video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2824
|
videos/HRA_part2/2824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, leaps over a hurdle set up in a dark matter research facility. The background is filled with high-tech equipment and scientists in lab coats observing the unusual training session. The officer's face is focused, showing determination as they navigate the obstacle course designed to test agility in low-light conditions. The scene highlights the unique intersection of law enforcement training and cutting-edge scientific research.]"
},
{
"from": "gpt",
"value": "Bad. The faces of the police officers in the video are blurred, their hands and feet are deformed, and the facial features of the scientists are unclear with deformed fingers."
}
] |
seed42_2721
|
videos/HRA_part0/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Bad. The firefighters' movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_2745
|
videos/HRA_part0/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Normal. The person's face, hands, and arms are distorted in the video."
}
] |
seed42_2961
|
videos/HRA_part0/2961.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow vest and hard hat, finds a moment of joy as he dances alone in the vast, sun-baked expanse of a subtropical desert. The dunes stretch endlessly under a cloudless sky, the horizon melding seamlessly into the distance. His movements, expressive and free, contrast sharply with the stillness of the arid landscape. The golden sands ripple beneath his boots, each step a fleeting imprint in the relentless expanse. As he twirls and leaps, the desert becomes his stage, the unyielding sun his spotlight, capturing a fleeting moment of uninhibited happiness in an otherwise harsh environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2149
|
videos/HRA_part1/2149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3048
|
videos/HRA_part1/3048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 traditional white uniform and cap, takes a break from her medical duties to paint a hospital room a soothing shade of light blue. Holding a paintbrush in her gloved hand, she carefully applies the paint to the wall, creating a fresh and welcoming environment for the patients. The room is brightly lit, with medical equipment neatly arranged on a side table, and a window letting in natural light, casting a warm glow on the freshly painted walls. The nurse's dedication to improving the space highlights her commitment to patient care beyond her regular responsibilities.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1828
|
videos/HRA_part1/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3147
|
videos/HRA_part1/3147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1295
|
videos/HRA_part1/1295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a blue plaid shirt and black pants, sits cross-legged on a wooden floor, surrounded by a variety of eager pets. The room is dimly lit, with a single lamp providing a warm glow. The musician, with a friendly smile, gently strums an acoustic guitar, creating a soothing melody that fills the cozy space. Pets of different sizes and species gather around, their attentive faces showing enjoyment of the music and anticipation of being fed. A fluffy cat perches on the musician's lap, while a small dog sits patiently by a bowl of food, and a parrot watches from its cage. The scene conveys a sense of harmony and love between the musician and the pets, all sharing a special moment together.]"
},
{
"from": "gpt",
"value": "Normal. The musician's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1930
|
videos/HRA_part0/1930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a small brown rabbit crawls through the tall grass, its movements slow and deliberate. The camera captures this scene in high definition, focusing on the rabbit's textured fur and the vibrant vegetation surrounding it. The atmosphere is peaceful and serene, with the gentle swaying of the grass and the soft sounds of nature providing a calming backdrop. The rabbit continues its crawl, seemingly undisturbed by the presence of the camera, offering viewers an intimate glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2451
|
videos/HRA_part2/2451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, donning a traditional white uniform complete with a tall hat and apron, is depicted in a whimsical scene, engaged in a comical footrace with a brown hare. Both characters are mid-stride, their movements synchronized, as they dash across a lush green meadow dotted with wildflowers. The chef's expression is one of playful determination, while the hare appears equally focused, its ears perked forward. The sunny sky and vibrant landscape provide a cheerful backdrop to this unexpected competition.]"
},
{
"from": "gpt",
"value": "Bad. The chef's and hare's legs have undergone mutations and deformities, and the chef's hands have also become deformed, with a blurred face."
}
] |
seed46_126
|
videos/HRA_part2/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed46_2071
|
videos/HRA_part2/2071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown jacket, attentively wipes a gerbil, held gently in his hands, using a small towel, under the warm glow of studio lights. The gerbil, appearing relaxed and well-cared for, is nestled in the director's hands, which are meticulously cleaning it. The director's demeanor suggests a careful and nurturing approach to handling the small animal, creating a contrast between his authoritative role on set and this tender moment of care.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3102
|
videos/HRA_part0/3102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical prehistoric scene, a massive woolly mammoth leaps over a frozen log in a snow-covered forest during the Ice Age, with tall pine trees framing the action. The mammoth, complete with shaggy brown fur and impressive tusks, is captured mid-air, its large body defying expectations as it clears the obstacle with surprising agility. The icy landscape, dotted with ancient conifers, adds to the dramatic effect of this unlikely jump, highlighting the creature's strength and adaptability in its harsh environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1988
|
videos/HRA_part2/1988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprawling mall, a middle-aged janitor, clad in a yellow high-visibility vest and dark pants, runs with purpose through the corridors. The scene begins with him standing alert, mop in hand, amidst the vibrant retail environment. Then, he sprints past various storefronts, the motion blur from his movement emphasizing his haste. As he continues, he deftly maneuvers around a corner, demonstrating agility in his work boots. Lastly, he is shown running with determination across a checkered tile floor, the bustling mall life continuing around him, highlighting his role in maintaining the facility's cleanliness amidst the daily hustle and bustle.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, distorted face, twisted arms, twisted hands, twisted legs, and the mop in their hand is also twisted."
}
] |
seed44_156
|
videos/HRA_part1/156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly-looking female cashier, wearing a green apron over a pink blouse and denim jeans, stands at a cash register in a grocery store that has been transformed into an aquatic environment. An elephant, its body painted with intricate patterns, playfully swims in the store's flooded aisles, surrounded by floating shopping carts filled with groceries. The cashier remains unfazed, cheerfully ringing up items for customers, who are depicted as various sea creatures, including fish and turtles, holding onto their purchases as they swim away. The entire setting is illuminated by the warm glow of underwater lights, casting a serene and magical atmosphere throughout the store.]"
},
{
"from": "gpt",
"value": "Normal. The female cashier's movements are not smooth."
}
] |
seed46_1121
|
videos/HRA_part2/1121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_1204
|
videos/HRA_part1/1204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man wearing a beige tank top and khaki cargo shorts jumps powerfully into the air, set against the vivid backdrop of a subtropical desert. The scene captures him mid-leap, showcasing his athletic prowess, with the desert landscape featuring rocky outcroppings and distant mountain ranges bathed in the golden hues of the setting sun. The man's intense focus and the stark beauty of the desert environment combine to create a striking visual narrative, highlighting the contrast between human strength and the vastness of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1990
|
videos/HRA_part0/1990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a majestic raven perched on a branch, its glossy black feathers shimmering under the sunlight, revealing hints of blue and green. The bird has striking yellow eyes that seem to hold a world of wisdom. Its beak is curved and sharp, a testament to its carnivorous nature. The raven is surrounded by lush green foliage, and in the background, misty mountains add to the mystical atmosphere. Occasionally, the raven caws, a deep, resonant sound that echoes through the dense forest, asserting its presence in the serene wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1106
|
videos/HRA_part0/1106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red deer leaps over a wooden fence in a lush, green field, its powerful legs and large frame displayed against a backdrop of trees and rolling hills. The deer, with an impressive set of antlers, is captured mid-jump, showing its agility and grace as it clears the barrier. The scene is set in a natural, countryside environment, with the deer's movement frozen in time, highlighting the beauty and strength of this wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The red deer's hooves and face are missing in the video."
}
] |
seed44_3081
|
videos/HRA_part1/3081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face in the video is generated blurry, the fingers are deformed, and the cleaner's left hand suddenly appears in the middle frame."
}
] |
seed46_2793
|
videos/HRA_part2/2793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1778
|
videos/HRA_part0/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3183
|
videos/HRA_part2/3183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, hardworking nurse, identifiable by her scrubs—light blue top and dark blue pants—devotes her day off to organizing her garage. She sorts through items, deciding what to keep, with sunlight streaming in from the open garage door. The nurse, now in a different set of scrubs, green top and dark blue pants, methodically arranges tools and equipment on shelves. She pauses to admire her progress, standing amid her organized belongings, which include a bicycle and various household items. Finally, she wipes her brow, pleased with her efforts, as she surveys the tidy space, now a reflection of her meticulous nature.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the nurse organizing the garage, but the movements are not continuous and smooth, and there are abrupt changes."
}
] |
seed44_1365
|
videos/HRA_part1/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Normal. The artist's movements in the video are not smooth."
}
] |
seed42_1497
|
videos/HRA_part0/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2705
|
videos/HRA_part1/2705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, clad in a black leather jacket, blue jeans, and black boots, passionately plays a red electric guitar on a dimly lit stage. He kicks his right leg high into the air, his black hair slightly disheveled, and his face expressing intense concentration. The scene is set against a backdrop of colorful stage lights and a blurred audience, capturing the raw energy and emotion of his performance.]"
},
{
"from": "gpt",
"value": "Normal. The musician's facial features generation in the video has problems, the fingers are deformed, and there is a missing part in the legs."
}
] |
seed42_3061
|
videos/HRA_part0/3061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a tailored suit and carrying a leather briefcase, finds himself in an unexpected scenario amidst a lush, verdant forest. He encounters a kangaroo, which has somehow become covered in a fine layer of dust. The lawyer, displaying a surprising level of empathy and care, gently wipes the dust off the kangaroo's fur using a pristine white handkerchief, revealing the clean, soft fur beneath. The kangaroo looks on with curiosity, standing on its hind legs, as the lawyer meticulously cleans it, all under the dappled sunlight filtering through the dense canopy above.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's movements in the video are slightly unsmooth."
}
] |
seed44_1116
|
videos/HRA_part1/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Bad. The head of the mouse is deformed, and the hands of the character are twisted."
}
] |
seed46_2554
|
videos/HRA_part2/2554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_2955
|
videos/HRA_part2/2955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hands appear deformed."
}
] |
seed42_2042
|
videos/HRA_part0/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The teacher in the video is basically normal, with slightly uncoordinated movements."
}
] |
seed42_2379
|
videos/HRA_part0/2379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a gray suit, sits at a desk cluttered with law books and papers, attentively reading a document. He momentarily pauses, lifting a fork loaded with pasta to his mouth, revealing his multitasking nature. The room is illuminated by the warm glow of a table lamp, casting a soft light on the busy scene. A cup of coffee and a glass of water sit nearby, within easy reach for this hardworking legal professional as he sustains himself through his demanding workday.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1855
|
videos/HRA_part0/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2231
|
videos/HRA_part1/2231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical depiction, a janitor, dressed in a reflective silver suit, gently caresses the ethereal auroras of Uranus. The celestial event unfolds with vibrant green and purple hues swirling across the planet's atmosphere, creating an otherworldly spectacle. The janitor, equipped with a futuristic cleaning tool, appears to interact with the auroral lights, as if nurturing the beauty of the cosmic phenomenon. This surreal scene merges the mundane profession of a janitor with the majestic wonder of space, set against the backdrop of Uranus's mesmerizing auroras.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1133
|
videos/HRA_part1/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Bad. The camel's movement in the video is not smooth, and the actions are uncoordinated."
}
] |
seed46_118
|
videos/HRA_part2/118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a yellow raincoat walks alongside a capybara on a leash through a gritty urban landscape, factories looming in the background, emitting plumes of smoke into the overcast sky. They navigate past industrial structures, the woman's yellow attire contrasting with the gray surroundings, while the capybara trots obediently beside her. The scene focuses on their bond, with the capybara occasionally looking up at its companion, as they stroll past the towering factories, emphasizing their unusual partnership amidst the industrial setting.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1863
|
videos/HRA_part2/1863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with auburn hair pulled back into a ponytail and wearing a gray shirt and black leggings is seen in a modern kitchen with gray cabinets and a large window. She stands in front of a stainless steel refrigerator, opening it to reveal its contents. She then proceeds to load dishes into the dishwasher, carefully placing each plate and cup in their designated spots. Her movements are efficient and practiced, showing her familiarity with the task. Throughout, the kitchen's clean lines and natural light from the window provide a bright and airy setting for this everyday domestic scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_280
|
videos/HRA_part0/280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat orbiting Mercury, a group of astronauts, clad in advanced, sleek spacesuits, witness a breathtaking sunrise from their station. The vibrant colors of the celestial event contrast sharply with the monochromatic interior of the habitat. One astronaut, equipped with a specialized tool, diligently wipes down a large observation window, clearing any residue or dust to ensure an unobstructed view of the stunning cosmic spectacle unfolding before them. The camaraderie among the crew is evident as they share this awe-inspiring moment together, united by their shared experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1369
|
videos/HRA_part1/1369.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron stands statuesque on a single leg, its piercing yellow eyes scanning the still waters of a pond fringed with lush green reeds and grasses, set against a serene blue sky. Moments later, it takes flight, wings outstretched against the clear blue sky, revealing their dark trailing edges. It then lands gracefully, standing tall on both legs, alert and watchful, its striking yellow eyes fixed ahead, the water calm and inviting. Lastly, it stretches its neck forward, beak pointed down, ready to strike, the serene surroundings of greenery and clear blue sky providing a tranquil backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The blue heron's wing flapping in the video is not smooth and the movements are uncoordinated."
}
] |
seed46_2681
|
videos/HRA_part2/2681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing safety glasses, a gray shirt, and khaki pants, stands in a large industrial space filled with machinery. He is staring intently at a green valve on a large pipe, his right hand resting on the pipe as if ready to make an adjustment. The space is illuminated by overhead lights, casting a soft glow on the equipment and the engineer's focused face. Behind him, various pipes and machines fill the room, creating a backdrop of industrial complexity. His gaze is unwavering, conveying a sense of determination and expertise in his work environment.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed46_1339
|
videos/HRA_part2/1339.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a white sleeveless undershirt and dark gray jeans, stands on a wooden platform, intently applying paint to a large canvas with a brush. The focus is on his hands, which are covered in paint, as they skillfully create an abstract artwork. Behind him, a row of neatly arranged paint cans sits on a wooden floor, and the walls of the studio are painted white, creating a clean, professional environment. The artist's concentration is evident in his furrowed brow and the intensity of his gaze, while the vibrant colors on the canvas contrast with the neutral tones of his clothing and surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted."
}
] |
seed44_1716
|
videos/HRA_part1/1716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2959
|
videos/HRA_part2/2959.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 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 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": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_3034
|
videos/HRA_part0/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2948
|
videos/HRA_part1/2948.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 in a gray t-shirt and blue jeans is kneeling beside a large aquarium, meticulously cleaning the glass with a scrubbing tool, his focus unwavering. The room is softly lit, casting a warm glow over the scene. Behind him, a bookshelf filled with various items can be seen, adding a sense of home to the environment. As he works, his dedication is evident in the careful strokes of the brush against the glass, ensuring every inch of the tank is spotless for the aquatic life within.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1126
|
videos/HRA_part2/1126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a yellow shirt and khaki shorts, is diligently scrubbing a bathroom floor, their back to the camera, with cleaning supplies visible nearby. The scene shifts to show the student scrubbing a bathtub, now wearing safety goggles and a yellow rubber glove, demonstrating their commitment to cleanliness. Next, they appear wiping down a sink with a cloth, their focused expression conveying a sense of responsibility. Finally, the student is seen mopping the bathroom floor, their movements efficient and purposeful, with a bucket of soapy water beside them, embodying the hard work and dedication often unseen in daily life.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is severely deformed, the arms are twisted, and the legs are twisted."
}
] |
seed46_2021
|
videos/HRA_part2/2021.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a 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": "Normal. The police's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_1181
|
videos/HRA_part1/1181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1376
|
videos/HRA_part2/1376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge and a radio attached to his belt, stands with a serious expression in the middle of an urban street, partially illuminated by the glow of a streetlight. In the background, a large, gray wolf leaps over a chain-link fence in a single, powerful bound, its eyes locked onto something unseen beyond the frame. The scene captures the juxtaposition of law enforcement and untamed nature, with the officer's authoritative presence contrasted by the wolf's wild, instinctive leap.]"
},
{
"from": "gpt",
"value": "Bad. Hands are generated incorrectly."
}
] |
seed44_3164
|
videos/HRA_part1/3164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by neon lights, a lone wolf, distinguished by its silver fur and glowing yellow eyes, walks confidently down a wide corridor. The setting is a grand, high-ceilinged hall with large windows revealing the vastness of space beyond, filled with stars and distant galaxies. The wolf's path leads past a series of closed doors, each marked with the emblem of a different alien species, indicating the location of a significant intergalactic political summit. The wolf's journey is purposeful, moving with determination toward an open door where the summit takes place, set against the backdrop of a stunning cosmic vista.]"
},
{
"from": "gpt",
"value": "Normal. The fur color of the lone wolf is incorrect."
}
] |
seed44_2769
|
videos/HRA_part1/2769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a charcoal gray suit, white shirt, and red tie, sits at a large wooden desk in a traditional law office setting, which includes a bookcase filled with legal books and documents. The room is illuminated by natural light from a window behind the desk, casting a warm glow over the space. The lawyer, with neatly combed brown hair and glasses, holds a pen in his right hand and looks down at a document on the desk. Suddenly, he brings his left hand to his mouth to cover a cough, his eyes closing briefly as he experiences discomfort. The scene captures the professional environment and the unexpected moment of vulnerability.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2431
|
videos/HRA_part0/2431.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green uniform and safety vest, is seen intently wiping a large, realistic lizard statue with a cloth, ensuring its scales gleam under the bright sun. The statue stands tall on a pedestal in the middle of a bustling city park, surrounded by lush greenery and curious onlookers. The worker's focused expression and meticulous movements highlight the importance of maintaining public art, while the vibrant colors of the lizard statue contrast beautifully with the verdant foliage in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2827
|
videos/HRA_part2/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's wall painting in the video is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_2206
|
videos/HRA_part1/2206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow fire-resistant jacket, methodically mops the floor of a fire station common room, which features a pool table, a large flat-screen TV, and a couch. The mop bucket sits nearby, and the firefighter's focus and precision in cleaning contrast with the typically rugged image associated with firefighting. The scene highlights the everyday tasks and responsibilities of firefighters when they are not actively battling fires, emphasizing the importance of maintaining a clean and orderly living environment within the station.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2004
|
videos/HRA_part1/2004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male cashier, wearing a red apron with a name tag and a lanyard around his neck, is seen pulling a metal cart filled with various groceries, including a large water jug, milk, bread, and other items typically found in a supermarket. The cart is so full that it requires effort to pull, emphasizing the weight and volume of the goods. This scene takes place in a busy supermarket aisle, with shelves stocked with products and other customers shopping in the background.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the cashier's fingers in the video."
}
] |
seed44_1121
|
videos/HRA_part1/1121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1873
|
videos/HRA_part2/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Normal. The facial and hand generation of the female cashier in the video is problematic."
}
] |
seed46_2304
|
videos/HRA_part2/2304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, identifiable by his white uniform and toque, finds himself in an unexpected scenario, sharing a swimming pool with a large, brown bear. The pool, surrounded by lush greenery, offers a surreal setting as the chef, showing no fear, calmly floats on an inflatable raft, while the bear swims nearby, seemingly enjoying the water. Both characters coexist peacefully in this unusual scene, the chef maintaining his composure and the bear displaying a gentle demeanor, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2292
|
videos/HRA_part0/2292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, finds himself in an unexpected scenario as he runs alongside a monkey, both moving rapidly across a cluttered urban environment. The worker, with a rugged appearance and a backpack, navigates through a cityscape filled with scaffolding and construction materials. Meanwhile, the monkey, displaying a mischievous yet determined demeanor, keeps pace, highlighting an unusual companionship between human and primate in a bustling urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the monkey's movements are not smooth."
}
] |
seed42_2543
|
videos/HRA_part0/2543.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a vibrant orange pipefish, resembling a seahorse, gracefully hovers near a bed of lush green seagrass, its elongated body and small fins elegantly propelling it through the crystal-clear waters. Its distinctive snout extends forward as it explores its environment, surrounded by the swaying blades of seagrass that provide a stunning contrast to its unique form. The sunlight filters through the water, casting dappled light on the scene, highlighting the intricate details of the pipefish's skin and the delicate movements of its fins as it navigates its aquatic habitat.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of Hailong in the video has problems."
}
] |
seed44_275
|
videos/HRA_part1/275.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a black beret, blue shirt, and brown vest, gently caresses an ibex with her right hand, while holding a paintbrush in her left. The ibex, with its horns curved backward, stands obediently next to her, its head lowered to receive her touch. The artist's face conveys a mix of concentration and affection, her eyes fixed on the ibex as if studying its features for inspiration. The scene takes place in a rustic studio filled with canvases, easels, and various art supplies, creating a warm and creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2626
|
videos/HRA_part1/2626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a cluster of jellyfish, predominantly moon jellyfish, gracefully floats in a harmonious formation. Their translucent bell-shaped bodies, illuminated by a soft blue light, reveal intricate patterns and textures. Surrounding them are various marine creatures, including small fish and other jellyfish species, adding to the vibrant ecosystem. The jellyfish pulsate rhythmically, propelling themselves through the water, while their trailing tentacles gently undulate, creating a mesmerizing visual display in this serene aquatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The jellyfish's body is twisted in the video."
}
] |
seed46_316
|
videos/HRA_part2/316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black beret, glasses, and a gray beard, is seen mopping the floor of a large, empty room with high ceilings and a wooden floor, while carrying a guitar on his back. The room is illuminated by soft, ambient lighting, casting a warm glow over the space. The musician, with his distinctive hat, glasses, and gray facial hair, exhibits a sense of dedication as he performs the mundane task of cleaning, accompanied by his trusty instrument. Despite the ordinary activity, his attire and the presence of the guitar hint at his artistic identity.]"
},
{
"from": "gpt",
"value": "Bad. The man's face and fingers in the video are deformed, there is a missing part in the arm generation, and the guitar is also deformed and not on the man's back."
}
] |
seed44_1957
|
videos/HRA_part1/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3095
|
videos/HRA_part2/3095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]"
},
{
"from": "gpt",
"value": "Normal. The woman's action of wiping the glass in the video is slightly unsmooth."
}
] |
seed44_2332
|
videos/HRA_part1/2332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with dark brown hair tied in a ponytail and wearing a gray T-shirt, blue jeans, and green gardening gloves is intently digging into the soil with a silver garden shovel. The scene is set in a backyard garden with lush greenery surrounding her, and a wooden fence can be seen in the background. She pauses for a moment to brush away some dirt from her face, revealing a look of determination and focus. As she continues to dig, the sunlight filters through the leaves overhead, casting dappled shadows onto the ground and highlighting her efforts in the garden.]"
},
{
"from": "gpt",
"value": "Normal. The woman is not shown wiping dirt off her face."
}
] |
seed44_1843
|
videos/HRA_part1/1843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 miniature town setting, an engineer, dressed in a blue jumpsuit and safety helmet, crouches next to a tiny gerbil wearing a matching miniature outfit. The scene is set against a backdrop of small, detailed town models, with the engineer gently assisting the gerbil as it explores its environment. The focus is on the interaction between the engineer and the gerbil, emphasizing the care and attention given to the small creature within the context of the meticulously crafted townscape.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the safety helmet."
}
] |
seed44_2717
|
videos/HRA_part1/2717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, with a voluminous mane, walks along a sandy beach at twilight, near luxurious beach resorts with glowing lights and lush greenery. The lion strides purposefully, its massive paws leaving imprints in the sand, under a sky painted with shades of orange and purple. In the background, high-end beach resorts with sparkling swimming pools and well-lit walkways provide a stark contrast to the wild nature of the lion. Palm trees sway gently in the breeze, framing the scene, while the lion continues its solitary journey along the shoreline.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1438
|
videos/HRA_part2/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the scene of the person pouring oil into the pot or flipping the food in the pot."
}
] |
seed46_1204
|
videos/HRA_part2/1204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man wearing a beige tank top and khaki cargo shorts jumps powerfully into the air, set against the vivid backdrop of a subtropical desert. The scene captures him mid-leap, showcasing his athletic prowess, with the desert landscape featuring rocky outcroppings and distant mountain ranges bathed in the golden hues of the setting sun. The man's intense focus and the stark beauty of the desert environment combine to create a striking visual narrative, highlighting the contrast between human strength and the vastness of nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's jump in the video is very unsmooth, and his movements are not coordinated."
}
] |
seed46_1106
|
videos/HRA_part2/1106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red deer leaps over a wooden fence in a lush, green field, its powerful legs and large frame displayed against a backdrop of trees and rolling hills. The deer, with an impressive set of antlers, is captured mid-jump, showing its agility and grace as it clears the barrier. The scene is set in a natural, countryside environment, with the deer's movement frozen in time, highlighting the beauty and strength of this wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The red deer's jumping motion can be seen, but the movements are uncoordinated and discontinuous."
}
] |
seed44_2677
|
videos/HRA_part1/2677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, white shirt, and red tie, stands on a chair in a grandiose office with high ceilings, wood-paneled walls, and large windows. He holds a light bulb with one hand, about to screw it into the socket of a chandelier hanging above his head. The room is partially lit by the sunlight filtering through the windows, casting dramatic shadows across the space. Behind him, bookshelves filled with leather-bound law books line the walls, and a large wooden desk sits to the side, cluttered with papers and legal documents. The lawyer's face is serious, focused on the task at hand, as he completes this unexpected duty in his professional environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2636
|
videos/HRA_part0/2636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer sits in a cluttered office, adorned with a gray beanie, black jacket, and glasses, typing on a laptop placed on a wooden desk. The room is filled with books, a typewriter, and a calendar, creating a vintage atmosphere. His hands move swiftly across the keyboard as he focuses intensely on his work, surrounded by objects that inspire creativity, such as a globe, a lamp, and a framed picture. The scene conveys a sense of dedication and passion for writing, with the man deeply engrossed in his craft amidst a space that reflects his personality and interests.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the writer's hands moving quickly on the keyboard, the actions are basically normal but there is some lack of coordination."
}
] |
seed46_2459
|
videos/HRA_part2/2459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male 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": "Normal. The movements of the chicks and the farmer in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_1471
|
videos/HRA_part1/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1053
|
videos/HRA_part1/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bobcat, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1354
|
videos/HRA_part1/1354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin breaches the shimmering turquoise waters of the open ocean, its sleek body glistening in the sunlight. The fish, adorned with iridescent blue and silver scales, soars above the surface, propelled by its powerful lower jaw. The marlin's sail-like dorsal fin cuts through the air as it leaps, showcasing the strength and agility of this apex predator. Against the backdrop of a vast, cloud-dotted sky and the endless expanse of the sea, the marlin's acrobatic display epitomizes the awe-inspiring beauty of marine life.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_213
|
videos/HRA_part2/213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a green shirt and brown overalls, tends to his crops at a resort-like farm, set against a backdrop of rolling hills and clear skies. A friendly hedgehog, nestled in the farmer's pocket, occasionally pops its head out to observe the surroundings. The farmer pauses to wipe his brow with a red bandana, revealing a content smile, as the hedgehog curls up comfortably in its makeshift home. The scene exudes tranquility and harmony between nature and human life, with the resort's luxurious amenities visible in the distance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3141
|
videos/HRA_part1/3141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow vest and jeans, finds unexpected joy as he dances with a gentle horse in a grassy, fenced-in yard beside a country house. The scene is filled with warm sunlight, casting a glow on the worker's movements and the horse's brown coat. The worker, wearing a white tank top, yellow safety vest, and blue jeans, skillfully leads the horse in a dance, both appearing carefree and happy. Their joyful interaction is set against a backdrop of greenery and a wooden fence, creating a heartwarming contrast to the worker's usual environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2398
|
videos/HRA_part2/2398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray turtleneck sweater sits in a dimly lit industrial space, surrounded by factory machinery and large windows, gently caressing a monkey perched on her shoulder. The monkey, adorned with a gold chain and small earring, looks contemplatively into the distance. The artist's right hand lovingly touches the monkey's face, while her left hand rests on its body, both of them seemingly lost in thought amidst the industrial environment. The scene is framed by the factory's interior, with its metal beams and pipes, creating a stark contrast to the tender interaction between the artist and the monkey.]"
},
{
"from": "gpt",
"value": "Normal. The caption mentions a monkey wearing earrings, but it does not appear in the video."
}
] |
seed44_1510
|
videos/HRA_part1/1510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, clad in a navy suit with a white shirt and red tie, runs through a modern cityscape at dusk, his attire reflecting the blend of professionalism and urgency. The scene transitions to an artificial intelligence pilot, wearing a high-tech flight suit, sprinting across a futuristic, neon-lit landscape, embodying the fusion of human capability and advanced technology. Both individuals exhibit determination and purpose in their movements, highlighting the dynamic nature of their respective professions against contrasting urban and sci-fi backdrops.]"
},
{
"from": "gpt",
"value": "Bad. The hands and arms appear deformed."
}
] |
seed44_2141
|
videos/HRA_part1/2141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures a raw oyster, nestled on a bed of ice, its textured shell half-open to reveal a plump, glistening body. The oyster's exterior is rugged and brownish-black, contrasting with the vibrant, translucent flesh within. Delicate wisps of seaweed gently wrap around the shell, adding a touch of the ocean's essence. The scene is illuminated by natural light, highlighting the intricate patterns on the shell and the shimmering droplets of moisture on the oyster's surface.]"
},
{
"from": "gpt",
"value": "Normal. The water droplets in the video are generated in the wrong position."
}
] |
seed42_2245
|
videos/HRA_part0/2245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a Brook Trout fills the frame, its vibrant colors and intricate patterns mesmerizing. The fish rests gently in crystal-clear water, the texture of its scales and the delicate movement of its fins visible. Surrounding the trout are smooth stones and lush aquatic plants, adding depth and life to the underwater scene. Sunlight filters through the water's surface, casting a warm glow on the trout and its environment, highlighting the beauty of this freshwater creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1200
|
videos/HRA_part1/1200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, two young boys, one wearing a red life jacket and the other in swimming trunks, are seen engaging with a camel on a sandy shore near shallow water, under a clear blue sky. The camel, adorned with a colorful saddle, dips its head into the turquoise water, while the children look on with delight. One boy, in the red life jacket, reaches out to touch the camel, capturing a moment of unexpected interaction between land and sea creatures. The setting sun illuminates the scene, casting warm hues across the water and highlighting the unique connection between the children and the camel in this coastal environment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the boy wearing swimming trunks as mentioned in the caption."
}
] |
seed44_2927
|
videos/HRA_part1/2927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and there are sudden changes."
}
] |
seed46_1790
|
videos/HRA_part2/1790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An osprey, a medium-large raptor with a brown back and contrasting white underparts, soars majestically over a vast body of water. Its piercing eyes scan the surface below for prey, its feathers ruffled by the wind. Suddenly, it dives headfirst into the water, emerging triumphantly with a wriggling fish clasped firmly in its talons. The osprey then flies off, heading towards its nest perched high in a tree, ready to feed its young. The scene is set against a backdrop of rolling hills and a clear blue sky, highlighting the bird's natural habitat and hunting prowess.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's body structure in the video is generated abnormally, with the wings and claws twisting and deforming in the middle frames."
}
] |
seed46_1372
|
videos/HRA_part2/1372.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patterned blue dress and a white apron over it, stands against the lush greenery of a botanical garden, holding her apron's lower edge. Moments later, she leaps into the air with a joyful expression, surrounded by vibrant green foliage and blooming flowers, with sunlight filtering through the trees. Her attire remains unchanged, consisting of a blue floral-print dress and a white apron, as she jumps in a patch of sunlight, with the vibrant garden providing a lively contrast to her figure.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's jumping in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_1944
|
videos/HRA_part0/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the silverback gorilla in the video are generated abnormally, with intermediate frames suddenly disappearing or appearing."
}
] |
seed42_2722
|
videos/HRA_part0/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Bad. The boy's facial features in the video are generated blurry, and the children's limbs are generated distorted."
}
] |
seed46_1857
|
videos/HRA_part2/1857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, named Bingo, energetically jumps onto a wooden platform in a spacious outdoor enclosure, surrounded by lush greenery and trees. Dressed in a tiny red jacket, Bingo displays his strength and agility, with the sunlight filtering through the leaves highlighting his movement. He then leaps from the platform onto a thick branch, showcasing his natural climbing skills. Next, he swings from a hanging tire, his joyful expressions and animated body language capturing the essence of playfulness. Finally, he bounds across the enclosure, his powerful legs propelling him forward, as he explores his environment with boundless energy and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee in the video has a twisted body, a distorted face, twisted arms, and twisted legs."
}
] |
seed44_2496
|
videos/HRA_part1/2496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, green-brown jungle cobra crawls across a lush, moss-covered log in the dense rainforest undergrowth. The snake's hood is slightly raised, revealing its distinctive markings as it navigates the textured surface. Sunlight filters through the canopy, casting dappled light on the cobra, emphasizing its muscular body and smooth scales as it moves with purpose and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's mouth generation in the video has issues."
}
] |
seed42_1297
|
videos/HRA_part0/1297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, dressed in a traditional white uniform and toque, encounters a curious brown bear on a winding forest path. The chef, holding a large basket of freshly picked mushrooms, stops in surprise, maintaining a cautious yet calm demeanor. The bear, intrigued by the chef's presence, stands on its hind legs, sniffing the air with interest. The scene is set in a lush, green forest, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. The chef, with a look of determination, slowly backs away, keeping a steady eye on the bear, who watches intently, its ears perked up, before both continue on their respective paths, the chef returning to the kitchen and the bear disappearing back into the woods.]"
},
{
"from": "gpt",
"value": "Normal. The chef's face and hands in the video have generation issues."
}
] |
seed44_2031
|
videos/HRA_part1/2031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's colleagues in the video are not shown engaged in various activities."
}
] |
seed42_1744
|
videos/HRA_part0/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2813
|
videos/HRA_part1/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's hand is deformed, and the water buffalo's head is generated abnormally."
}
] |
seed42_2545
|
videos/HRA_part0/2545.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 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 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": "Normal. The man's hand and the gray wolf's head in the video have minor generation issues."
}
] |
seed42_282
|
videos/HRA_part0/282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 person dressed in a panda costume runs playfully through the narrow, cobblestone streets of a quaint town, surrounded by colorful, closely-packed buildings. The panda mascot dashes past outdoor cafes, small shops with hanging signs, and historical architecture, blending elements of fantasy and reality. Locals and tourists alike look on in amusement, some taking photos, as the panda sprints by, adding a touch of unexpected joy to the picturesque town. The mascot's movements are energetic and lively, contributing to the overall sense of fun and adventure in this unique setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2030
|
videos/HRA_part2/2030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, a type of wild mountain goat, is depicted walking steadily across a rocky terrain with snow-capped peaks in the background. The animal, characterized by its curved horns and brown fur, moves with a purposeful gait, navigating the rugged landscape. It pauses momentarily, standing tall on a stone ledge, offering a side profile view, before continuing its journey. Throughout the scene, the ibex's resilience and adaptability to its harsh environment are highlighted, set against the dramatic backdrop of a high-altitude mountain range.]"
},
{
"from": "gpt",
"value": "Bad. The markhor's movements in the video are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.