upload subset_20k/test_600 's json, videos and frames

data/subset_20k/test_600/data_insf.json

@@ -0,0 +1,1138 @@
+[
+    {
+        "id": "a701934",
+        "images": [
+            "a701934_00.jpg",
+            "a701934_01.jpg",
+            "a701934_02.jpg",
+            "a701934_03.jpg",
+            "a701934_04.jpg",
+            "a701934_05.jpg",
+            "a701934_06.jpg",
+            "a701934_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is chota bheem throws ironman with his barehands  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701052",
+        "images": [
+            "a701052_00.jpg",
+            "a701052_01.jpg",
+            "a701052_02.jpg",
+            "a701052_03.jpg",
+            "a701052_04.jpg",
+            "a701052_05.jpg",
+            "a701052_06.jpg",
+            "a701052_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Create a captivating animation that begins with a serene landscape of the Snowpeak Mountains. As the wind picks up, simulate the gentle movement of the towering pines, and gradually introduce swirling snowflakes to announce the approaching blizzard. Transition seamlessly to the exterior of a rustic mountain cabin, showcasing its wooden frame and vintage decorations. Use subtle lighting effects to emphasize the coziness inside, with the fire flickering in the stone fireplace. Convey a sense of warmth and anticipation as the characters make their way into the cabin, seeking refuge from the biting wind.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500395",
+        "images": [
+            "a500395_00.jpg",
+            "a500395_01.jpg",
+            "a500395_02.jpg",
+            "a500395_03.jpg",
+            "a500395_04.jpg",
+            "a500395_05.jpg",
+            "a500395_06.jpg",
+            "a500395_07.jpg",
+            "a500395_08.jpg",
+            "a500395_09.jpg",
+            "a500395_10.jpg",
+            "a500395_11.jpg",
+            "a500395_12.jpg",
+            "a500395_13.jpg",
+            "a500395_14.jpg",
+            "a500395_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is cinematic shot of a drone view of the carribean islands, sun shining  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701670",
+        "images": [
+            "a701670_00.jpg",
+            "a701670_01.jpg",
+            "a701670_02.jpg",
+            "a701670_03.jpg",
+            "a701670_04.jpg",
+            "a701670_05.jpg",
+            "a701670_06.jpg",
+            "a701670_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a woman asks her mom to bail her our of prison in torreon, mexico.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402096",
+        "images": [
+            "a402096_00.jpg",
+            "a402096_01.jpg",
+            "a402096_02.jpg",
+            "a402096_03.jpg",
+            "a402096_04.jpg",
+            "a402096_05.jpg",
+            "a402096_06.jpg",
+            "a402096_07.jpg",
+            "a402096_08.jpg",
+            "a402096_09.jpg",
+            "a402096_10.jpg",
+            "a402096_11.jpg",
+            "a402096_12.jpg",
+            "a402096_13.jpg",
+            "a402096_14.jpg",
+            "a402096_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is In the moonlit darkness of a forgotten town, whispers of a malevolent force echoed through the narrow streets.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701180",
+        "images": [
+            "a701180_00.jpg",
+            "a701180_01.jpg",
+            "a701180_02.jpg",
+            "a701180_03.jpg",
+            "a701180_04.jpg",
+            "a701180_05.jpg",
+            "a701180_06.jpg",
+            "a701180_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a pirate resembling Blackbeard, and observing an ancient map of the world  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701496",
+        "images": [
+            "a701496_00.jpg",
+            "a701496_01.jpg",
+            "a701496_02.jpg",
+            "a701496_03.jpg",
+            "a701496_04.jpg",
+            "a701496_05.jpg",
+            "a701496_06.jpg",
+            "a701496_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a painter with a wide brush brushes indigo fabric dye onto wet silk, causing the color to bleed and expand across the canvas  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500560",
+        "images": [
+            "a500560_00.jpg",
+            "a500560_01.jpg",
+            "a500560_02.jpg",
+            "a500560_03.jpg",
+            "a500560_04.jpg",
+            "a500560_05.jpg",
+            "a500560_06.jpg",
+            "a500560_07.jpg",
+            "a500560_08.jpg",
+            "a500560_09.jpg",
+            "a500560_10.jpg",
+            "a500560_11.jpg",
+            "a500560_12.jpg",
+            "a500560_13.jpg",
+            "a500560_14.jpg",
+            "a500560_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a girl is knitting a doll that looks like a music note, steadly sitting on a cozy chair  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a400721",
+        "images": [
+            "a400721_00.jpg",
+            "a400721_01.jpg",
+            "a400721_02.jpg",
+            "a400721_03.jpg",
+            "a400721_04.jpg",
+            "a400721_05.jpg",
+            "a400721_06.jpg",
+            "a400721_07.jpg",
+            "a400721_08.jpg",
+            "a400721_09.jpg",
+            "a400721_10.jpg",
+            "a400721_11.jpg",
+            "a400721_12.jpg",
+            "a400721_13.jpg",
+            "a400721_14.jpg",
+            "a400721_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Night sky, black sky, dark blue, slightly purple, bright star in the center, Disney style  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a400837",
+        "images": [
+            "a400837_00.jpg",
+            "a400837_01.jpg",
+            "a400837_02.jpg",
+            "a400837_03.jpg",
+            "a400837_04.jpg",
+            "a400837_05.jpg",
+            "a400837_06.jpg",
+            "a400837_07.jpg",
+            "a400837_08.jpg",
+            "a400837_09.jpg",
+            "a400837_10.jpg",
+            "a400837_11.jpg",
+            "a400837_12.jpg",
+            "a400837_13.jpg",
+            "a400837_14.jpg",
+            "a400837_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is carthage ,atlantis civilisation,genral hannibal barca, elephant, port of carthage,army,gold,diamont  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500531",
+        "images": [
+            "a500531_00.jpg",
+            "a500531_01.jpg",
+            "a500531_02.jpg",
+            "a500531_03.jpg",
+            "a500531_04.jpg",
+            "a500531_05.jpg",
+            "a500531_06.jpg",
+            "a500531_07.jpg",
+            "a500531_08.jpg",
+            "a500531_09.jpg",
+            "a500531_10.jpg",
+            "a500531_11.jpg",
+            "a500531_12.jpg",
+            "a500531_13.jpg",
+            "a500531_14.jpg",
+            "a500531_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Create a video of dopamine and acetylcholine acting on receptors simultaneously  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500539",
+        "images": [
+            "a500539_00.jpg",
+            "a500539_01.jpg",
+            "a500539_02.jpg",
+            "a500539_03.jpg",
+            "a500539_04.jpg",
+            "a500539_05.jpg",
+            "a500539_06.jpg",
+            "a500539_07.jpg",
+            "a500539_08.jpg",
+            "a500539_09.jpg",
+            "a500539_10.jpg",
+            "a500539_11.jpg",
+            "a500539_12.jpg",
+            "a500539_13.jpg",
+            "a500539_14.jpg",
+            "a500539_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is young beautiful wealthy woman with short blonde hair, standing with a glass of champagne in a huge dressing room with high ceilings of a townhouse, Art Nouveau interior, interior architect Alvar Aalto, bright cheerful photo  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500505",
+        "images": [
+            "a500505_00.jpg",
+            "a500505_01.jpg",
+            "a500505_02.jpg",
+            "a500505_03.jpg",
+            "a500505_04.jpg",
+            "a500505_05.jpg",
+            "a500505_06.jpg",
+            "a500505_07.jpg",
+            "a500505_08.jpg",
+            "a500505_09.jpg",
+            "a500505_10.jpg",
+            "a500505_11.jpg",
+            "a500505_12.jpg",
+            "a500505_13.jpg",
+            "a500505_14.jpg",
+            "a500505_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Scorpio King as ruler. The photo should be full of drama and excitement  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402924",
+        "images": [
+            "a402924_00.jpg",
+            "a402924_01.jpg",
+            "a402924_02.jpg",
+            "a402924_03.jpg",
+            "a402924_04.jpg",
+            "a402924_05.jpg",
+            "a402924_06.jpg",
+            "a402924_07.jpg",
+            "a402924_08.jpg",
+            "a402924_09.jpg",
+            "a402924_10.jpg",
+            "a402924_11.jpg",
+            "a402924_12.jpg",
+            "a402924_13.jpg",
+            "a402924_14.jpg",
+            "a402924_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is A man with blond hair and blue eyes stands in the middle of the universe with all these auras behind him  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401647",
+        "images": [
+            "a401647_00.jpg",
+            "a401647_01.jpg",
+            "a401647_02.jpg",
+            "a401647_03.jpg",
+            "a401647_04.jpg",
+            "a401647_05.jpg",
+            "a401647_06.jpg",
+            "a401647_07.jpg",
+            "a401647_08.jpg",
+            "a401647_09.jpg",
+            "a401647_10.jpg",
+            "a401647_11.jpg",
+            "a401647_12.jpg",
+            "a401647_13.jpg",
+            "a401647_14.jpg",
+            "a401647_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is granite and onyx figure turning to face the overhead grey clouds  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500917",
+        "images": [
+            "a500917_00.jpg",
+            "a500917_01.jpg",
+            "a500917_02.jpg",
+            "a500917_03.jpg",
+            "a500917_04.jpg",
+            "a500917_05.jpg",
+            "a500917_06.jpg",
+            "a500917_07.jpg",
+            "a500917_08.jpg",
+            "a500917_09.jpg",
+            "a500917_10.jpg",
+            "a500917_11.jpg",
+            "a500917_12.jpg",
+            "a500917_13.jpg",
+            "a500917_14.jpg",
+            "a500917_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Vlogger is fully armed and ready to ski, and the background music rises to a climax.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a400874",
+        "images": [
+            "a400874_00.jpg",
+            "a400874_01.jpg",
+            "a400874_02.jpg",
+            "a400874_03.jpg",
+            "a400874_04.jpg",
+            "a400874_05.jpg",
+            "a400874_06.jpg",
+            "a400874_07.jpg",
+            "a400874_08.jpg",
+            "a400874_09.jpg",
+            "a400874_10.jpg",
+            "a400874_11.jpg",
+            "a400874_12.jpg",
+            "a400874_13.jpg",
+            "a400874_14.jpg",
+            "a400874_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is mystical, woman, 25 years old, refined and sharp features, not bold but graceful features, slight facial bones, magical, mythical, light caramel hair, oval face, straight hair, symmetrical features, cartoon artistic, cartoon art style, art style, mystery, dark eyebrows, averted gaze, brown eyes, darkeyed, fantasy, dark theme, purple, classic, christmas, winter, december, lucia, red, red coloured, st lucia swedish celebration  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402616",
+        "images": [
+            "a402616_00.jpg",
+            "a402616_01.jpg",
+            "a402616_02.jpg",
+            "a402616_03.jpg",
+            "a402616_04.jpg",
+            "a402616_05.jpg",
+            "a402616_06.jpg",
+            "a402616_07.jpg",
+            "a402616_08.jpg",
+            "a402616_09.jpg",
+            "a402616_10.jpg",
+            "a402616_11.jpg",
+            "a402616_12.jpg",
+            "a402616_13.jpg",
+            "a402616_14.jpg",
+            "a402616_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is A clock rounding 1 min table clock white blue  color and white background  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401714",
+        "images": [
+            "a401714_00.jpg",
+            "a401714_01.jpg",
+            "a401714_02.jpg",
+            "a401714_03.jpg",
+            "a401714_04.jpg",
+            "a401714_05.jpg",
+            "a401714_06.jpg",
+            "a401714_07.jpg",
+            "a401714_08.jpg",
+            "a401714_09.jpg",
+            "a401714_10.jpg",
+            "a401714_11.jpg",
+            "a401714_12.jpg",
+            "a401714_13.jpg",
+            "a401714_14.jpg",
+            "a401714_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Make an animation of Jinx holding a gun  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402997",
+        "images": [
+            "a402997_00.jpg",
+            "a402997_01.jpg",
+            "a402997_02.jpg",
+            "a402997_03.jpg",
+            "a402997_04.jpg",
+            "a402997_05.jpg",
+            "a402997_06.jpg",
+            "a402997_07.jpg",
+            "a402997_08.jpg",
+            "a402997_09.jpg",
+            "a402997_10.jpg",
+            "a402997_11.jpg",
+            "a402997_12.jpg",
+            "a402997_13.jpg",
+            "a402997_14.jpg",
+            "a402997_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is generate a video of many wild Animals in on e frame in the forest  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701036",
+        "images": [
+            "a701036_00.jpg",
+            "a701036_01.jpg",
+            "a701036_02.jpg",
+            "a701036_03.jpg",
+            "a701036_04.jpg",
+            "a701036_05.jpg",
+            "a701036_06.jpg",
+            "a701036_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is cute anime kitten wearing a ladies dress and watching innocently  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701023",
+        "images": [
+            "a701023_00.jpg",
+            "a701023_01.jpg",
+            "a701023_02.jpg",
+            "a701023_03.jpg",
+            "a701023_04.jpg",
+            "a701023_05.jpg",
+            "a701023_06.jpg",
+            "a701023_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Beautiful single gold coin flipping in the air, pulsating gold energy, pitch black background, 4K, 8K ultra realism, flipping motion  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401116",
+        "images": [
+            "a401116_00.jpg",
+            "a401116_01.jpg",
+            "a401116_02.jpg",
+            "a401116_03.jpg",
+            "a401116_04.jpg",
+            "a401116_05.jpg",
+            "a401116_06.jpg",
+            "a401116_07.jpg",
+            "a401116_08.jpg",
+            "a401116_09.jpg",
+            "a401116_10.jpg",
+            "a401116_11.jpg",
+            "a401116_12.jpg",
+            "a401116_13.jpg",
+            "a401116_14.jpg",
+            "a401116_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Josh Kelly seated on the lava throne, Anne Hathaway and eated on the glass throne  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401562",
+        "images": [
+            "a401562_00.jpg",
+            "a401562_01.jpg",
+            "a401562_02.jpg",
+            "a401562_03.jpg",
+            "a401562_04.jpg",
+            "a401562_05.jpg",
+            "a401562_06.jpg",
+            "a401562_07.jpg",
+            "a401562_08.jpg",
+            "a401562_09.jpg",
+            "a401562_10.jpg",
+            "a401562_11.jpg",
+            "a401562_12.jpg",
+            "a401562_13.jpg",
+            "a401562_14.jpg",
+            "a401562_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is man asking Jesus Christ for help  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401438",
+        "images": [
+            "a401438_00.jpg",
+            "a401438_01.jpg",
+            "a401438_02.jpg",
+            "a401438_03.jpg",
+            "a401438_04.jpg",
+            "a401438_05.jpg",
+            "a401438_06.jpg",
+            "a401438_07.jpg",
+            "a401438_08.jpg",
+            "a401438_09.jpg",
+            "a401438_10.jpg",
+            "a401438_11.jpg",
+            "a401438_12.jpg",
+            "a401438_13.jpg",
+            "a401438_14.jpg",
+            "a401438_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is animate, both persons hair move, eyes wave,  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402584",
+        "images": [
+            "a402584_00.jpg",
+            "a402584_01.jpg",
+            "a402584_02.jpg",
+            "a402584_03.jpg",
+            "a402584_04.jpg",
+            "a402584_05.jpg",
+            "a402584_06.jpg",
+            "a402584_07.jpg",
+            "a402584_08.jpg",
+            "a402584_09.jpg",
+            "a402584_10.jpg",
+            "a402584_11.jpg",
+            "a402584_12.jpg",
+            "a402584_13.jpg",
+            "a402584_14.jpg",
+            "a402584_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is The recipient celebrating an achievement, with God applauding in the background.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701643",
+        "images": [
+            "a701643_00.jpg",
+            "a701643_01.jpg",
+            "a701643_02.jpg",
+            "a701643_03.jpg",
+            "a701643_04.jpg",
+            "a701643_05.jpg",
+            "a701643_06.jpg",
+            "a701643_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is low poly freddie gibbs, pixar quality, fighting abomidable snowman from classic movie and winning  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402079",
+        "images": [
+            "a402079_00.jpg",
+            "a402079_01.jpg",
+            "a402079_02.jpg",
+            "a402079_03.jpg",
+            "a402079_04.jpg",
+            "a402079_05.jpg",
+            "a402079_06.jpg",
+            "a402079_07.jpg",
+            "a402079_08.jpg",
+            "a402079_09.jpg",
+            "a402079_10.jpg",
+            "a402079_11.jpg",
+            "a402079_12.jpg",
+            "a402079_13.jpg",
+            "a402079_14.jpg",
+            "a402079_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is beyond time and space there is a construct that rotates  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402392",
+        "images": [
+            "a402392_00.jpg",
+            "a402392_01.jpg",
+            "a402392_02.jpg",
+            "a402392_03.jpg",
+            "a402392_04.jpg",
+            "a402392_05.jpg",
+            "a402392_06.jpg",
+            "a402392_07.jpg",
+            "a402392_08.jpg",
+            "a402392_09.jpg",
+            "a402392_10.jpg",
+            "a402392_11.jpg",
+            "a402392_12.jpg",
+            "a402392_13.jpg",
+            "a402392_14.jpg",
+            "a402392_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is 70s eastern european horror, Experiment with juxtapositions and unexpected transitions to create a disjointed narrative that leaves room for interpretation. Blur the boundaries between past and present, memory and imagination, inviting viewers to delve into the depths of the subconscious  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a700318",
+        "images": [
+            "a700318_00.jpg",
+            "a700318_01.jpg",
+            "a700318_02.jpg",
+            "a700318_03.jpg",
+            "a700318_04.jpg",
+            "a700318_05.jpg",
+            "a700318_06.jpg",
+            "a700318_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is A scary hooded figure walks in a dark room.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a402719",
+        "images": [
+            "a402719_00.jpg",
+            "a402719_01.jpg",
+            "a402719_02.jpg",
+            "a402719_03.jpg",
+            "a402719_04.jpg",
+            "a402719_05.jpg",
+            "a402719_06.jpg",
+            "a402719_07.jpg",
+            "a402719_08.jpg",
+            "a402719_09.jpg",
+            "a402719_10.jpg",
+            "a402719_11.jpg",
+            "a402719_12.jpg",
+            "a402719_13.jpg",
+            "a402719_14.jpg",
+            "a402719_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is resurrect yourself, resurrect yourself,  resurrect yourself, resurrect yourself,  resurrect yourself, resurrect yourself  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500266",
+        "images": [
+            "a500266_00.jpg",
+            "a500266_01.jpg",
+            "a500266_02.jpg",
+            "a500266_03.jpg",
+            "a500266_04.jpg",
+            "a500266_05.jpg",
+            "a500266_06.jpg",
+            "a500266_07.jpg",
+            "a500266_08.jpg",
+            "a500266_09.jpg",
+            "a500266_10.jpg",
+            "a500266_11.jpg",
+            "a500266_12.jpg",
+            "a500266_13.jpg",
+            "a500266_14.jpg",
+            "a500266_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a man standing  in the universe between couple of ways  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401457",
+        "images": [
+            "a401457_00.jpg",
+            "a401457_01.jpg",
+            "a401457_02.jpg",
+            "a401457_03.jpg",
+            "a401457_04.jpg",
+            "a401457_05.jpg",
+            "a401457_06.jpg",
+            "a401457_07.jpg",
+            "a401457_08.jpg",
+            "a401457_09.jpg",
+            "a401457_10.jpg",
+            "a401457_11.jpg",
+            "a401457_12.jpg",
+            "a401457_13.jpg",
+            "a401457_14.jpg",
+            "a401457_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is beaver ninja, Japanese cat, wood, Rdr  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701828",
+        "images": [
+            "a701828_00.jpg",
+            "a701828_01.jpg",
+            "a701828_02.jpg",
+            "a701828_03.jpg",
+            "a701828_04.jpg",
+            "a701828_05.jpg",
+            "a701828_06.jpg",
+            "a701828_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is drow Spy girl fighting against Kelemvor paladin, 4k, cinematics, dnd, zoom  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a700037",
+        "images": [
+            "a700037_00.jpg",
+            "a700037_01.jpg",
+            "a700037_02.jpg",
+            "a700037_03.jpg",
+            "a700037_04.jpg",
+            "a700037_05.jpg",
+            "a700037_06.jpg",
+            "a700037_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Flickering Light in an Empty Room. Briefly illuminate an empty room with a flickering light, suggesting an unseen presence or a mysterious event.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a701100",
+        "images": [
+            "a701100_00.jpg",
+            "a701100_01.jpg",
+            "a701100_02.jpg",
+            "a701100_03.jpg",
+            "a701100_04.jpg",
+            "a701100_05.jpg",
+            "a701100_06.jpg",
+            "a701100_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is the Sun suddenly blinks out of existence  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a401770",
+        "images": [
+            "a401770_00.jpg",
+            "a401770_01.jpg",
+            "a401770_02.jpg",
+            "a401770_03.jpg",
+            "a401770_04.jpg",
+            "a401770_05.jpg",
+            "a401770_06.jpg",
+            "a401770_07.jpg",
+            "a401770_08.jpg",
+            "a401770_09.jpg",
+            "a401770_10.jpg",
+            "a401770_11.jpg",
+            "a401770_12.jpg",
+            "a401770_13.jpg",
+            "a401770_14.jpg",
+            "a401770_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a cowboy playing guitar in a dark bar  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a700825",
+        "images": [
+            "a700825_00.jpg",
+            "a700825_01.jpg",
+            "a700825_02.jpg",
+            "a700825_03.jpg",
+            "a700825_04.jpg",
+            "a700825_05.jpg",
+            "a700825_06.jpg",
+            "a700825_07.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is A colourful drawing  of a picturesque sunrise paints the sky with warm shades of orange and pink. Tony the tomato is perched on a vine overlooking the garden, his eyes wide with wonder.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a400910",
+        "images": [
+            "a400910_00.jpg",
+            "a400910_01.jpg",
+            "a400910_02.jpg",
+            "a400910_03.jpg",
+            "a400910_04.jpg",
+            "a400910_05.jpg",
+            "a400910_06.jpg",
+            "a400910_07.jpg",
+            "a400910_08.jpg",
+            "a400910_09.jpg",
+            "a400910_10.jpg",
+            "a400910_11.jpg",
+            "a400910_12.jpg",
+            "a400910_13.jpg",
+            "a400910_14.jpg",
+            "a400910_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is The village transformed into a more compassionate and caring community.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    },
+    {
+        "id": "a500593",
+        "images": [
+            "a500593_00.jpg",
+            "a500593_01.jpg",
+            "a500593_02.jpg",
+            "a500593_03.jpg",
+            "a500593_04.jpg",
+            "a500593_05.jpg",
+            "a500593_06.jpg",
+            "a500593_07.jpg",
+            "a500593_08.jpg",
+            "a500593_09.jpg",
+            "a500593_10.jpg",
+            "a500593_11.jpg",
+            "a500593_12.jpg",
+            "a500593_13.jpg",
+            "a500593_14.jpg",
+            "a500593_15.jpg"
+        ],
+        "conversations": [
+            {
+                "from": "human",
+                "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is the entrance to a hobbit cove. The cove door is light brown. There are green plants, vines, flowers, and butterflies around the door.  ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
+            },
+            {
+                "from": "gpt",
+                "value": "visual quality: 1\n object consistency: 1\n dynamic degree: 3\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
+            }
+        ]
+    }
+]