video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2280
|
videos/HRA_part0/2280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand in the video is distorted, and the item in their hand is also distorted."
}
] |
seed46_1940
|
videos/HRA_part2/1940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a well-dressed lawyer, wearing a dark suit, finds himself in a courtroom that resembles a jungle environment. Seated at a desk adorned with law books and vines, he attentively wipes a chimpanzee's face, which is sitting calmly beside him. The chimp, looking somewhat bewildered, is wearing a miniature suit and tie, adding to the surreal atmosphere of the scene. The lawyer's serious demeanor contrasts with the absurdity of the situation, creating a unique visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1916
|
videos/HRA_part0/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2221
|
videos/HRA_part1/2221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1432
|
videos/HRA_part0/1432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, neatly trimmed beard, and glasses stands in a modern office setting, wearing a dark gray blazer, white shirt, and jeans. He points his right index finger upward with a serious yet excited expression, indicating an idea or making a significant point. Behind him, a large window reveals a cityscape, adding depth and context to the scene. The office is sparsely decorated, featuring a simple desk and chair, which complements the minimalist aesthetic of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3100
|
videos/HRA_part1/3100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech laboratory setting, a professional lawyer, dressed in a sharp navy suit, consults with a dedicated nanobot repair crew. The crew, clad in matching silver jumpsuits, works diligently on a complex control panel. One crew member uses a microfiber cloth to carefully wipe down a row of advanced machinery, ensuring every surface is spotless. The lawyer observes closely, occasionally pointing to specific components and engaging in animated discussions with the crew about the intricacies of the nanobot technology. The scene is lit by the soft glow of the lab equipment, creating a futuristic and professional atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. In the video, one team member's action of carefully wiping the machine with a microfiber cloth is not continuous and smooth, showing some lack of coordination; in the video, the lawyer can be seen pointing to specific parts for discussion, the actions are basically normal but there is some lack of coordination."
}
] |
seed44_223
|
videos/HRA_part1/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's limbs generation in the video has problems, and the body is deformed."
}
] |
seed44_3043
|
videos/HRA_part1/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Normal. The waiter's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_2987
|
videos/HRA_part0/2987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a vibrant floral-print dress over her swimsuit, stands before a majestic waterfall cascading into a serene pool. She joyfully leaps into the water, her dress fluttering in the breeze, revealing her red swimwear beneath. Emerging from the pool, she playfully splashes water, her laughter echoing through the lush, green surroundings. As she exits the frame, a panoramic view of the waterfall and its misty spray enveloping the tranquil pool takes center stage, offering a peaceful contrast to the nurse's lively energy.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's action of jumping into the water in the video is not smooth."
}
] |
seed46_2276
|
videos/HRA_part2/2276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a grey t-shirt, beige shorts, and a cap, is organizing his spacious garage, which features a white ceiling and walls. The garage is filled with various items, including bicycles, a stroller, storage containers, and a large, open shelving unit containing numerous tools and equipment. The doctor methodically arranges these items, creating a neat and orderly space. As he works, he occasionally pauses to examine specific objects, such as a red bicycle, before continuing his task with purpose and precision. Throughout the process, the garage remains well-lit, highlighting the doctor's meticulous efforts to transform the cluttered area into a well-organized and functional space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2390
|
videos/HRA_part0/2390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the character and the rhinoceros in the video are not smooth."
}
] |
seed42_2918
|
videos/HRA_part0/2918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, sits on a wooden beam in the middle of a desert construction site. With a gentle smile, he caresses a small green lizard that has wandered onto his open palm. The dusty landscape and unfinished buildings surround him, yet in this moment, his attention is tenderly focused on the tiny creature basking in the warmth of his hand.]"
},
{
"from": "gpt",
"value": "Bad. The hand and green lizard in the video are deformed."
}
] |
seed42_1192
|
videos/HRA_part0/1192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2308
|
videos/HRA_part2/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2021
|
videos/HRA_part1/2021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge, hat, and tactical vest, stands under a dimly lit streetlamp on a quiet, empty urban street at night. The officer's face is contorted in anguish, tears streaming down their cheeks, highlighting the emotional weight they carry. Their eyes are closed, and they're holding a tissue in one hand, indicating a moment of vulnerability amidst their duty. The scene conveys a powerful message about the human side of law enforcement, emphasizing the emotional toll it can take on those who serve.]"
},
{
"from": "gpt",
"value": "Bad. The police officer holding a tissue with one hand mentioned in the caption does not appear in the video."
}
] |
seed46_1448
|
videos/HRA_part2/1448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Normal. The bear's legs show deformities."
}
] |
seed42_2250
|
videos/HRA_part0/2250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male farmhand, clad in a white shirt and brown apron, gently caresses a small, fluffy yellow chick with a tender smile on his face, showcasing a moment of care and connection in a rural setting. The scene is set against a backdrop of wooden crates and greenery, highlighting the peaceful atmosphere of the farm. His hands, rough from labor yet gentle in touch, cradle the delicate creature, emphasizing the bond between man and nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1028
|
videos/HRA_part2/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2545
|
videos/HRA_part2/2545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 natural, woody setting, a man with a beard, wearing a brown jacket, sits on the ground, gently caressing a gray wolf that lies calmly beside him, its head resting on the man's lap. The wolf appears relaxed and trusting, as if sharing a moment of mutual understanding with the man, who looks on with a soft, compassionate gaze, the lush forest and tall trees providing a serene backdrop to their connection.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1607
|
videos/HRA_part0/1607.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 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, 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": "Good. No obvious problems."
}
] |
seed44_1743
|
videos/HRA_part1/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3204
|
videos/HRA_part0/3204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded male musician, wearing a brown hat and a blue shirt with suspenders, sits against a plain gray backdrop. He is knitting a long, cream-colored scarf with large needles, showcasing his dexterity. In another scene, he holds the growing scarf in his hands, his facial expression one of concentration. Next, he looks directly at the camera, his eyes conveying a sense of peace and contentment. Finally, he continues knitting, his fingers moving skillfully, set against the simple gray background that emphasizes his artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands and the knitting tools in his hands are deformed."
}
] |
seed42_1270
|
videos/HRA_part0/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1935
|
videos/HRA_part0/1935.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a large, sleek bass fish fills the screen, its body glistening with vibrant green and brown hues, accented by striking black spots. The fish's powerful form is emphasized as it swims within its natural freshwater habitat, surrounded by lush aquatic plants and a rocky bottom. The water's rippling surface occasionally comes into view, hinting at the bass's movements just beneath. The scene is captured in high definition, highlighting the intricate details of the fish's scales, fins, and eyes, offering a captivating glimpse into the underwater world of this formidable predator.]"
},
{
"from": "gpt",
"value": "Normal. The pectoral fin generation of the perch in the video is problematic."
}
] |
seed46_2011
|
videos/HRA_part2/2011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sandy desert under a clear blue sky, a lone camel, distinguished by a single hump, leaps gracefully into the air. Its action is captured mid-jump, with all four feet off the ground, showcasing its unique ability to navigate the dunes. The camel's tan fur contrasts beautifully with the blue sky and golden sand, highlighting its natural habitat. As it springs forward, the surrounding landscape of dunes and distant mountains provides a stunning backdrop, emphasizing the creature's agility and the serenity of its environment.]"
},
{
"from": "gpt",
"value": "Bad. The camel's jumping action in the video is not continuous and smooth, and the movements are uncoordinated."
}
] |
seed44_1462
|
videos/HRA_part1/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a brown coffee table."
}
] |
seed46_2646
|
videos/HRA_part2/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, legs, beaver head, and legs are distorted."
}
] |
seed46_2117
|
videos/HRA_part2/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers are missing in the video, there are issues with the generation of his eyes, and the facial features of the porcupine have not been generated."
}
] |
seed42_2099
|
videos/HRA_part0/2099.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": "Normal. The worker's actions of drawing the blueprint in the video can be clearly seen, the actions are basically normal, but there is slight disharmony."
}
] |
seed42_1392
|
videos/HRA_part0/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand appears deformed."
}
] |
seed46_2077
|
videos/HRA_part2/2077.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, iridescent green with a crimson throat, hovers in a clear blue sky, its wings a blur of motion. It approaches a red feeder, designed with four feeding stations, each marked with a yellow flower, hanging from a branch in a lush, green forest. The bird lands momentarily on the feeder before resuming its characteristic hovering flight, sipping nectar with its long, slender beak. Against the vibrant backdrop of the forest, the hummingbird's agility and the feeder's design stand out, capturing the beauty of nature in a serene setting.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's claws, eyes, and wings in the video have generation issues."
}
] |
seed46_1749
|
videos/HRA_part2/1749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a white lab coat over a black turtleneck and black pants, runs down a sleek, futuristic corridor of a space medical facility. The hallway is lined with glass panels that offer glimpses into advanced treatment rooms. The artist's stride is purposeful, their gaze determined, as they navigate the sterile environment illuminated by soft, ambient lighting. The facility's design incorporates curved walls and high-tech equipment, creating a blend of artistry and cutting-edge medicine in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2694
|
videos/HRA_part2/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2959
|
videos/HRA_part0/2959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished with salt-and-pepper hair and a trimmed beard, stands in a dimly lit, cluttered bathroom. Dressed casually in a gray t-shirt, dark jeans, and a black jacket, he focuses intently on unclogging a blocked sink drain. His right hand grips a metal tool, while his left hand steadies the sink's rim. The scene captures his determination, with the bathroom's sparse details - a white toilet, a beige wall, and a small window - adding context to his solitary task. The director's serious demeanor and the bathroom's functional design emphasize the mundane yet necessary act of home maintenance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2895
|
videos/HRA_part1/2895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 inventive engineer, donning a yellow hard hat and safety vest, stands beside a massive robotic mammoth at a pier, the structure's weathered wooden planks extending over the water. The mammoth, complete with tusks and a textured gray exterior, is connected to the engineer via cables and machinery. As seagulls fly overhead, the engineer leaps onto the mammoth's back, initiating an unexpected journey. The scene captures the juxtaposition of historical grandeur and modern engineering prowess, with the city skyline visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1900
|
videos/HRA_part1/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_114
|
videos/HRA_part0/114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red jacket and gray pants, dances joyfully on a mountain trail, surrounded by lush greenery and towering trees. The scene is set in the afternoon, with the sunlight filtering through the leaves, casting dappled shadows on the ground. The student performs a series of energetic dance moves, twirling and leaping across the rocky path, their face beaming with happiness and freedom. The mountain range looms majestically in the background, providing a breathtaking backdrop to this spontaneous dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The students' dancing in the video is very unsmooth, and their movements are uncoordinated."
}
] |
seed44_298
|
videos/HRA_part1/298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2112
|
videos/HRA_part1/2112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, a gentle hand caresses a small, curious mouse, creating a tender scene. The mouse, with its tiny body and delicate features, sits on a smooth wooden surface, possibly a desk or table. The hand, belonging to a caring individual, moves gently, stroking the mouse's back with slow, soothing motions. The atmosphere is peaceful, with the focus solely on the interaction between the human and the mouse, emphasizing the bond formed in this quiet moment. The mouse appears relaxed and comfortable under the hand's touch, highlighting the trust and connection that has developed between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2090
|
videos/HRA_part1/2090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two children, a boy and a girl, both wearing space-themed pajamas, walk across a vast, cosmic landscape under a night sky filled with stars and a stunning galactic nebula. The boy leads, wearing a blue cap and holding a flashlight, illuminating their path on the alien terrain. The girl follows closely, carrying a toy astronaut, as they venture together into the unknown, their small figures contrasting dramatically against the grandeur of the universe stretching above them.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_170
|
videos/HRA_part0/170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate writer, donning a black beanie and glasses, sits at a modern desk, engrossed in typing on a sleek laptop. The scene is set in a cozy room with a brick wall and a wooden shelf filled with books, plants, and a clock. Morning sunlight softly illuminates the space, casting a warm glow on the writer's face. A cup of coffee sits nearby, a trusted companion during the creative process. The writer occasionally glances at notes spread across the desk, incorporating ideas into the digital manuscript, capturing the essence of dedication and inspiration in the art of writing.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated and there are issues with the eyes, and there are too few books on the bookshelf."
}
] |
seed44_2895
|
videos/HRA_part1/2895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 inventive engineer, donning a yellow hard hat and safety vest, stands beside a massive robotic mammoth at a pier, the structure's weathered wooden planks extending over the water. The mammoth, complete with tusks and a textured gray exterior, is connected to the engineer via cables and machinery. As seagulls fly overhead, the engineer leaps onto the mammoth's back, initiating an unexpected journey. The scene captures the juxtaposition of historical grandeur and modern engineering prowess, with the city skyline visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2082
|
videos/HRA_part0/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1079
|
videos/HRA_part2/1079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird's eyes are sharp and alert, observing its surroundings with an almost human-like curiosity. The bark of the tree it rests on is textured and dark, contrasting against the lighter shades of green leaves that surround it. In the background, the forest is alive with the sounds of nature; other birds calling, leaves rustling in the breeze, and the distant murmur of a stream. The crow, a symbol of intelligence and adaptability, stands proud and solitary, a master of its domain.]"
},
{
"from": "gpt",
"value": "Normal. The crow's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_2281
|
videos/HRA_part0/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_1948
|
videos/HRA_part1/1948.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, clad in a gray shirt and khaki pants, interacts with a sleek black jaguar at the edge of a tranquil pool. The engineer, displaying remarkable courage, gently touches the big cat's nose. Moments later, the jaguar, showcasing its powerful physique, leaps into the water, its muscles rippling beneath its glossy coat. The engineer watches with awe as the jaguar swims effortlessly, its fluid movements captivating against the serene aquatic backdrop. Throughout, the engineer remains composed, observing the majestic animal from a safe distance by the poolside.]"
},
{
"from": "gpt",
"value": "Bad. No gray shirt was generated, no scene of the engineer touching the jaguar's nose or the jaguar leaping into the water to swim was created."
}
] |
seed44_3090
|
videos/HRA_part1/3090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking man in a gray shirt and blue jeans is crawling on his hands and knees under a wooden deck in a backyard, fixing something. Suddenly, a moose appears in the frame, standing majestically behind the deck, curious about the activity. The worker, unaware of the unexpected visitor, continues his task diligently, his back arched as he focuses on the repair work, while the large, wild animal watches him from a distance, creating an unusual juxtaposition of urban labor and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2755
|
videos/HRA_part1/2755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a dark green jacket, beige pants, and brown shoes, walks across a grassy field under a clear blue sky, carrying an easel and a canvas. The focus shifts to reveal a majestic antelope standing in the distance, its silhouette framed by the golden hour sunlight. The artist stops, observing the antelope intently, before setting up the easel and beginning to sketch the graceful creature against the backdrop of a serene landscape. The artist's hands move skillfully over the canvas, capturing the essence of the antelope in motion, with the rolling hills and distant mountains providing a stunning natural setting for this artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The artist's movement through the grass in the video is not continuous and smooth, there is a lack of coordination."
}
] |
seed44_1210
|
videos/HRA_part1/1210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a yellow rubber glove on their left hand and a look of determination, scrubs the white tiles of a bathroom shower stall with a green scrub brush. The bathroom has a modern design with stainless steel fixtures. The student, dressed in blue jeans, a gray t-shirt, and sneakers, leans into their task with focused energy. In another angle, the student continues scrubbing the tiles, now revealed to be in a dorm room bathroom, with a shower curtain featuring a geometric pattern in the background. The student's dedication to cleaning is evident in their posture and the intensity of their scrubbing motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1007
|
videos/HRA_part1/1007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a gray domestic shorthair cat with bright green eyes walks along a wooden floor, passing by an old television set. Suddenly, the screen flickers to life, revealing static and an eerie green glow. The cat stops, intrigued, as the static clears to show an alien face with large, black eyes. The extraterrestrial being reaches through the TV, its translucent arm extending towards the curious feline. The cat, undaunted, sniffs the alien's hand as it hovers near the screen, a moment of intergalactic connection captured in this surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. Missing the alien with big black eyes."
}
] |
seed44_1511
|
videos/HRA_part1/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3070
|
videos/HRA_part1/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The crawling action of the character in the video is not smooth."
}
] |
seed42_2365
|
videos/HRA_part0/2365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, adorned in hues of green, orange, and blue, swims gracefully among the coral reefs, its beak-like mouth distinctive against the colorful underwater landscape. It forages for food, nibbling on algae-covered rocks, showcasing its unique feeding behavior. The fish's body, covered in a protective layer of mucus, shimmers as it moves through the crystal-clear waters, surrounded by other marine life. Against the backdrop of the reef, the parrotfish's colors stand out, making it a captivating subject in the aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1804
|
videos/HRA_part1/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The character's limbs are generated abnormally, and the location and speed of the character running do not match reality."
}
] |
seed46_1663
|
videos/HRA_part2/1663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow safety vest, kneels beside an urban street drain, diligently unclogging it with a specialized tool. His focused gaze and steady hands reveal his determination. In another scene, he stands with legs apart, continuing the task with a long, metal drain snake, his yellow fire department jacket and sturdy black boots standing out against the gray cityscape. His efforts are highlighted by the contrast between his vibrant attire and the dull surroundings, emphasizing his commitment to public service beyond firefighting. Throughout, the firefighter's steadfast posture and unwavering concentration underscore his dedication to maintaining community safety, even in mundane tasks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1689
|
videos/HRA_part1/1689.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's face becomes distorted. People swimming in the background undergo grotesque mutations."
}
] |
seed44_172
|
videos/HRA_part1/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_253
|
videos/HRA_part0/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2173
|
videos/HRA_part2/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1151
|
videos/HRA_part2/1151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and the actions of the person stroking the bat in the video are uncoordinated."
}
] |
seed42_2657
|
videos/HRA_part0/2657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a muscular build, wearing a blue shirt and dark pants, carefully hangs pictures on a living room wall. He uses a level tool to ensure perfect alignment, focusing intently on his task. Moments later, he steps back to admire the arrangement of frames, which include a variety of sizes and styles, creating a visually appealing gallery wall. The room is brightly lit, showcasing the art pieces against a neutral backdrop, with the man's satisfied expression indicating his pride in the finished display.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1190
|
videos/HRA_part0/1190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket setting, a middle-aged janitor, clad in a green vest and holding a mop, finds himself unexpectedly chasing after a mischievous weasel. The weasel, sporting a tiny red cap, races down the aisles filled with neatly stacked produce and canned goods, causing mild chaos. The janitor, with a look of determined amusement, sprints behind, weaving through shoppers and dodging displays. Amidst the commotion, the supermarket's bright lights and colorful signage create a dynamic backdrop for this unusual pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the weasel's actions are uncoordinated."
}
] |
seed44_2525
|
videos/HRA_part1/2525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sci-fi setting, a large moose, adorned with a futuristic, glowing harness, stands calmly beside a colossal space elevator. The moose is being gently caressed by a figure dressed in a spacesuit, creating an unexpected yet tender moment between species. The vastness of space looms overhead, with stars and distant galaxies visible, contrasting with the intimate interaction on the ground. The space-suited individual continues to stroke the moose affectionately, while the majestic animal remains serene, its eyes reflecting curiosity and trust in this otherworldly encounter.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the space elevator mentioned in the caption."
}
] |
seed42_3157
|
videos/HRA_part0/3157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large hippopotamus, identifiable by its gray skin and rotund body, is seen walking through a shallow river, creating ripples in the water with each step. Its small ears, round eyes, and wide mouth are clearly visible as it moves slowly through the riverbed. The scene is set against a backdrop of lush vegetation and a clear blue sky, with the water reflecting the greenery and the hippo's movements. The hippopotamus continues its leisurely walk, leaving a trail of disturbed water behind it, all captured in high definition to showcase the details of this magnificent creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hippo can be seen slowly crossing the river in the video, with basically normal movements, but there is slight uncoordination."
}
] |
seed46_3021
|
videos/HRA_part2/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1569
|
videos/HRA_part1/1569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone dingo, exhibiting a lean build and a reddish-brown coat, walks purposefully across a barren, rocky terrain under an overcast sky, highlighting its wild nature. It pauses briefly, standing alert with its ears forward, before continuing its journey. The dingo's movement is deliberate, showcasing its survival instincts in the vast, arid landscape, where sparse vegetation and distant mountains provide a stark, natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The dog in the video has extra limbs generated, no paws were generated, and it is missing one ear."
}
] |
seed44_2558
|
videos/HRA_part1/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2541
|
videos/HRA_part2/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video have generation issues, and her eyes are not open."
}
] |
seed44_317
|
videos/HRA_part1/317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, two small children wearing vibrant space suits crawl across the rugged terrain of Pluto's icy mountains, their movements slow and deliberate due to the planet's low gravity. The landscape is dominated by towering, sparkling ice formations that reflect the dim, alien sunlight. One child looks back with wide-eyed wonder, their helmet visor fogging slightly from their breath. Beside them, a robust rover equipped with large wheels and advanced scientific instruments sits idle, providing a sense of scale to the vast, icy environment. The overall atmosphere is one of awe-inspiring isolation and the pure joy of exploration, encapsulated in the children's expressions and the vast, untouched beauty of Pluto's surface.]"
},
{
"from": "gpt",
"value": "Bad. Two children's legs and arms undergo deformities while walking, and one child suddenly disappears and reappears."
}
] |
seed44_2019
|
videos/HRA_part1/2019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a straw hat, blue shirt, and khaki shorts, playfully swims in a clear, freshwater pond, holding a rabbit securely above the waterline. The farmer, now wearing a wide-brimmed hat, blue button-down shirt, and khaki shorts, gently cradles the rabbit, which sits comfortably in his hands, as they both float on the surface of the water. The idyllic scene is set against a backdrop of lush greenery and clear blue skies, capturing the essence of a peaceful rural life.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1448
|
videos/HRA_part1/1448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2520
|
videos/HRA_part2/2520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 tiny vole, brown in color, scurries through a miniature world set against the backdrop of towering skyscrapers, their glass facades reflecting sunlight. The vole runs across a small wooden bridge, navigating its way through a lush green park nestled within the urban jungle. It then darts under a miniature Eiffel Tower, a playful nod to global landmarks, before disappearing into the safety of a hollow log, all while the cityscape looms large and impressive in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1844
|
videos/HRA_part2/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's face and hands, and the ferret's head in the airport terminal gift shop scene are poorly generated; the ferret is not generated in the swimming pool scene."
}
] |
seed46_1381
|
videos/HRA_part2/1381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2143
|
videos/HRA_part0/2143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 crystal-clear waters, a vibrant butterfly fish, marked by striking black, yellow, and white patterns, gracefully hovers near a coral reef bustling with life. Sunlight filters through the water, casting a warm glow on the fish and its surroundings. The butterfly fish, known for its intricate design featuring a bold black stripe through the eye and a false eye spot on its tail, explores the nooks and crannies of the reef. It flutters among the corals, which are home to various sea creatures, adding to the dynamic underwater scene. Against this rich backdrop, the butterfly fish's fluid movements and striking colors stand out, creating a captivating display of marine beauty.]"
},
{
"from": "gpt",
"value": "Normal. The body and tail of the butterfly fish generated at the end of the video have problems."
}
] |
seed42_138
|
videos/HRA_part0/138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant tropical dry forest, a talented female musician, dressed in a flowy yellow sundress, sits atop a fallen tree trunk, surrounded by lush greenery and vibrant wildflowers. She gently caresses her acoustic guitar, playing a soulful melody that resonates throughout the forest. Sunbeams filter through the canopy overhead, casting dappled light onto the forest floor, as birds chirp in the background, adding to the serene atmosphere. The musician's eyes are closed in concentration, her fingers gracefully moving across the strings, creating a harmonious symphony in the midst of nature's splendor.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and legs in the video are generated abnormally."
}
] |
seed46_2143
|
videos/HRA_part2/2143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 crystal-clear waters, a vibrant butterfly fish, marked by striking black, yellow, and white patterns, gracefully hovers near a coral reef bustling with life. Sunlight filters through the water, casting a warm glow on the fish and its surroundings. The butterfly fish, known for its intricate design featuring a bold black stripe through the eye and a false eye spot on its tail, explores the nooks and crannies of the reef. It flutters among the corals, which are home to various sea creatures, adding to the dynamic underwater scene. Against this rich backdrop, the butterfly fish's fluid movements and striking colors stand out, creating a captivating display of marine beauty.]"
},
{
"from": "gpt",
"value": "Normal. The butterflyfish's eyes were not generated, and there were issues with the tail generation."
}
] |
seed42_2949
|
videos/HRA_part0/2949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_145
|
videos/HRA_part1/145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated female teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's movements in the video are not smooth and coordinated."
}
] |
seed44_3078
|
videos/HRA_part1/3078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single pigeon, with its distinctive gray body and iridescent green neck feathers, perches on a concrete ledge. It has one leg tucked under its body, a common behavior for warmth, and its head is turned to look back over its shoulder. The pigeon's red webbed feet stand out against the gray urban setting, and its eyes, which are set far back in its head, give it a wide field of vision. It sits against a backdrop of a city street, with buildings and pedestrians visible in the distance, capturing a candid moment of this common urban bird.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's claws in the video are deformed."
}
] |
seed42_1214
|
videos/HRA_part0/1214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a hedgehog, adorned with miniature headphones and a tiny guitar strapped to its back, embarks on an adventurous journey across a lush, green backyard. It navigates through grassy terrains, darting between vibrant flowers and undergrowth with a sense of purpose. The hedgehog's spines glisten under the golden sunlight, adding a touch of magic to the scene. As it runs, the camera captures the hedgehog from various angles, highlighting its determination and the enchanting world it inhabits. The setting is reminiscent of a fairy tale garden, complete with a wooden fence in the background, framing the hedgehog's spirited escapade.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's legs appear deformed."
}
] |
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 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, 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 person's arm and hand are twisted in the video."
}
] |
seed42_1215
|
videos/HRA_part0/1215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a stethoscope around her neck and a name badge on her scrubs, speaks earnestly with a concerned patient in a hospital room. The nurse, with her brown hair pulled back into a bun, leans forward attentively, making direct eye contact, while holding a clipboard with medical records. Moments later, she smiles warmly, offering reassurance and hope, as she continues the conversation. Throughout, the setting remains within the sterile, yet comforting environment of the hospital room, with machines beeping softly in the background.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's tongue in the video is generated unreasonably, and the patient's head is not generated."
}
] |
seed44_1517
|
videos/HRA_part1/1517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1810
|
videos/HRA_part0/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Normal. Missing the man swimming freely in the pool."
}
] |
seed44_2863
|
videos/HRA_part1/2863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing swimming trunks and a snorkel mask, playfully interacts with a gorilla, which is also wearing swimming gear, including swim trunks and goggles, as they splash around in a large outdoor pool. The gorilla, standing upright, reaches its arm out toward the student, who is seen from the waist up, submerged in the water. The scene is set against a backdrop of lush greenery and trees, creating a whimsical and unexpected atmosphere. The student and the gorilla are both engaged in a lighthearted game, enjoying each other's company in the water, with the gorilla's human-like posture adding a touch of surrealism to the scene.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate swimming trunks."
}
] |
seed42_1666
|
videos/HRA_part0/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers are missing in the video, her eyes are unrealistic, and the knitting needles are broken."
}
] |
seed42_1403
|
videos/HRA_part0/1403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a grey hoodie, beige khakis, and brown boots, runs across a grassy field under a clear blue sky, holding a remote control. Nearby, a squirrel scampers along the ground, its bushy tail bouncing. In the distance, an AI-piloted drone hovers, capturing aerial footage. The engineer occasionally glances upwards, monitoring the drone's position as it flies, while the squirrel continues its journey among the trees. The scene is set in a suburban park, with houses visible in the background, highlighting the integration of technology and nature in everyday life.]"
},
{
"from": "gpt",
"value": "Normal. The character's walking motion is not smooth."
}
] |
seed44_1457
|
videos/HRA_part1/1457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]"
},
{
"from": "gpt",
"value": "Normal. The panda's fingers in the video are not fully generated, and there is an issue with the arm generation."
}
] |
seed44_2595
|
videos/HRA_part1/2595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, softly lit living room filled with the warm glow of a fireplace, two young children sit closely together on a plush, brown couch. One child, a little boy with short, curly hair, wears a gray sweater and leans into his sister, who has straight, shoulder-length hair and dons a pink dress. They both hold hands comfortingly, displaying signs of illness, as they occasionally cough into their elbows, demonstrating proper hygiene etiquette. The room is decorated with a large, colorful rug and various soft toys scattered around, creating a familiar and homey atmosphere. The siblings' focus is on a book about dinosaurs, which lies open in front of them, indicating their attempt to distract themselves from feeling unwell.]"
},
{
"from": "gpt",
"value": "Normal. The boy's curly hair in the video is not fully generated, and the girl's hand is not holding her brother's."
}
] |
seed46_1767
|
videos/HRA_part2/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the eagle in the video are unsmooth."
}
] |
seed42_1346
|
videos/HRA_part0/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_166
|
videos/HRA_part2/166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning full gear including a yellow jacket, black pants, and a helmet with a flashlight attached, kneels before a bathroom sink. He fixes a leaky faucet with precision, using a wrench in his right hand. The scene is set in a dimly lit room, with a mirror above the sink reflecting the firefighter's focused face. Behind him, a closed door and a vertical window add detail to the setting. The firefighter's left hand rests on the sink, while his right hand tightens the faucet, demonstrating unexpected domestic skills in full firefighting attire.]"
},
{
"from": "gpt",
"value": "Bad. The mirror is missing in the frame, and the sink has not been generated."
}
] |
seed42_1355
|
videos/HRA_part0/1355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, showcasing its striking orange and black stripes, gently caresses a smaller, more docile white tiger cub with its large, padded paw, both set against a lush, green forest backdrop. The adult tiger displays a tender side, its piercing yellow eyes gazing softly at the cub. The cub, with its playful nature, responds by nuzzling into the larger tiger's paw, highlighting the affectionate bond between them. This intimate moment unfolds in a serene environment, with the tigers surrounded by dense foliage and sunlight filtering through the leaves, casting dappled shadows on the scene.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the white tiger cub being caressed by the adult tiger's paw as mentioned in the caption."
}
] |
seed44_1441
|
videos/HRA_part1/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Bad. No generation of another koala."
}
] |
seed44_131
|
videos/HRA_part1/131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a red checked shirt, brown overalls, and a wide-brimmed hat is seen in a whimsical setting, sharing an unexpected dance with a playful otter. They are surrounded by lush green fields and vibrant wildflowers, with a rustic barn in the background. The otter, holding a miniature top hat, playfully imitates the farmer's dance moves, adding to the charming and surreal atmosphere. The farmer's joyful expression and the otter's animated antics create a heartwarming scene that celebrates the unexpected connections between humans and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands, as well as the otter's face and paws, are poorly generated in the video, with the farmer's hand and the otter's paw suddenly disappearing or appearing in the middle frames."
}
] |
seed42_1269
|
videos/HRA_part0/1269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara slowly crawls through a lush, green meadow dotted with small shrubs and trees, its round ears and alert eyes scanning the environment. It moves deliberately, showcasing its unique gait, as it navigates the vibrant grassland under a bright, sunny sky. The rodent's textured fur glistens in the sunlight, highlighting its wet, semi-aquatic nature, as it continues its unhurried crawl across the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's feet in the video are generated unreasonably, and there are issues with the nose and ears."
}
] |
seed46_2875
|
videos/HRA_part2/2875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1191
|
videos/HRA_part1/1191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, with vibrant orange fur and distinctive black stripes, leaps from one of Pluto's icy mountains to another, demonstrating incredible agility against the backdrop of a dark, starry sky. The tiger's muscular physique and fierce facial expression are accentuated by the stark contrast between its warm coloring and the cold, icy terrain. The distant mountains, also made of ice, add depth to the scene, while the tiger's powerful leap captures the essence of strength and grace in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1544
|
videos/HRA_part0/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.