HRA_part1/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is not smooth."
}
] |
seed42_2303
|
videos/HRA_part0/2303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a wooden desk in a dimly lit room, wearing a white shirt with rolled-up sleeves and a black blazer, intently drawing on a large sketchbook with a mechanical pencil. The focus is on his hands, which hold the pencil and manipulate its grip, while the rest of his body remains still. The background shows the texture of the wooden desk, and the man's right hand rests on the edge of the sketchbook, as he leans forward with his left elbow on the table, cradling his chin with his hand. The scene conveys a sense of concentration and dedication to the craft of drawing.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted in the video."
}
] |
seed46_2172
|
videos/HRA_part2/2172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1238
|
videos/HRA_part0/1238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a European starling perched on a branch, its vibrant plumage shimmering with hues of green and purple under the sunlight. The bird's beady eye is fixed ahead, and its feathers appear ruffled, as if enjoying a gentle breeze. The starling's curved bill and round body are distinct against the blurred green foliage in the background, creating a contrast that highlights the bird's intricate details. The scene is set in a serene forest environment, where the starling seems unperturbed by the camera, offering a rare glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The bird's head turning in the video is basically normal, but there is a slight lack of coordination in the movement."
}
] |
seed46_1509
|
videos/HRA_part2/1509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a majestic stag with an impressive set of antlers leads a herd of deer through a narrow path, their movements graceful and unhurried. The camera captures their journey from a low angle, emphasizing the size and strength of the animals. The lush greenery surrounds them, providing a natural backdrop that complements their brown coats. As they walk, the sound of their hooves softly hitting the ground echoes through the woods, creating a serene atmosphere. The herd moves with purpose, navigating the terrain with ease, highlighting the beauty and resilience of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1099
|
videos/HRA_part2/1099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat wearing a green apron and a name tag stands behind a wooden cash register, located on a small island amidst a vast desert. The meerkat, resembling a human cashier, rings up purchases with expertise, surrounded by volcanic landscapes visible in the distance. The sandy terrain is dotted with various items for sale, creating a surreal marketplace. In the next moment, the meerkat walks across the sandy ground, navigating between the cash register and the products, with the volcanoes providing a dramatic backdrop to this unusual shopping experience.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2378
|
videos/HRA_part2/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the object in hand is distorted."
}
] |
seed44_1538
|
videos/HRA_part1/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2977
|
videos/HRA_part2/2977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Normal. The workers and the horse walking in the video are basically normal, but there is slight disharmony in the movements."
}
] |
seed42_1528
|
videos/HRA_part0/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_3098
|
videos/HRA_part1/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1426
|
videos/HRA_part2/1426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed42_1572
|
videos/HRA_part0/1572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young children, a boy and a girl, are diligently cleaning a large fish tank positioned against a wall covered with a floral-patterned curtain. The boy, wearing a gray shirt and dark pants, uses a net to scoop debris from the water, while the girl, dressed in a yellow shirt and blue jeans, scrubs the glass with a small brush. Both children work attentively, surrounded by an array of aquarium supplies, including bags of gravel, fish food containers, and various cleaning tools. The tank is home to several colorful fish that swim tranquilly in the background, undisturbed by the children's careful efforts to maintain their environment.]"
},
{
"from": "gpt",
"value": "Bad. There are issues with the generation of the boy's hands and feet, and the fishing net."
}
] |
seed44_1752
|
videos/HRA_part1/1752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial setting, a mature man with salt-and-pepper hair and a full beard, wearing a dark jacket, gray shirt, and black pants, gently touches and inspects a large turbine blade from a power plant. The blade is massive, with a metallic sheen, positioned horizontally against a backdrop of complex machinery and pipes, indicative of a hydroelectric or nuclear power facility. The man's tender gesture contrasts with the harsh environment, highlighting a personal connection or professional pride in the technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed44_2665
|
videos/HRA_part1/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Normal. The video shows students petting chicks, but the movements are not very continuous and there is a lack of coordination."
}
] |
seed42_1473
|
videos/HRA_part0/1473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Bad. The bee-eater's beak in the video is generated unreasonably, and the honeybee is missing parts."
}
] |
seed42_1289
|
videos/HRA_part0/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1779
|
videos/HRA_part2/1779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jackal walks through ancient ruins, its sandy fur blending into the weathered stone walls of a historical site bathed in warm sunlight. The camera captures the jackal from various angles, showcasing its cautious exploration of the site, which features tall columns and ornate carvings, hinting at the grandeur of a long-lost civilization. The jackal pauses, its ears perked, scanning the surroundings before continuing its journey through the silent, time-worn corridors, the texture of the stones and the play of light adding depth to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, the actions are not continuous."
}
] |
seed46_2079
|
videos/HRA_part2/2079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit kitchen, a young man with short brown hair, wearing a black apron over a casual outfit, stands attentively at a modern gas stove. He is seen from a side angle, focusing on cooking a sizzling meal in a large pan, his face expressing concentration. Moments later, he checks the progress of his dish, revealing a close-up of the appetizing food. He then stirs the contents of the pan with a wooden spoon, the steam rising from the meal adding to the atmosphere. Throughout, the kitchen remains bright and welcoming, with a clear countertop and various cooking utensils visible, enhancing the sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The shovel in hand suddenly disappeared, and the person's hand and arm became deformed and disfigured."
}
] |
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 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 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": "Good. No obvious problems."
}
] |
seed44_2716
|
videos/HRA_part1/2716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a white spacesuit with a NASA logo, crawls across the Martian landscape under a starlit sky. The camera captures her movements as she stops to gaze upwards, her helmet visor reflecting the celestial panorama. The focus is on her figure against the rugged terrain, with the distant stars and the curvature of Mars' horizon providing a dramatic backdrop. Her spacesuit, adorned with medical insignia, stands out against the red soil, emphasizing her unique role as a caregiver in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_232
|
videos/HRA_part2/232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate a puppy."
}
] |
seed44_310
|
videos/HRA_part1/310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a black jacket and khaki pants, confidently walks alongside a zebra in the middle of a desert landscape, both seemingly unfazed by the arid environment. The director holds a megaphone in one hand and a script in the other, while the zebra, a symbol of the untamed, ambles beside him, the two forming an unlikely duo in this surreal scene. The sun casts long shadows, highlighting the stark beauty of the desert, as the director and the zebra continue their journey together, a testament to the unexpected alliances that can occur in the pursuit of art.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the director walking side by side with a zebra in a desert landscape, but the movements are not very smooth and continuous, showing some disharmony."
}
] |
seed44_1944
|
videos/HRA_part1/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1732
|
videos/HRA_part1/1732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1373
|
videos/HRA_part0/1373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated."
}
] |
seed44_1796
|
videos/HRA_part1/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2919
|
videos/HRA_part0/2919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 captivating scene, a bobcat is gently caressing a gray cat on a sandy arena floor, both animals seated facing each other. The bobcat, displaying unusual friendliness, reaches out with a paw to touch the cat's face, while the cat responds with a curious gaze. The sandy arena floor provides a textured backdrop, emphasizing the unique interaction between these two feline species. Moments later, the bobcat leans in closer to the gray cat, its paw still extended in a tender gesture, as if sharing a moment of mutual understanding within the sandy enclosure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2266
|
videos/HRA_part2/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic space medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2702
|
videos/HRA_part2/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed46_2127
|
videos/HRA_part2/2127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild dingo, characterized by its sandy coat, alert ears, and bushy tail, walks purposefully across a rocky terrain, surrounded by arid scrubland and distant, hazy mountains, evoking a sense of freedom and survival in the Australian wilderness. The dingo moves with a steady gait, its eyes scanning the environment, showcasing its natural instincts and resilience in a harsh landscape.]"
},
{
"from": "gpt",
"value": "Bad. The dingo's leg is twisted in the video."
}
] |
seed44_320
|
videos/HRA_part1/320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a lawyer, dressed in a sleek gray suit, stands in a spacious room with large windows overlooking a space station's agricultural area, filled with vibrant green plants under artificial lights. He begins to dance gracefully, his movements a stark contrast to his professional attire, as he moves across the room with the space agriculture serving as a backdrop, highlighting the unique juxtaposition of law, agriculture, and dance in zero gravity.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's body is twisted, head is twisted, legs are twisted, feet are twisted, arms are twisted, and hands are twisted."
}
] |
seed42_1609
|
videos/HRA_part0/1609.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student with a messy bun, wearing a white t-shirt and grey sweatpants, stands in a small dorm kitchen. She measures coffee grounds into a filter, her movements practiced and efficient. Next, she pours water from a bottle into the coffee maker, the light catching the droplets as they fall. Then, she pushes the start button on the machine, her face lighting up with anticipation. Lastly, she adds a splash of milk to her mug, stirring it slowly as steam rises, ready to enjoy her well-deserved break amidst the stacks of books and papers on her desk.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2520
|
videos/HRA_part2/2520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny vole, brown in color, scurries through a miniature world set against the backdrop of towering skyscrapers, their glass facades reflecting sunlight. The vole runs across a small wooden bridge, navigating its way through a lush green park nestled within the urban jungle. It then darts under a miniature Eiffel Tower, a playful nod to global landmarks, before disappearing into the safety of a hollow log, all while the cityscape looms large and impressive in the background.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the little field mouse in the video are not smooth."
}
] |
seed46_176
|
videos/HRA_part2/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1445
|
videos/HRA_part0/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's movements are not smooth."
}
] |
seed46_1005
|
videos/HRA_part2/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's limbs and the nurse's face and hands are generated abnormally in the video."
}
] |
seed42_1683
|
videos/HRA_part0/1683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2219
|
videos/HRA_part0/2219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a yellow shirt with a black apron, stands in a modern kitchen classroom filled with stainless steel appliances, teaching a group of attentive students how to stir-fry vegetables. She masterfully tosses vibrant bell peppers, carrots, and broccoli in a large wok over high heat, creating an engaging lesson on cooking techniques. The students, clad in matching aprons, watch intently as she demonstrates the art of stir-frying, her actions punctuated by the sizzling sounds of the hot oil and vegetables. Throughout the scene, the teacher's enthusiasm and expertise shine as she shares her culinary knowledge with her eager pupils.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed46_275
|
videos/HRA_part2/275.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a black beret, blue shirt, and brown vest, gently caresses an ibex with her right hand, while holding a paintbrush in her left. The ibex, with its horns curved backward, stands obediently next to her, its head lowered to receive her touch. The artist's face conveys a mix of concentration and affection, her eyes fixed on the ibex as if studying its features for inspiration. The scene takes place in a rustic studio filled with canvases, easels, and various art supplies, creating a warm and creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1342
|
videos/HRA_part2/1342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man wearing a yellow safety vest, blue jeans, and work gloves is seen from a low angle, balancing on a ladder as he scoops wet leaves out of the clogged gutters. The camera pans to show the man, his face intent and focused, tossing the debris onto the grass below. His movements are deliberate and efficient, showcasing his experience in this task. The scene is set against a backdrop of a suburban house with a red roof, emphasizing the routine nature of home maintenance. As the man continues his work, the afternoon sunlight highlights the water and leaves cascading down from the gutters, capturing the essence of a fall day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_282
|
videos/HRA_part1/282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a person dressed in a panda costume runs playfully through the narrow, cobblestone streets of a quaint town, surrounded by colorful, closely-packed buildings. The panda mascot dashes past outdoor cafes, small shops with hanging signs, and historical architecture, blending elements of fantasy and reality. Locals and tourists alike look on in amusement, some taking photos, as the panda sprints by, adding a touch of unexpected joy to the picturesque town. The mascot's movements are energetic and lively, contributing to the overall sense of fun and adventure in this unique setting.]"
},
{
"from": "gpt",
"value": "Bad. The panda mascot in the video has twisted hands, arms, and legs."
}
] |
seed42_1382
|
videos/HRA_part0/1382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed casino, a large brown bear, standing on two feet, walks with a casual gait, wearing a red shirt, blue jeans, and a gold watch. The bear is surrounded by various elements of the space casino, including a bar with neon lights, slot machines, and a large window displaying a view of the galaxy. As it strides through the casino, the bear passes by a table where alien creatures play cards, their eyes following the unexpected visitor. The atmosphere is filled with a sense of wonder and fun, as the bear continues its stroll, blending seamlessly into the otherworldly environment.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, and feet of the brown bear in the video were generated incorrectly."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.