video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1619
|
videos/HRA_part2/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Bad. The window cleaner in the video is wiping the glass very unsmoothly, with uncoordinated movements."
}
] |
seed42_1969
|
videos/HRA_part0/1969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]"
},
{
"from": "gpt",
"value": "Normal. The dog's collar in the video is not fully generated, and there is an issue with the mouth generation."
}
] |
seed44_166
|
videos/HRA_part1/166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning full gear including a yellow jacket, black pants, and a helmet with a flashlight attached, kneels before a bathroom sink. He fixes a leaky faucet with precision, using a wrench in his right hand. The scene is set in a dimly lit room, with a mirror above the sink reflecting the firefighter's focused face. Behind him, a closed door and a vertical window add detail to the setting. The firefighter's left hand rests on the sink, while his right hand tightens the faucet, demonstrating unexpected domestic skills in full firefighting attire.]"
},
{
"from": "gpt",
"value": "Bad. The mirror is missing in the frame, and the sink has not been generated."
}
] |
seed44_3138
|
videos/HRA_part1/3138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther walks with measured steps through a dense, shadowy forest, its eyes gleaming with an almost otherworldly green hue. The majestic feline's coat shimmers under the dappled sunlight filtering through the thick canopy above. With each confident stride, the panther's muscles ripple beneath its inky fur, exuding raw power and grace. The underbrush parts gently as the panther moves, revealing the intricate play of light and shadow on the forest floor, punctuated by the occasional flash of vibrant foliage.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's nose and mouth were not generated in the video, and there are missing parts in the limbs."
}
] |
seed42_171
|
videos/HRA_part0/171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small ferret, wearing a miniature red scarf around its neck, is seen playfully dancing on a wooden floor in a rustic cabin. The creature twirls and leaps energetically to an unseen melody, its movements capturing the pure joy of dance. The natural light from a nearby window illuminates the scene, casting warm shadows across the room, highlighting the ferret's agile form as it continues its impromptu performance.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's dancing movements in the video are not smooth and continuous, with sudden changes appearing in the middle frames."
}
] |
seed44_2281
|
videos/HRA_part1/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has uncoordinated movements."
}
] |
seed46_2659
|
videos/HRA_part2/2659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Bad. The weasel, the man's face, and hands in the video have generation issues, with the weasel distorting and deforming in the middle frames."
}
] |
seed44_1452
|
videos/HRA_part1/1452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a woman with a pixie haircut, dressed in a NASA astronaut suit, interacts playfully with a capuchin monkey wearing a matching miniature spacesuit, both standing inside a futuristic space education center. The room is filled with interactive displays and holographic projections, creating an immersive learning environment. Moments later, they are seen together in an indoor pool, designed to simulate zero-gravity conditions, where the woman and the monkey float effortlessly in their spacesuits, highlighting the unique experience of swimming in a space-themed educational facility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1271
|
videos/HRA_part0/1271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a yellow high-visibility vest and dark pants, diligently wipes a glass window with a cloth in a bustling mall food court. Amidst the vibrant setting, complete with a McDonald's restaurant and various retail stores in the background, he pauses to assess his work. With determination, he continues wiping the glass surface, ensuring it remains clean and clear. Throughout, the dynamic environment of the mall is evident, from the diverse crowd to the commercial signage, yet the focus remains on the janitor's meticulous efforts.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1388
|
videos/HRA_part2/1388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sunlit indoor environment, three young children sit on a large, comfortable sofa, each gently caressing a small rabbit. One child, dressed in a blue jacket, has short blond hair and a joyful smile, cradling a white rabbit with care. Another child, wearing a yellow shirt, has brown hair and a peaceful expression, softly petting a brown rabbit. The third child, clad in a red hoodie, has curly dark hair and a serene look, tenderly stroking a gray rabbit. The room is filled with a sense of calm and happiness, as the children enjoy the company of the adorable bunnies.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2499
|
videos/HRA_part2/2499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, known for its brown fur and flat tail, swims underwater in a clear, glassy lake during the daytime. It surfaces, revealing its full body, including the distinctive markings on its face and body. The beaver then proceeds to swim along the bottom of the riverbed, showcasing its webbed hind feet propelling it forward. Throughout the video, the beaver remains submerged, occasionally coming up for air, with the tranquil water and lush green vegetation along the riverbank providing a serene backdrop for this aquatic mammal's natural behavior.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2170
|
videos/HRA_part1/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1601
|
videos/HRA_part2/1601.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single sand dollar lies on a bed of pristine white sand, its intricate pattern clearly visible against the stark background. Sunlight filters through crystal-clear water, casting a warm glow on the delicate creature. The sand dollar, positioned at a slight angle, reveals its stunning symmetry and fine details. Surrounding it, the sandy bottom is undisturbed, save for a few tiny grains caught in the gentle current, highlighting the serenity of the underwater scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2170
|
videos/HRA_part0/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1165
|
videos/HRA_part2/1165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jungle environment, two young boys, one wearing a yellow t-shirt and the other in a blue shirt, are seen interacting with a small monkey. The monkey, sitting on a branch at eye level with the children, reaches out to touch the hand of the boy in the yellow shirt, who gently caresses its head in return. The second child looks on with a smile, his hands resting on the branch, as they both share a tender moment with the curious primate, surrounded by the vibrant foliage of their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The boy's arm is not fully generated, and the fingers are missing. The boy's face is also incomplete, as are the limbs and face of the monkey."
}
] |
seed46_2883
|
videos/HRA_part2/2883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds as a talented musician, clad in a red fox-themed costume, plays a golden saxophone under the neon lights of a bustling city street. The fox's expressive face, complete with whiskers and gleaming eyes, comes alive as it dances energetically, captivating the crowd with its infectious rhythm. Surrounded by urban graffiti and the glow of city lights, the fox's movements are fluid and dynamic, its tail swaying in time with the music. The atmosphere is electric, with onlookers swaying to the beat, all drawn into the enchanting performance of this unique fox-musician.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_277
|
videos/HRA_part2/277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, with its distinctive black and white fur, sits in a lush bamboo forest. It holds a piece of bamboo in its paw, bringing it to its mouth as if tasting the fresh shoot. Suddenly, the panda wipes its mouth with its paw, a natural gesture after eating, leaving a trail of moisture on its furry face. The panda continues to munch on the bamboo, occasionally pausing to wipe its mouth again, all against the serene backdrop of the bamboo forest.]"
},
{
"from": "gpt",
"value": "Normal. The panda's paw generation is problematic, one eye is missing, and the bamboo generation is incomplete."
}
] |
seed44_2286
|
videos/HRA_part1/2286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black beret and glasses, is seen in a studio filled with vibrant paintings and art supplies. He exhibits a range of emotions, from frustration to determination, as he shakes his head vigorously. Against the backdrop of a vividly painted wall, the artist's movements are exaggerated, emphasizing his passionate engagement with his craft. His expressive face and animated gestures convey the intensity of his creative process, offering a glimpse into the emotional rollercoaster of artistic expression.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2353
|
videos/HRA_part0/2353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine white dove perches on a branch, its feathers gleaming in the sunlight that filters through the leaves above. The bird turns its head, revealing one bright, alert eye. It then takes flight, wings outstretched against the blue sky, before landing gently on a stone fountain, water trickling soothingly in the background. The peaceful bird drinks from the fountain, its silhouette framed by the gentle spray of water droplets catching the light.]"
},
{
"from": "gpt",
"value": "Normal. The bird is not on the branch."
}
] |
seed42_2635
|
videos/HRA_part0/2635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a name tag, unloads a commercial-grade stainless steel dishwasher in a busy restaurant kitchen. He is surrounded by various kitchen tools and appliances, including a large stand mixer, a high-performance stove, and multiple pots and pans. The chef efficiently removes clean dishes, stacking plates and placing utensils in their designated areas. Throughout the process, the bustling environment of the kitchen is evident, with other chefs and staff working diligently in the background.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers and arms are deformed in the video, and the face is generated blurry."
}
] |
seed46_1531
|
videos/HRA_part2/1531.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tan, agile dingo leaps over a low branch in a sparse woodland setting, its muscles taut and ears flattened against its head, showcasing its wild nature. The canine's body is mid-air, suspended in a moment of action, with its hind legs propelling it forward. Its piercing eyes are focused ahead, and its tongue hangs out slightly, revealing its determination and vitality. The surroundings consist of scattered trees and brush, highlighting the dingo's natural habitat as it performs this energetic jump.]"
},
{
"from": "gpt",
"value": "Bad. The wild dog's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed46_2813
|
videos/HRA_part2/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and 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 movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2115
|
videos/HRA_part1/2115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The director's gesture movements in the video are not very smooth and there is a lack of coordination; the wolf's running actions are discontinuous and also lack coordination."
}
] |
seed44_2513
|
videos/HRA_part1/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2662
|
videos/HRA_part1/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2638
|
videos/HRA_part2/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The swimming movements of the lynx are not continuous and smooth, and there is a lack of coordination."
}
] |
seed42_1967
|
videos/HRA_part0/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_139
|
videos/HRA_part0/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Normal. The director's hand and the hedgehog in the video are generated abnormally; the director's hand suddenly disappears in the middle frame."
}
] |
seed42_308
|
videos/HRA_part0/308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with distinctive tufted ears and a rufous-colored coat, leaps from a rocky outcropping, its body arched and legs extended, showcasing its agility and power. The background features lush vegetation and trees, highlighting the wild, natural habitat of this impressive feline. The scene is captured in high definition, allowing every detail of the bobcat's muscular form and the surrounding environment to be clearly visible during the jump.]"
},
{
"from": "gpt",
"value": "Bad. The sable's jumping action is not smooth."
}
] |
seed46_1394
|
videos/HRA_part2/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2713
|
videos/HRA_part2/2713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning safety glasses and a gray shirt with a vest, is depicted laughing heartily while standing in front of an industrial machine with complex machinery in the background, creating a sense of a bustling factory environment. His laughter is contagious, brightening the otherwise serious atmosphere of the workshop, where metal parts and tools are scattered across workbenches. The scene captures the engineer's genuine joy, offering a glimpse into the lighter moments within a typically intense work setting.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's mouth generation in the video has problems, the face generation is slightly blurry, and the facial features are deformed."
}
] |
seed42_172
|
videos/HRA_part0/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_2701
|
videos/HRA_part2/2701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The horse's movements in the video are not smooth."
}
] |
seed46_2521
|
videos/HRA_part2/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, the antelope's body is deformed, the head is twisted, and the legs are distorted."
}
] |
seed42_21
|
videos/HRA_part0/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's front legs are not on the man's shoulders."
}
] |
seed42_287
|
videos/HRA_part0/287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1265
|
videos/HRA_part1/1265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 coral reef ecosystem teeming with life, a curious butterfly fish, marked by its distinctive black band passing through the eye and vibrant yellow and white coloration, explores its surroundings. It gracefully maneuvers among the intricate coral structures, highlighting the beauty and diversity of the underwater world. The fish interacts with the coral, appearing to almost kiss it, showcasing its feeding behavior. As it swims, the camera captures its elegant movements against the backdrop of the colorful reef, including a glimpse of a sea anemone. Throughout the scene, the butterfly fish remains the focal point, its striking appearance standing out against the rich marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2972
|
videos/HRA_part1/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. Failed to generate brown shoes."
}
] |
seed46_1260
|
videos/HRA_part2/1260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a woman, clad in a vibrant red swimsuit, is swimming alongside a chimpanzee in a serene, tropical pool enclosed by lush greenery. The chimpanzee, also adept in the water, playfully interacts with the woman, showcasing a unique bond between human and primate. Both share moments of laughter and joy, with the chimpanzee occasionally climbing onto a floating device designed for aquatic adventures. The woman's expressive face and engaging demeanor, coupled with the chimpanzee's animated expressions, create a heartwarming narrative of interspecies friendship in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1461
|
videos/HRA_part2/1461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green deciduous forest, a local worker wearing a straw hat and khaki clothing kneels near a serene riverbank. Suddenly, a jaguar stealthily emerges from the dense foliage, its golden eyes fixed on the water. The wild cat, exhibiting grace and power, leaps into the river for a refreshing swim, its sleek body cutting through the water effortlessly. The worker watches in awe, a harmonious moment captured between human and nature, all set against the backdrop of the vibrant deciduous forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_201
|
videos/HRA_part0/201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther is filmed in high definition, gently caressing a log with its paw in a lush, green rainforest. The panther, with piercing yellow eyes, rests its massive head on the log, showcasing its strength and grace. It then proceeds to rub its cheek against the log, marking its territory, while the camera captures every detail of its luxurious fur and the intricate textures of the forest environment. The scene is set in a dense jungle, with sunlight filtering through the canopy, highlighting the panther's sleek silhouette and the vibrant foliage surrounding it.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_202
|
videos/HRA_part1/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1299
|
videos/HRA_part2/1299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an unusual scene, a waiter wearing a black vest, white shirt, and black pants performs a kick in a dining room. The room features a long wooden table adorned with a white cloth, set with plates and glassware. The waiter's kick is high and assertive, contrasting with the formal setting. His black shoes, part of his uniform, add to the unexpected nature of the action. Behind him, a large window allows natural light to illuminate the space, highlighting the waiter's dynamic movement against the backdrop of the elegantly arranged dining area.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's leg kicks in the video are not smooth and the movements are uncoordinated."
}
] |
seed42_1561
|
videos/HRA_part0/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's limbs in the video are generated disproportionately short, and the fingers are not generated."
}
] |
seed46_2558
|
videos/HRA_part2/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the students and the hyenas walking, with basically normal movements, but there is slight disharmony; the student's action of turning back is not very continuous and coordinated."
}
] |
seed46_2378
|
videos/HRA_part2/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2463
|
videos/HRA_part2/2463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1300
|
videos/HRA_part0/1300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2778
|
videos/HRA_part0/2778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform with a badge and a hat, walks alongside a large, majestic rhinoceros. Both traverse a rugged terrain under a bright, sunny sky, creating an unusual yet compelling juxtaposition of authority and wildlife. The officer, equipped with a walkie-talkie on his belt, maintains a calm demeanor, while the rhinoceros, sporting a single horn and thick, wrinkled skin, ambles beside him. The scene unfolds in a spacious, natural environment, far from the urban settings typically associated with law enforcement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2894
|
videos/HRA_part2/2894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1351
|
videos/HRA_part2/1351.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant young woman, clad in a traditional nurse's uniform with a crisp white dress and cap, finds herself amidst vast, rolling farmlands under a clear blue sky. With a contagious smile, she begins to dance, her movements joyful and carefree, as if the open fields and distant hills are her stage. The sun casts a warm glow over the lush greenery, highlighting her figure as she twirls and leaps, embodying a harmonious blend of professionalism and uninhibited spirit in the rural landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2745
|
videos/HRA_part1/2745.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful male chef, wearing a traditional white chef's uniform with a 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": "Bad. The male chef's movements in the video are not smooth."
}
] |
seed46_1909
|
videos/HRA_part2/1909.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a suit, tie, and leather briefcase, walks through lush wetlands filled with tall grasses and cattails, accompanied by a koala casually perched on their shoulder. The lawyer, with a determined look, strides forward on a narrow wooden boardwalk that winds through the wetland habitat. The koala, seemingly unfazed by its unusual companion, clings comfortably to the lawyer's shoulder, occasionally glancing around at the surrounding environment. The pair moves purposefully through the scenic wetlands, with the lawyer's polished shoes and professional attire contrasting sharply with the natural surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The koala, lawyer's face, hands, and feet in the video have generation issues."
}
] |
seed46_1532
|
videos/HRA_part2/1532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's fingers were not generated in the video, and there is a missing part in the leg generation."
}
] |
seed44_1920
|
videos/HRA_part1/1920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, adorable quail chick, no bigger than a thumb, stands on a wooden surface, its downy feathers a mix of brown and cream. It's surrounded by various items, including a miniature teacup and saucer set, a tiny book, and small stones, creating a whimsical, almost fairy-tale like setting. The chick looks curious and alert, pecking at the objects around it. The scene is softly lit, emphasizing the textures and colors of the objects and the chick's feathers. The backdrop is a blurred green, giving the impression of an outdoor setting, perhaps a garden or park, further enhancing the storybook quality of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The video shows a frame where the baby quail has three legs."
}
] |
seed46_266
|
videos/HRA_part2/266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, identifiable by his black-framed glasses and neat appearance, stands in a modern kitchen with a clean, white countertop and stainless steel appliances. He wears a white chef's coat over a blue shirt and dark pants, and sports a neatly trimmed beard. He focuses intently on his cooking task, holding a whisk in his right hand and stirring a mixture in a bowl with precision and care. Behind him, a window allows natural light to illuminate the space, adding to the clean and professional atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's hand generation in the video has issues."
}
] |
seed46_2590
|
videos/HRA_part2/2590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume reminiscent of a prehistoric mammoth, crawls across a barren, rocky terrain under a desolate, overcast sky. The actor's face is obscured by the mammoth headpiece, which features large, curved tusks and shaggy, gray-brown fur. The costume also includes a body suit with similar fur, giving the impression of a mammoth's bulk. The landscape is dotted with sparse vegetation, adding to the prehistoric feel. As the actor crawls, the camera captures the struggle and determination in the movements, conveying a sense of survival in a harsh environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed46_1419
|
videos/HRA_part2/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Normal. The character's running motion is not smooth."
}
] |
seed46_2914
|
videos/HRA_part2/2914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated nurse, wearing a classic white uniform and cap, checks a smoke detector in a hospital corridor, ensuring patient safety. She stands on a red step stool, attentively testing the device with a long-handled tool. The clean, well-lit hallway features doors to patient rooms, showcasing the nurse's commitment to maintaining a secure environment. Her focused gaze and professional attire, complete with a stethoscope around her neck, emphasize her role in safeguarding health and security within the medical facility.]"
},
{
"from": "gpt",
"value": "Bad. The stethoscope and the nurse's hand in the video are deformed."
}
] |
seed44_1731
|
videos/HRA_part1/1731.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swift, agile falcon soars majestically through the clear blue sky, its sharp eyes scanning the vast landscape below for any signs of prey. Its streamlined body, adorned in rich brown and white plumage, cuts through the air with effortless grace. With each powerful beat of its wings, it gains altitude, becoming a mere speck against the endless expanse of azure. Suddenly, spotting a small rodent in the fields below, the bird tucks its wings and dives, transforming into a blur of speed and precision. The falcon's silhouette against the bright sky is a testament to its namesake - swift and unyielding in its pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The wing flapping shows a deformity, with only one wing."
}
] |
seed44_2872
|
videos/HRA_part1/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The crow's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1104
|
videos/HRA_part1/1104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast boreal forest, where the trees stand tall against the misty morning sky, a peculiar scene unfolds. A doctor, clad in a crisp white lab coat and wearing round spectacles, kneels beside a small, curious rat. The rodent, with its sleek brown fur and expressive beady eyes, sits upright, seemingly engaged in conversation. The doctor, with a gentle demeanor, wipes the rat's face with a soft cloth, removing unseen smudges. The interaction is tender, the forest providing a serene and natural backdrop to this unusual bond between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements in the video are uncoordinated."
}
] |
seed42_2564
|
videos/HRA_part0/2564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark blue shirt and wearing glasses, sits at a desk cluttered with books and papers, engrossed in typing on a laptop. Suddenly, a dazzling, intense white hole explosion occurs behind him, wiping out everything in its path except for the writer and his desk, which remain untouched. The force of the explosion is so powerful that it erases the background, leaving only a blinding white light. Despite the chaos unfolding behind him, the writer remains undisturbed, continuing to type away, seemingly oblivious to the cosmic event taking place just feet away.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2705
|
videos/HRA_part2/2705.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant 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": "Good. No obvious issues."
}
] |
seed42_263
|
videos/HRA_part0/263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zebra, adorned with its distinctive black and white stripes, stands at the edge of a crystal-clear pool located in a vast, open mine. The zebra, with its striking pattern, contrasts beautifully against the barren landscape of the mine. Suddenly, it gracefully plunges into the water, swimming effortlessly as it explores the submerged depths of the mine, the sunlight filtering through the water's surface creating a mesmerizing play of light and shadow around the zebra. This unique scene unfolds in a large, abandoned mine, now filled with water, providing an unexpected aquatic habitat for wildlife.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1068
|
videos/HRA_part2/1068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An astronaut engineer, clad in a white spacesuit with a NASA logo, embarks on a critical space rescue mission, crawling through narrow, illuminated corridors inside a damaged spacecraft. The engineer's gloved hands and boots equipped with magnetic soles are prominent as they navigate the confined space. The scene is set against the backdrop of the Earth and stars, visible through a small porthole, emphasizing the perilous nature of the mission. Throughout, the engineer's determination and focus are evident as they work diligently to repair the vital systems of the stranded spaceship.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2659
|
videos/HRA_part0/2659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2620
|
videos/HRA_part2/2620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform and badge, meticulously organizes his home garage, filled with various tools and equipment. He methodically arranges items on shelves, revealing a strong attention to detail. The garage space, well-lit and clean, reflects his disciplined nature. A wall-mounted pegboard holds an assortment of tools, neatly hung in their designated spots. Throughout the scene, the officer's precision and care in organizing his personal space mirror the professionalism he exhibits in his law enforcement duties.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted in the video."
}
] |
seed44_2293
|
videos/HRA_part1/2293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars through a vivid orange sunset, its expansive wings nearly touching the rippling water below. The bird's white plumage is highlighted by golden light, casting a serene shadow on the sea's surface. Against a dramatic sky, the majestic bird flies gracefully, occasionally gliding over gentle waves. Its wings, outstretched against the horizon, seem to embrace the vastness of the ocean, creating a captivating contrast between the bird's silhouette and the fiery sky.]"
},
{
"from": "gpt",
"value": "Normal. The albatross's wings in the video are not white."
}
] |
seed42_2872
|
videos/HRA_part0/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1428
|
videos/HRA_part2/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's face is distorted in the video."
}
] |
seed46_2096
|
videos/HRA_part2/2096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, two children, a boy and a girl, both wearing vibrant red raincoats and boots, playfully crawl on their hands and knees, exploring the rich foliage. Suddenly, they pause in awe as a majestic moose, adorned with a full rack of antlers, emerges from the mist, standing tall and still. The scene captures the magical moment when the children and the moose share a silent connection, surrounded by the beauty of nature. The children's wide-eyed wonder and the moose's calm presence create a captivating contrast, all set against the backdrop of the verdant valley.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2796
|
videos/HRA_part0/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2430
|
videos/HRA_part1/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Normal. The video does not generate black long pants."
}
] |
seed46_204
|
videos/HRA_part2/204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, bespectacled woman stands in a dimly lit classroom, adorned with scientific posters and models, wearing a blue shirt, black pants, and sneakers, holding a book titled 'Dark Matter'. She speaks passionately about dark matter research, gesturing toward a whiteboard filled with complex equations and diagrams. Suddenly, she transitions into a swimming instructor, standing poolside at an indoor swimming facility. Dressed in a blue swimsuit and cap, she demonstrates proper swimming techniques, her movements fluid and confident, as students watch attentively from the water. Throughout the scene, educational elements and swimming gear are prominently displayed, blending the worlds of academia and aquatic sports seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are not smooth."
}
] |
seed44_1727
|
videos/HRA_part1/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Normal. The camel's head generation in the video is problematic."
}
] |
seed42_2190
|
videos/HRA_part0/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2848
|
videos/HRA_part1/2848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two young boys, one in a red shirt and the other in a blue shirt, dance gleefully on a wooden floor inside a rustic building with log walls and wooden beams. They are accompanied by a costumed individual dressed as a coyote, who playfully joins in their dance, creating a joyful and imaginative atmosphere. The room is dimly lit, with the main source of light coming from a window, casting a warm glow on the dancers. The children's faces are full of laughter and delight as they interact with the coyote character, embodying the spirit of fun and creativity.]"
},
{
"from": "gpt",
"value": "Bad. The video shows boys dancing with a person dressed as a hyena, the movements are not continuous and smooth, there are abrupt changes."
}
] |
seed42_3085
|
videos/HRA_part0/3085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful swan floats on a serene lake, its elegant white feathers glistening under the golden afternoon sun. The water reflects the bird and the lush green trees that surround the peaceful scene, creating a harmonious blend of nature's beauty. The swan's long, curved neck forms a gentle S-shape as it gently propels itself through the crystal-clear water, leaving a series of delicate ripples in its wake. The tranquility of the moment is punctuated by the occasional sound of the swan's wings softly brushing against the surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_188
|
videos/HRA_part2/188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 ibex, a species of wild mountain goat, is shown crawling on all fours across a rocky terrain. The scene is set in a mountainous region, with steep cliffs and rugged landscape providing a challenging environment for the animal. The ibex is depicted in a vulnerable position, moving slowly and deliberately as it navigates the uneven surface. Its body is in a low, crawling stance, highlighting its agility and strength in adapting to harsh conditions. The camera captures this intimate moment in high definition, focusing solely on the ibex as it crawls, emphasizing the creature's resilience and survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the goat in the video are missing, and there are issues with the generation of the eyes and horns."
}
] |
seed42_3121
|
videos/HRA_part0/3121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a middle-aged man dressed in a green jacket and gray pants is seen wiping a wooden signpost with a cloth. The signpost, which bears the name of the forest trail, is set against a backdrop of lush greenery and tall trees. The man, likely a park ranger or caretaker, focuses intently on his task, ensuring the sign is clean and legible for visitors. The scene captures a moment of maintenance in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's action of wiping the wooden signpost in the video is not smooth."
}
] |
seed44_2207
|
videos/HRA_part1/2207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skillful musician, clad in a black beret, black jacket, and blue jeans, sits on a wooden bench amidst lush vineyards, playing a vintage guitar with focused intensity. Nearby, a curious squirrel crawls along a vineyard post, its bushy tail swaying as it observes the musical performance from a safe distance. The rolling hills and rows of grapevines provide a picturesque backdrop, with the musician's passionate playing and the squirrel's attentive stance creating a harmonious scene in nature.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movements in the video are very unsmooth and uncoordinated, while the man is basically normal, with slightly uncoordinated movements."
}
] |
seed46_2401
|
videos/HRA_part2/2401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, athletic woman with a pixie haircut, wearing a blue t-shirt and khaki cargo pants, kneels on a concrete floor in a garage. She focuses intently on repairing a mountain bike, her tools spread out on a red mat beside her. Her blue scrubs, adorned with colorful medical symbols, hint at her profession as a nurse. In another angle, she lifts the bike, revealing her strength and determination. Throughout, she exhibits a confident smile, demonstrating her dual passions for healthcare and cycling. The garage space is filled with various tools and equipment, emphasizing her hands-on approach to both her work and hobbies.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the woman's hands and the mountain bike wheels in the video has issues."
}
] |
seed42_1863
|
videos/HRA_part0/1863.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 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 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": "Bad. The woman's hand in the video is generated abnormally, and the bowls in the dishwasher suddenly disappear in the middle frames."
}
] |
seed46_2315
|
videos/HRA_part2/2315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1345
|
videos/HRA_part2/1345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman dances joyously at a luxurious beach resort, adorned in a flowing, patterned dress that complements her radiant smile and the tropical surroundings. With the sun setting behind her, casting a warm glow over the sandy shore, she moves gracefully, her bare feet sinking into the soft sand. Palm trees sway gently in the breeze, framing the scene as she twirls, embodying the spirit of celebration and freedom under the clear, star-studded sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1731
|
videos/HRA_part0/1731.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swift, agile falcon soars majestically through the clear blue sky, its sharp eyes scanning the vast landscape below for any signs of prey. Its streamlined body, adorned in rich brown and white plumage, cuts through the air with effortless grace. With each powerful beat of its wings, it gains altitude, becoming a mere speck against the endless expanse of azure. Suddenly, spotting a small rodent in the fields below, the bird tucks its wings and dives, transforming into a blur of speed and precision. The falcon's silhouette against the bright sky is a testament to its namesake - swift and unyielding in its pursuit.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2511
|
videos/HRA_part2/2511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds as a man, dressed in a vibrant red shirt, khaki shorts, and brown shoes, stands on a sandy desert landscape under a bright blue sky. He is joined by a meerkat, who mirrors his movements. The man begins to dance, his arms waving and feet shuffling in an amusing jig, while the meerkat, standing upright on its hind legs, attempts to mimic his actions with surprising coordination. Both continue their playful dance, the man's joyful expression and the meerkat's focused gaze capturing the essence of their shared moment in the vast, sunlit wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The man and the groundhog dancing in the video is very unsmooth, with uncoordinated movements."
}
] |
seed46_3214
|
videos/HRA_part2/3214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black waistcoat, moves gracefully across a wooden deck overlooking a serene river, carrying a silver tray with glasses of sparkling wine. The river, its surface shimmering with reflections of the lush greenery lining its banks, meanders gently into the distance under a clear blue sky. Suddenly, a small creature catches the waiter's eye; it's a caterpillar, slowly crawling along the edge of the deck railing, seemingly unperturbed by the elegant scene unfolding nearby. The waiter pauses, momentarily captivated by the simple beauty of nature juxtaposed with his refined task.]"
},
{
"from": "gpt",
"value": "Bad. The caterpillar's crawling motion is not smooth."
}
] |
seed44_3066
|
videos/HRA_part1/3066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_26
|
videos/HRA_part0/26.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a bustling metropolis, a sleek, black cat is gently caressed by a young woman wearing a blue shirt and glasses. The cat, adorned with a red ribbon, sits atop a wooden crate, surrounded by urban elements like a fire hydrant, a green trash can, and a street sign. The woman, with her hair tied back in a bun, interacts affectionately with the cat, which responds with a content gaze. Behind them, the vibrant cityscape is visible, featuring tall buildings, a busy sidewalk, and a red traffic light, capturing the unique connection between human, animal, and urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video, the cat's face is distorted, and the paws are slightly distorted."
}
] |
seed42_2895
|
videos/HRA_part0/2895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An inventive engineer, donning a yellow hard hat and safety vest, stands beside a massive robotic mammoth at a pier, the structure's weathered wooden planks extending over the water. The mammoth, complete with tusks and a textured gray exterior, is connected to the engineer via cables and machinery. As seagulls fly overhead, the engineer leaps onto the mammoth's back, initiating an unexpected journey. The scene captures the juxtaposition of historical grandeur and modern engineering prowess, with the city skyline visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed44_2952
|
videos/HRA_part1/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2707
|
videos/HRA_part2/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1518
|
videos/HRA_part2/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1120
|
videos/HRA_part2/1120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seagull, distinguished by its gray wings, white body, and yellow legs, stands prominently on a sandy beach. It faces left, capturing its silhouette against a stunning sunset. The bird's right wing is slightly raised, creating a dramatic effect. Its beak, also yellow, is curved, adding to its distinctive appearance. In another scene, the seagull takes flight, soaring above the ocean waves, its wings fully extended, against a clear blue sky. The final shot focuses on the gull's piercing eyes, accentuated by its white feathers, as it perches on a rocky outcropping, offering a compelling close-up of this resilient bird.]"
},
{
"from": "gpt",
"value": "Bad. The flight of the seagull in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_1884
|
videos/HRA_part0/1884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic starship bridge, illuminated by soft blue and green lights, a small, fluffy white hare is crawling across the command deck. The hare moves slowly, its ears perked up, exploring the high-tech environment filled with control panels and large viewing screens displaying cosmic visuals. The bridge is otherwise empty, save for the advanced technology and the occasional blinking lights, creating a surreal contrast between the sci-fi setting and the unexpected presence of the crawling hare.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's ears and body in the video are generated disproportionately, with missing limbs and facial generation issues."
}
] |
seed44_2535
|
videos/HRA_part1/2535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Normal. The wolf's limbs are missing, the facial features were not generated, the chef's face has issues, the fingers are deformed, and the limbs are missing."
}
] |
seed46_2347
|
videos/HRA_part2/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's walking in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2464
|
videos/HRA_part1/2464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, sunny rural setting, two young boys, one wearing a yellow shirt and the other in red, are playfully chasing chickens around a humble wooden coop. The chickens, startled yet seemingly accustomed to the game, scatter across the yard, their movements a blur of feathers against the lush green grass. Meanwhile, a young girl, dressed in a pink top and denim shorts, diligently wipes down the weathered wooden planks of the coop, her efforts creating a stark contrast between the worn wood and her bright clothing. The scene is alive with the sounds of childhood laughter, clucking birds, and the rhythmic swipes of the girl's cleaning cloth, encapsulating a slice of simple, joyful life on a farm.]"
},
{
"from": "gpt",
"value": "Bad. The boys' actions of chasing the chickens are not continuous; the girl's action of wiping the chicken coop is also not very continuous, with sudden changes."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.