video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2913
|
videos/HRA_part1/2913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements while bathing the dog in the video are not smooth and coordinated."
}
] |
seed44_183
|
videos/HRA_part1/183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seamless blend of concepts, a majestic jaguar, adorned with Saturn's rings as a necklace, gracefully extends its paw in a caressing gesture toward the camera, creating an intimate connection. The jaguar wears a collar resembling Saturn's rings, adding a cosmic touch to its regal appearance. Its piercing eyes meet the viewer's gaze, while it gently touches the lens with its paw, as if extending a tender greeting. Against a dark, mysterious background, the jaguar's powerful form and the celestial rings combine to create a captivating and surreal scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2445
|
videos/HRA_part1/2445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene grassland setting under a clear blue sky, a police officer, clad in a standard uniform with a badge and gun holster, kneels by a small, clear pond. He watches intently as a group of children joyfully splash and swim in the water, their laughter echoing across the open landscape. The officer's presence is both protective and relaxed, creating a harmonious scene where law enforcement and community enjoyment coexist peacefully amidst the natural beauty of the vast, green grasslands.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed42_1279
|
videos/HRA_part0/1279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Normal. Can't see the red tie."
}
] |
seed46_2937
|
videos/HRA_part2/2937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling fire station, a seasoned firefighter, clad in a navy blue uniform and a yellow reflective vest, expertly operates a coffee machine. The walls are adorned with firefighting equipment and memorabilia, adding to the authenticity of the setting. The firefighter, with a rugged beard and a focused gaze, pours the freshly brewed coffee into a white mug with the fire department's emblem. The room is illuminated by natural light streaming in from a large window, casting a warm glow on the firefighter as he adds a touch of cream to his coffee, embodying a moment of calm amidst the high-stakes environment of emergency response.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1947
|
videos/HRA_part2/1947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two graceful antelopes gently touch noses in a tender caress, surrounded by lush grasses and distant acacia silhouettes. The golden light bathes the scene, highlighting the intricate details of their fur, the tenderness in their eyes, and the delicate interaction, creating a moment of serene connection amid the wild beauty of their habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2603
|
videos/HRA_part0/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, and the hand is distorted."
}
] |
seed42_2131
|
videos/HRA_part0/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2272
|
videos/HRA_part0/2272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Normal. The fingers of the police officer in the video are missing, and the face generation is blurry."
}
] |
seed42_1241
|
videos/HRA_part0/1241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown vole wearing a miniature top hat and a tiny pair of spectacles stands on its hind legs atop a wooden stage, backdropped by a dark, starlit night. It begins to dance, performing a series of charming, unexpected moves that captivate the viewer. The vole's expressive face shows pure joy as it twirls and leaps, its tiny body moving gracefully to an unheard melody. Occasionally, the vole pauses, looking directly into the camera with a mischievous glint in its eye, before continuing its delightful solo performance under the twinkling stars.]"
},
{
"from": "gpt",
"value": "Normal. The vole's movements are not smooth."
}
] |
seed46_144
|
videos/HRA_part2/144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, dressed in a casual striped shirt and beige shorts, walks leisurely on a sandy beach, with the ocean's edge just beyond his feet. He pauses for a moment, looking down thoughtfully, before continuing his stroll. The chef, now wearing a straw hat, is seen from behind, walking with purpose along the shoreline, with the vast sea stretching out behind him. In the final scene, he stands still, gazing out at the horizon, his posture conveying a sense of peace and reflection, all set against the serene backdrop of the beach and sea.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated."
}
] |
seed42_1439
|
videos/HRA_part0/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. No limbs were generated for the brown mouse."
}
] |
seed42_1552
|
videos/HRA_part0/1552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen note that due to the rule about scene transitions, the last sentence should be disregarded, so here's an alternative ending without a transition:\nThe camera then pans out to show the sand dollar resting peacefully on the sandy seabed, surrounded by a few small pebbles and seaweed, capturing the serenity of its underwater habitat. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures the intricate beauty of a sand dollar, its pale color and fine texture contrasting against a dark, grainy sand background. The camera zooms in to reveal the small, delicate spines covering the surface of the sand dollar, emphasizing its natural design. As the focus shifts, the circular shape of the sand dollar becomes prominent, highlighting its symmetrical pattern. The final shot showcases the sand dollar partially buried in the sand, with a blurred oceanic horizon in the distance, evoking a sense of mystery and wonder about this enigmatic sea creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1807
|
videos/HRA_part0/1807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional-looking woman, dressed in a dark blazer, white blouse, and black trousers, sits at a cluttered desk in her office, surrounded by bookshelves filled with law books. Despite the serious environment, she is knitting a vibrant red scarf with a look of concentration on her face, her hands moving deftly as she works on her craft. The room is illuminated by a desk lamp, casting a warm glow over the scene, and a window can be seen behind her, offering a glimpse of a city skyline at twilight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2925
|
videos/HRA_part0/2925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a black leather jacket, dark jeans, and sunglasses, walks purposefully down a busy city street, the iconic Flatiron Building visible in the background. Suddenly, the scene shifts to depict him walking at an extraordinary pace, a visual effect suggesting the concept of light-speed travel. He continues his brisk walk, now surrounded by blurs of color and light, evoking the sensation of moving at incredible velocities. Throughout this dynamic sequence, he maintains his cool demeanor, his outfit unchanged, embodying the fusion of urban style and science fiction themes.]"
},
{
"from": "gpt",
"value": "Normal. The male musician can be clearly seen walking in the video, his movements are basically normal but there is some lack of coordination."
}
] |
seed42_2643
|
videos/HRA_part0/2643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed setting, a chef wearing a white uniform and a red bandana stands out against the metallic walls of what appears to be a bank interior. He walks purposefully, holding a large, clear bag filled with currency, suggesting a daring robbery. The chef's attire, which includes a white chef's jacket, black pants, and a red bandana, contrasts sharply with the cold, metallic environment. The scene is set in a space bank with curved, silver walls and a floor covered in scattered bills, as the chef strides away, his unique occupation and bold actions creating a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2483
|
videos/HRA_part0/2483.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spotted hyena, mid-jump, leaps across a grassy savanna landscape, its powerful hind legs fully extended beneath it, capturing the essence of its agility and strength. The hyena's spotted coat is vivid against the green vegetation, and its mouth is open, revealing sharp teeth, as it focuses on an unseen target ahead. The scene is set during the golden hour, with warm sunlight casting a glow over the hyena and the surrounding environment, highlighting the texture of the grass and the depth of the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The spotted hyena in the video has uncoordinated running movements."
}
] |
seed44_1359
|
videos/HRA_part1/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1607
|
videos/HRA_part2/1607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, open field under a clear blue sky, two young children, a boy and a girl, both wearing vibrant yellow raincoats, wide-brimmed hats, and boots, are seen walking together. They carry a large, reflective solar sail, its metallic surface shimmering in the sunlight. The sail, supported by a wooden frame they hold, catches the wind as they walk, propelling them forward playfully across the grassy landscape. Their joyful expressions and the sail's gentle movements create a whimsical scene, blending elements of childhood wonder with futuristic technology.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face and legs show deformities, but the girl's face does not show deformities. The hands also exhibit deformities."
}
] |
seed46_2641
|
videos/HRA_part2/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The server's hand generation in the video has issues."
}
] |
seed46_1348
|
videos/HRA_part2/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, and one arm is missing."
}
] |
seed44_3044
|
videos/HRA_part1/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Normal. The middle-aged male chef's hands in the video have generation issues, and the employees in the background are generated blurry."
}
] |
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 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 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": "Good. No obvious problems."
}
] |
seed44_2176
|
videos/HRA_part1/2176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating display, a slender cheetah with golden fur and black spots leaps into the air against a vivid, sunlit savanna landscape. Its body curves gracefully mid-leap, capturing the essence of its feline agility. The cheetah's intense, focused gaze is directed forward, suggesting a sense of purpose in its dance-like movements. Its tail extends elegantly, balancing its airborne form as it seemingly dances across the plains, embodying the spirit of the wild. The scene is framed by distant acacia silhouettes, enhancing the dramatic effect of the cheetah's dynamic leap.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_1970
|
videos/HRA_part1/1970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3026
|
videos/HRA_part2/3026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, clad in a navy blue t-shirt and beige cargo pants, meticulously organizes his cluttered garage, transforming it into a space of efficiency and order. The scene opens with him standing amidst a disorganized mess, shelves packed with tools and miscellaneous items. He begins by sorting through the chaos, creating piles of items to keep, donate, or discard. As the process unfolds, the garage gradually becomes a well-ordered workspace, with tools neatly arranged on pegboards, shelves neatly stocked, and the floor cleared of debris. The engineer, now in a clean environment, proudly surveys his accomplishment, the once chaotic garage now a testament to his organizational skills.]"
},
{
"from": "gpt",
"value": "Bad. The engineer in the video tidying up the garage is very unsmooth, with uncoordinated movements."
}
] |
seed42_3080
|
videos/HRA_part0/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Bad. The children in the video have distorted faces, hands, arms, and legs."
}
] |
seed46_1456
|
videos/HRA_part2/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated, and there are issues with the facial features."
}
] |
seed44_2739
|
videos/HRA_part1/2739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, clad in a light blue uniform, gently caresses the fur of a calm, gray wolf sitting beside her, both under the shade of a large tree in a grassy field. The wolf looks up at her with a relaxed demeanor, while she tenderly strokes its head, conveying a sense of mutual trust and peace between human and wild animal. Moments later, she holds the wolf's snout softly, her caring gaze meeting its calm eyes, with the serene natural surroundings enhancing the emotional connection depicted.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1814
|
videos/HRA_part1/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The red bow tie does not appear in the video."
}
] |
seed44_2205
|
videos/HRA_part1/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed42_1822
|
videos/HRA_part0/1822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a stethoscope around his neck and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand and fishing rod in the video have issues with generation, and the fishing rod deforms in the middle frames."
}
] |
seed46_2549
|
videos/HRA_part2/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1560
|
videos/HRA_part0/1560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 warbler, a small songbird with yellow-green plumage, perches on a branch, its head turned to the side, revealing its distinct facial markings. It opens its beak to sing, showcasing its natural habitat among lush green leaves. The bird then takes flight, its wings flapping gracefully, before landing on another branch, where it continues its melodious song, surrounded by the vibrant foliage of a tree. Throughout, the focus remains on the warbler's lively movements and distinctive features, set against the backdrop of a verdant forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The bird's claws were not generated in the video, and the bird disappeared later."
}
] |
seed42_2577
|
videos/HRA_part0/2577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2841
|
videos/HRA_part1/2841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a red flannel shirt and denim overalls, dances joyously in a lush green field, while a curious deer watches from a distance, its ears perked up, intrigued by the unusual sight. The farmer's movements are lively and free, embodying a sense of unbridled happiness, as the deer remains frozen in place, observing the dance with wide, expressive eyes. The scene is set against a backdrop of rolling hills and a clear blue sky, creating a picturesque rural landscape that complements the harmonious interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a farmer dancing, with movements that are not continuous and smooth, showing disharmony."
}
] |
seed42_102
|
videos/HRA_part0/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Normal. The animals in the video walk basically normally, with only slightly uncoordinated movements."
}
] |
seed44_1102
|
videos/HRA_part1/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Bad. The character's action of catching the glass bottle in the video is very unsmooth, with the hand suddenly disappearing or reappearing in the middle frames."
}
] |
seed42_1390
|
videos/HRA_part0/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1119
|
videos/HRA_part1/1119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Asian cashier, wearing a red apron over a white collared shirt, black pants, and black shoes, is seen mid-air, jumping with both feet off the ground, her ponytail bouncing behind her. The camera captures her from various angles, showing her enthusiasm and energy as she performs this unexpected action within the confines of her workplace, a modern convenience store with neatly arranged shelves and bright lighting.]"
},
{
"from": "gpt",
"value": "Bad. The jumping movements of the character in the video are very unsmooth, the character's hands are distorted and sometimes suddenly disappear or reappear."
}
] |
seed46_2163
|
videos/HRA_part2/2163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1053
|
videos/HRA_part0/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1700
|
videos/HRA_part1/1700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1798
|
videos/HRA_part0/1798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a green shirt and khaki shorts, tends to a lush garden filled with vibrant flowers and greenery. He strums his acoustic guitar, creating a melodic soundtrack for his gardening endeavors. The garden is brimming with life, featuring an array of colorful flowers such as daisies, roses, and tulips. The musician, wearing a wide-brimmed straw hat and sunglasses, works diligently, watering plants and trimming bushes. As he gardens, he occasionally pauses to play his guitar, seamlessly blending his passions for music and nature in a harmonious outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate sunglasses, water pipes, or pruning shears."
}
] |
seed42_2338
|
videos/HRA_part0/2338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an assortment of smaller fish. The grouper, distinguished by its size and spotted brown skin, explores its surroundings with a sense of ownership, occasionally pausing to inspect something of interest. Its powerful body and broad fins propel it through the crystal-clear waters, showcasing the serene beauty of life beneath the ocean's surface.]"
},
{
"from": "gpt",
"value": "Normal. The stone grouper's fins and mouth were generated incorrectly, the body was slightly deformed, and the small fish were generated incorrectly."
}
] |
seed42_1987
|
videos/HRA_part0/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2101
|
videos/HRA_part2/2101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 handsome, young male actor sprints through a bustling train station, wearing a dark blue coat, khaki pants, and brown shoes, his face a mask of urgency and determination. The vibrant, crowded setting provides a dynamic backdrop, filled with diverse individuals going about their day. His intense gaze and focused posture convey a sense of high stakes, while the surrounding architecture and the moving crowd add depth and realism to the scene. The camera captures his swift movement from multiple angles, highlighting his purposeful stride and the energy emanating from him as he weaves through the throngs of travelers.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1735
|
videos/HRA_part2/1735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a cartoon beaver, wearing a brown graduation cap and holding a yellow eraser, energetically wipes a green chalkboard clean, revealing a lesson about the water cycle. The beaver, now wearing a white shirt with a red tie and a brown vest, continues to erase enthusiastically, displaying a fun and engaging teaching style. Next, the beaver, still in its academic attire, uses the eraser to remove the last bit of chalk from the board, ensuring the surface is completely clear. Finally, the animated beaver teacher, dressed in its scholarly outfit, stands proudly beside the now-blank chalkboard, ready for the next lesson.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2775
|
videos/HRA_part2/2775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful-looking young man, possibly a librarian or a bookstore employee, organizes books on a shelf in a cozy library corner. He wears a mustard yellow sweater over a button-down shirt, khaki pants, and a stylish watch. The library is filled with bookshelves and has a warm, inviting atmosphere, enhanced by the wooden furniture and green plants. He carefully arranges the books, occasionally stopping to read titles or adjust their placement. The shelves are filled with various genres of literature, from classics to contemporary works, reflecting the diverse interests of the library's patrons. Throughout the scene, the man's dedication to his task is evident, as he meticulously organizes the books with a sense of purpose and care.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2507
|
videos/HRA_part1/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Normal. The swordfish's face and fins generation in the video have issues."
}
] |
seed46_1679
|
videos/HRA_part2/1679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dim light of a Martian sunset, casting an eerie orange glow, a small, brown mouse sits atop a large fire helmet, placed on the red, rocky surface of Mars. Nearby, a firefighter, dressed in a full suit and helmet, wipes his brow with a gloved hand, appearing weary yet determined. The vast, desolate landscape stretches out behind him, dotted with the remnants of a recently extinguished extraterrestrial fire, as the distant horizon is bathed in the fading embers of the alien sun.]"
},
{
"from": "gpt",
"value": "Normal. The firefighters' movements in the video are not smooth."
}
] |
seed44_2578
|
videos/HRA_part1/2578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scenario, a distinguished doctor, wearing a full lab coat and stethoscope, races alongside a nimble ibex on a vibrant green meadow. The doctor, maintaining a focused gaze, keeps pace with the ibex, which bounds gracefully across the landscape, showcasing the unlikely companionship between human and wild animal. The scene is set against a backdrop of rolling hills and clear blue skies, creating a vivid and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the rock goats and the doctor very unsmoothly, with uncoordinated movements."
}
] |
seed44_2727
|
videos/HRA_part1/2727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin leaps from the crystal-clear ocean waters, its streamlined body glistening in the sunlight. The vibrant blue and silver hues of its scales contrast beautifully against the turquoise backdrop. In another scene, the marlin swims gracefully beneath the surface, its elongated bill leading the way as it navigates the underwater world. Surrounded by schools of smaller fish and the lush marine environment, the marlin embodies the power and elegance of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1
|
videos/HRA_part2/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_189
|
videos/HRA_part0/189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The cat in the video walks basically normally, with only slight uncoordination in its movements. The college student's actions of petting the cat in the video are basically normal."
}
] |
seed42_1469
|
videos/HRA_part0/1469.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow 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": "Normal. The character's movements are not smooth."
}
] |
seed42_1065
|
videos/HRA_part0/1065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers appear deformed."
}
] |
seed44_2994
|
videos/HRA_part1/2994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two children, a boy and a girl, both dressed in khaki safari outfits, walk alongside a gentle rhinoceros in a lush, grassy savannah setting. The children, appearing fearless and joyful, interact closely with the rhino, which is adorned with natural vegetation, indicating its habitat. The trio moves harmoniously together, with the children occasionally touching the rhino, highlighting a unique bond between humans and wildlife. The scene is set against a backdrop of distant trees and clear skies, emphasizing the beauty and tranquility of their shared environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2407
|
videos/HRA_part2/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Bad. The red-tailed hawk's flying movements in the video are not smooth and coordinated."
}
] |
seed42_3049
|
videos/HRA_part0/3049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, clad in a blue checkered shirt and black pants, meticulously assembles a complex piece of furniture in a modern workshop, illuminated by bright overhead lights. His tools, including a screwdriver and measuring tape, are laid out on a clean, organized workbench. Close-up shots reveal his focused expression and skilled hands as he aligns and tightens screws, demonstrating precision and expertise. The space is filled with the ambient sounds of machinery and the occasional beep of electronic devices, creating a backdrop of industrious activity. Throughout the process, the engineer maintains a calm demeanor, pausing occasionally to consult a blueprint or adjust his glasses, embodying the essence of craftsmanship and dedication.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's face, hands, and arms are distorted in the video."
}
] |
seed42_1361
|
videos/HRA_part0/1361.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opera setting, a cashier, dressed in a metallic green costume with silver accents, is seen crawling across a high-tech stage filled with holographic displays and neon lights. The cashier, wearing a helmet with a transparent visor, moves slowly and deliberately, as if navigating through a complex transaction or performing a ritualistic dance. The background is filled with an audience of alien species, all watching intently as the cashier completes their task, emphasizing the unique blend of everyday life and dramatic performance in this cosmic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2076
|
videos/HRA_part1/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's limbs in the video were not fully generated, and the face was distorted."
}
] |
seed44_2074
|
videos/HRA_part1/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm appear deformed and distorted, and the chair in his hand also becomes deformed."
}
] |
seed44_1836
|
videos/HRA_part1/1836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a writer sits at a large wooden desk, adorned with a typewriter, a glass of whiskey, and a half-smoked cigar. Dressed in a brown leather jacket, black shirt, and jeans, he appears rugged and disheveled. Behind him, an open window reveals the gritty urban landscape of a city at night. Suddenly, the scene shifts to a close-up of a rhinoceros, its gray skin wrinkled and textured. The animal is being gently wiped down by a caregiver, who uses a cloth to clean its face, highlighting the creature's large size and docile nature. The juxtaposition of the writer and the rhinoceros creates a surreal and thought-provoking image.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_3215
|
videos/HRA_part0/3215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black helmet and protective gear, sits intently at a desk in a dimly lit station. His strong hands, adorned with a silver ring, deftly type on a laptop keyboard, while a yellow fire truck is visible through the window behind him. The scene conveys a sense of duty and focus as the firefighter's gaze is locked on the computer screen, illuminated by the soft glow of the monitor. A framed photo of a family rests on the bookshelf in the background, adding a personal touch to the otherwise utilitarian space.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the firefighter's hands tapping on the laptop keyboard, with basically normal movements, but there is slight inconsistency."
}
] |
seed44_1713
|
videos/HRA_part1/1713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark jacket and casual attire, steps out of a modern building into the urban night, holding a black garbage bag. He approaches a large, industrial dumpster under the dim glow of streetlights, surrounded by concrete walls and parked cars. As he lifts the dumpster lid, his directorial composure contrasts with the mundane task of disposing waste. The scene captures the unexpected juxtaposition of creative leadership and everyday chores, highlighting the director's relatable human side amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the character in the video are distorted."
}
] |
seed44_2538
|
videos/HRA_part1/2538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his wedding ring, enjoys a leisurely hike in a rural mountainous area, wearing a white button-down shirt and khaki pants, a departure from his usual doctor's attire. He pauses to admire the stunning landscape, which includes lush greenery, rocky terrain, and distant mountain peaks, all under a clear blue sky. Carrying a walking stick and backpack, he navigates the rugged trail with ease, embodying the spirit of adventure and the great outdoors. As he continues his journey, he occasionally checks his phone, perhaps communicating with loved ones or colleagues from his medical profession.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1076
|
videos/HRA_part1/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's movements in the video are uncoordinated."
}
] |
seed46_1547
|
videos/HRA_part2/1547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young Asian nurse wearing a white uniform and a name tag takes a break from her hospital duties to clean the large, rectangular window in the patient's room. Holding a squeegee in her right hand and a spray bottle in her left, she sprays the glass with a cleaning solution, creating a fine mist. She then wipes it down with the squeegee, leaving a clear, streak-free surface. The natural light from outside illuminates the room, casting a warm glow on the nurse as she works diligently, ensuring the window is spotless.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_112
|
videos/HRA_part2/112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of fresh mackerel fish, glistening under bright lights, showcases their vibrant silver scales, deep blue stripes, and dark spots. The fish lie on a bed of ice, their eyes clear and shiny, indicating peak freshness. The background features a bustling market scene, with vendors selling various seafood and customers browsing the selection. Focused on the mackerel, the camera captures every detail of the fish's texture and color, making them the star of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2099
|
videos/HRA_part2/2099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow hard hat, orange safety vest, and blue jeans, sits on a wooden crate at a bustling construction site. Surrounded by scaffolding, concrete mixers, and cranes, he meticulously draws architectural plans using a pencil and a large blueprint sheet laid out on a makeshift plywood table, illustrating his dual skills in both physical labor and design. The scene captures his focused expression and the gritty urban environment, highlighting the blend of creativity and labor in his work.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3063
|
videos/HRA_part1/3063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, walks alongside a cheetah on a leash in an urban park setting. The officer, wearing sunglasses and a cap, maintains a calm demeanor as they stroll together. The cheetah, fitted with a specialized harness, looks up attentively, its spots clearly visible against the green foliage of the park. The pair meanders past park benches and trees, creating an unusual yet harmonious scene of law enforcement and wildlife coexisting in a city environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2739
|
videos/HRA_part0/2739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, clad in a light blue uniform, gently caresses the fur of a calm, gray wolf sitting beside her, both under the shade of a large tree in a grassy field. The wolf looks up at her with a relaxed demeanor, while she tenderly strokes its head, conveying a sense of mutual trust and peace between human and wild animal. Moments later, she holds the wolf's snout softly, her caring gaze meeting its calm eyes, with the serene natural surroundings enhancing the emotional connection depicted.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the gray wolf's mouth in the video is problematic, with an extra piece of foreign material appearing on the neck, and the nurse's fingers are deformed."
}
] |
seed42_2121
|
videos/HRA_part0/2121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, characterized by its golden-brown fur and tiny ears, energetically jumps across wooden dock planks by a serene lake, surrounded by lush greenery. The hamster's miniature size contrasts with the vast, natural setting, creating a whimsical scene. Its movements are agile and lively, as it leaps from one dock plank to another, showcasing its playful spirit against the backdrop of a peaceful lakeside environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the hamster in the video are missing, and there is also a part of the body missing."
}
] |
seed46_1019
|
videos/HRA_part2/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Bad. The person wearing gray in the video has issues with the generation of their legs, hands, and face. The black leopard also has problems with the generation of its legs and face."
}
] |
seed42_2941
|
videos/HRA_part0/2941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The hand and the rhinoceros's head in the video are deformed."
}
] |
seed46_1185
|
videos/HRA_part2/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_148
|
videos/HRA_part1/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_286
|
videos/HRA_part1/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Normal. The officer's hand in the video has generation issues, and the eyes are slightly blurry."
}
] |
seed42_3151
|
videos/HRA_part0/3151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a trimmed beard, wearing a red flannel shirt, blue jeans, and a brown hat, stands in a barn filled with hay bales. He sneezes loudly, holding a pitchfork, as dust particles and shafts of sunlight fill the air around him. The barn is rustic, with wooden beams and a dirt floor, and the farmer's sneeze echoes throughout the space. Afterward, he wipes his nose with a red handkerchief, the barn's interior still visible behind him, before continuing his work with the hay.]"
},
{
"from": "gpt",
"value": "Normal. The man's sneezing action in the video is slightly unsmooth."
}
] |
seed44_1136
|
videos/HRA_part1/1136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red cap, stylish sunglasses, and a gray shirt, stands against a blurred background, engagingly waving at the audience with his right hand. Moments later, he passionately plays his guitar, exuding energy and confidence. He then smiles broadly, his eyes closed, clearly enjoying the music and the connection with his fans. Finally, he returns to waving, his joyful demeanor and dynamic presence captivating the crowd, all set against a backdrop of a lively concert atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1415
|
videos/HRA_part0/1415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a Rainbow Trout, showcasing its shimmering silver scales speckled with vibrant pink stripes, fills the frame. The fish's large, expressive eyes and intricate patterns on its fins are clearly visible, set against a dark, blurred aquatic environment. The water around it gently swirls, revealing bubbles and fine particles, while the trout remains remarkably still, allowing for a detailed examination of its stunning features.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3099
|
videos/HRA_part0/3099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dotted with distant acacia trees, a large herd of African cape buffaloes gathers. The scene opens with a panoramic view of the herd, then zooms in on two buffaloes standing face-to-face, seemingly engaged in a dance-like interaction. The dominant male, with massive horns and a thick mane, takes a step forward, while the other male responds with a matching step, creating a rhythmic pattern. They continue this 'dance', mirroring each other's movements against the serene backdrop of the savannah, the clear blue sky, and the distant horizon, evoking a sense of primal connection and ritual within the herd.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2063
|
videos/HRA_part0/2063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dedicated teacher, wearing a green shirt and khaki pants, stands in a classroom filled with educational posters and bookshelves, holding a small hippopotamus toy. Behind her, a large window reveals Saturn's majestic rings in the distance, dominating the sky. The teacher gently tosses the hippo into a clear, indoor swimming pool, where it floats on the water's surface, creating ripples. The room is illuminated by soft, warm lighting, casting a serene atmosphere over the unique combination of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2746
|
videos/HRA_part2/2746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of four energetic children, two boys and two girls, wearing colorful clothing including red, blue, and green shirts, jump high into the air in unison, against a backdrop of a cloudy sky and lush green grass. Their faces are filled with joy and excitement as they perform their synchronized leap. One boy, in a striped shirt, and one girl, in a pink dress, stand out among them, capturing the essence of youthful exuberance and carefree play in a natural outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The jumping movements of the children in the video are not smooth."
}
] |
seed42_1735
|
videos/HRA_part0/1735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a cartoon beaver, wearing a brown graduation cap and holding a yellow eraser, energetically wipes a green chalkboard clean, revealing a lesson about the water cycle. The beaver, now wearing a white shirt with a red tie and a brown vest, continues to erase enthusiastically, displaying a fun and engaging teaching style. Next, the beaver, still in its academic attire, uses the eraser to remove the last bit of chalk from the board, ensuring the surface is completely clear. Finally, the animated beaver teacher, dressed in its scholarly outfit, stands proudly beside the now-blank chalkboard, ready for the next lesson.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are not smooth."
}
] |
seed44_289
|
videos/HRA_part1/289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, gently caresses another meerkat lying on the ground, creating a tender and intimate moment. The first meerkat, with brown spots and alert eyes, uses its front paws to softly touch and comfort the other, which responds with closed eyes, indicating relaxation and trust. The scene takes place under the shade of a small bush in the savanna, with the soft, warm sunlight illuminating the interaction, highlighting the bond between these social animals.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat in the video has slightly uncoordinated movements."
}
] |
seed44_2117
|
videos/HRA_part1/2117.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 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 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": "Good. No obvious issues."
}
] |
seed42_2513
|
videos/HRA_part0/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the person's face."
}
] |
seed42_1123
|
videos/HRA_part0/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's hand in the video is generated incorrectly."
}
] |
seed42_1759
|
videos/HRA_part0/1759.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum gift shop, a young, cheerful female cashier with a short bob haircut, wearing a black apron over a gray shirt, assists customers. She momentarily pauses her duties to dance energetically behind the counter, swaying her hips and moving her arms to an unheard beat. The scene is set against a backdrop of museum exhibits, including a large model of the solar system hanging from the ceiling, and shelves filled with space-themed souvenirs and educational toys, creating a unique and engaging atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1480
|
videos/HRA_part2/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1632
|
videos/HRA_part0/1632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the person in the video were poorly generated."
}
] |
seed46_1886
|
videos/HRA_part2/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Bad. The beaver in the video has missing limbs, an uncoordinated tail, and no claws generated."
}
] |
seed46_3117
|
videos/HRA_part2/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The man's face is distorted, his hands are twisted, the lizard's head is distorted, and the body is twisted."
}
] |
seed44_1943
|
videos/HRA_part1/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, vibrant green lizard with intricate patterns adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The lizard's movements in the video are not smooth and are uncoordinated."
}
] |
seed42_1534
|
videos/HRA_part0/1534.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings with keen eyesight. Suddenly, it springs into action, jumping high into the air from the sandy ground of its desert habitat. The meerkat's body is arched gracefully mid-leap, showcasing its agility and strength. Its fur, a blend of tans and browns, contrasts beautifully against the clear blue sky, capturing the essence of life in the wild. As it lands, the meerkat's alert ears and expressive face reveal its readiness for any challenge in its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2708
|
videos/HRA_part2/2708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster, primarily white with gray patches, leaps into the air from within a wire cage, its hind legs propelling it upwards with remarkable agility. The hamster's front paws extend forward as it jumps, highlighting its determination and playfulness. The scene is set against a backdrop of a green meadow, creating a whimsical contrast between the indoor cage and the outdoor setting. The hamster's joyful leap is captured in high detail, showcasing its adventurous spirit and the soft fur that covers its body.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the hamster jumping."
}
] |
seed44_1860
|
videos/HRA_part1/1860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, sun-dappled forest, a small, bushy-tailed squirrel gently caresses a smooth, brown egg nestled among vibrant green moss on a flat rock. The squirrel, with its soft, gray fur and alert eyes, tenderly touches the egg with its tiny paws, creating a heartwarming scene of unexpected care. The lush surroundings include tall trees, filtered sunlight, and a variety of foliage, adding depth and texture to the intimate moment shared between the squirrel and the fragile egg.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2780
|
videos/HRA_part0/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands, arms, feet, and legs are distorted in the video."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.