Hugging Face's logo

Datasets:
hexuan21
/
VideoScore_legacy

License:
Dataset card Data Studio Files
xet
Community
hexuan21 commited on
Commit
7cc189b
·
verified ·
1 Parent(s): 047afe9

upload subset_20k/test_100 's json, videos and frames

Browse files
Files changed (1) hide show
  1. data/subset_20k/test_100/data_static.json +157 -0
data/subset_20k/test_100/data_static.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "d500946",
4
+ "images": [
5
+ "d500946_00.jpg",
6
+ "d500946_01.jpg",
7
+ "d500946_02.jpg",
8
+ "d500946_03.jpg",
9
+ "d500946_04.jpg",
10
+ "d500946_05.jpg",
11
+ "d500946_06.jpg",
12
+ "d500946_07.jpg",
13
+ "d500946_08.jpg",
14
+ "d500946_09.jpg",
15
+ "d500946_10.jpg",
16
+ "d500946_11.jpg",
17
+ "d500946_12.jpg",
18
+ "d500946_13.jpg",
19
+ "d500946_14.jpg",
20
+ "d500946_15.jpg"
21
+ ],
22
+ "conversations": [
23
+ {
24
+ "from": "human",
25
+ "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 video of children sad because of their sneakers ,\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"
26
+ },
27
+ {
28
+ "from": "gpt",
29
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
30
+ }
31
+ ]
32
+ },
33
+ {
34
+ "id": "d500947",
35
+ "images": [
36
+ "d500947_00.jpg",
37
+ "d500947_01.jpg",
38
+ "d500947_02.jpg",
39
+ "d500947_03.jpg",
40
+ "d500947_04.jpg",
41
+ "d500947_05.jpg",
42
+ "d500947_06.jpg",
43
+ "d500947_07.jpg",
44
+ "d500947_08.jpg",
45
+ "d500947_09.jpg",
46
+ "d500947_10.jpg",
47
+ "d500947_11.jpg",
48
+ "d500947_12.jpg",
49
+ "d500947_13.jpg",
50
+ "d500947_14.jpg",
51
+ "d500947_15.jpg"
52
+ ],
53
+ "conversations": [
54
+ {
55
+ "from": "human",
56
+ "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 8k, man with fearful expression horror, exploring the dark corridors of the house ,\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"
57
+ },
58
+ {
59
+ "from": "gpt",
60
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
61
+ }
62
+ ]
63
+ },
64
+ {
65
+ "id": "d500948",
66
+ "images": [
67
+ "d500948_00.jpg",
68
+ "d500948_01.jpg",
69
+ "d500948_02.jpg",
70
+ "d500948_03.jpg",
71
+ "d500948_04.jpg",
72
+ "d500948_05.jpg",
73
+ "d500948_06.jpg",
74
+ "d500948_07.jpg",
75
+ "d500948_08.jpg",
76
+ "d500948_09.jpg",
77
+ "d500948_10.jpg",
78
+ "d500948_11.jpg",
79
+ "d500948_12.jpg",
80
+ "d500948_13.jpg",
81
+ "d500948_14.jpg",
82
+ "d500948_15.jpg"
83
+ ],
84
+ "conversations": [
85
+ {
86
+ "from": "human",
87
+ "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 tentacles growing from television screens 4k ar 16:9 ,\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"
88
+ },
89
+ {
90
+ "from": "gpt",
91
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
92
+ }
93
+ ]
94
+ },
95
+ {
96
+ "id": "d500949",
97
+ "images": [
98
+ "d500949_00.jpg",
99
+ "d500949_01.jpg",
100
+ "d500949_02.jpg",
101
+ "d500949_03.jpg",
102
+ "d500949_04.jpg",
103
+ "d500949_05.jpg",
104
+ "d500949_06.jpg",
105
+ "d500949_07.jpg",
106
+ "d500949_08.jpg",
107
+ "d500949_09.jpg",
108
+ "d500949_10.jpg",
109
+ "d500949_11.jpg",
110
+ "d500949_12.jpg",
111
+ "d500949_13.jpg",
112
+ "d500949_14.jpg",
113
+ "d500949_15.jpg"
114
+ ],
115
+ "conversations": [
116
+ {
117
+ "from": "human",
118
+ "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 cat, subtle movement of head, subtle movement of mouth, fur moving in the air, eyes blinking ,\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"
119
+ },
120
+ {
121
+ "from": "gpt",
122
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
123
+ }
124
+ ]
125
+ },
126
+ {
127
+ "id": "d500950",
128
+ "images": [
129
+ "d500950_00.jpg",
130
+ "d500950_01.jpg",
131
+ "d500950_02.jpg",
132
+ "d500950_03.jpg",
133
+ "d500950_04.jpg",
134
+ "d500950_05.jpg",
135
+ "d500950_06.jpg",
136
+ "d500950_07.jpg",
137
+ "d500950_08.jpg",
138
+ "d500950_09.jpg",
139
+ "d500950_10.jpg",
140
+ "d500950_11.jpg",
141
+ "d500950_12.jpg",
142
+ "d500950_13.jpg",
143
+ "d500950_14.jpg",
144
+ "d500950_15.jpg"
145
+ ],
146
+ "conversations": [
147
+ {
148
+ "from": "human",
149
+ "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 giant hurricanes sweeping through a village ,\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"
150
+ },
151
+ {
152
+ "from": "gpt",
153
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
154
+ }
155
+ ]
156
+ }
157
+ ]