File size: 21,345 Bytes
b9d3de1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
[
    {
        "id": "r003679",
        "images": [
            "r003679_00.jpg",
            "r003679_01.jpg",
            "r003679_02.jpg",
            "r003679_03.jpg",
            "r003679_04.jpg",
            "r003679_05.jpg",
            "r003679_06.jpg",
            "r003679_07.jpg",
            "r003679_08.jpg",
            "r003679_09.jpg",
            "r003679_10.jpg",
            "r003679_11.jpg",
            "r003679_12.jpg",
            "r003679_13.jpg",
            "r003679_14.jpg",
            "r003679_15.jpg",
            "r003679_16.jpg",
            "r003679_17.jpg",
            "r003679_18.jpg",
            "r003679_19.jpg",
            "r003679_20.jpg",
            "r003679_21.jpg",
            "r003679_22.jpg",
            "r003679_23.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 dog rolls over and falls off couch,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r100916",
        "images": [
            "r100916_00.jpg",
            "r100916_01.jpg",
            "r100916_02.jpg",
            "r100916_03.jpg",
            "r100916_04.jpg",
            "r100916_05.jpg",
            "r100916_06.jpg",
            "r100916_07.jpg",
            "r100916_08.jpg",
            "r100916_09.jpg",
            "r100916_10.jpg",
            "r100916_11.jpg",
            "r100916_12.jpg",
            "r100916_13.jpg",
            "r100916_14.jpg",
            "r100916_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 young man is standing in front of a glacier with mountains 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: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r004061",
        "images": [
            "r004061_00.jpg",
            "r004061_01.jpg",
            "r004061_02.jpg",
            "r004061_03.jpg",
            "r004061_04.jpg",
            "r004061_05.jpg",
            "r004061_06.jpg",
            "r004061_07.jpg",
            "r004061_08.jpg",
            "r004061_09.jpg",
            "r004061_10.jpg",
            "r004061_11.jpg",
            "r004061_12.jpg",
            "r004061_13.jpg",
            "r004061_14.jpg",
            "r004061_15.jpg",
            "r004061_16.jpg",
            "r004061_17.jpg",
            "r004061_18.jpg",
            "r004061_19.jpg",
            "r004061_20.jpg",
            "r004061_21.jpg",
            "r004061_22.jpg",
            "r004061_23.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 wearing a striped blanket over his backpack runs behind two other men.,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r000228",
        "images": [
            "r000228_00.jpg",
            "r000228_01.jpg",
            "r000228_02.jpg",
            "r000228_03.jpg",
            "r000228_04.jpg",
            "r000228_05.jpg",
            "r000228_06.jpg",
            "r000228_07.jpg",
            "r000228_08.jpg",
            "r000228_09.jpg",
            "r000228_10.jpg",
            "r000228_11.jpg",
            "r000228_12.jpg",
            "r000228_13.jpg",
            "r000228_14.jpg",
            "r000228_15.jpg",
            "r000228_16.jpg",
            "r000228_17.jpg",
            "r000228_18.jpg",
            "r000228_19.jpg",
            "r000228_20.jpg",
            "r000228_21.jpg",
            "r000228_22.jpg",
            "r000228_23.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 two people get into sports car,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r100887",
        "images": [
            "r100887_00.jpg",
            "r100887_01.jpg",
            "r100887_02.jpg",
            "r100887_03.jpg",
            "r100887_04.jpg",
            "r100887_05.jpg",
            "r100887_06.jpg",
            "r100887_07.jpg",
            "r100887_08.jpg",
            "r100887_09.jpg",
            "r100887_10.jpg",
            "r100887_11.jpg",
            "r100887_12.jpg",
            "r100887_13.jpg",
            "r100887_14.jpg",
            "r100887_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 person using a spatula to spread something on a pan.,\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: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r104340",
        "images": [
            "r104340_00.jpg",
            "r104340_01.jpg",
            "r104340_02.jpg",
            "r104340_03.jpg",
            "r104340_04.jpg",
            "r104340_05.jpg",
            "r104340_06.jpg",
            "r104340_07.jpg",
            "r104340_08.jpg",
            "r104340_09.jpg",
            "r104340_10.jpg",
            "r104340_11.jpg",
            "r104340_12.jpg",
            "r104340_13.jpg",
            "r104340_14.jpg",
            "r104340_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 bartender is making an alcoholic drink by pouring a clear liquid into a glass with ice cubes.,\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: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r001599",
        "images": [
            "r001599_00.jpg",
            "r001599_01.jpg",
            "r001599_02.jpg",
            "r001599_03.jpg",
            "r001599_04.jpg",
            "r001599_05.jpg",
            "r001599_06.jpg",
            "r001599_07.jpg",
            "r001599_08.jpg",
            "r001599_09.jpg",
            "r001599_10.jpg",
            "r001599_11.jpg",
            "r001599_12.jpg",
            "r001599_13.jpg",
            "r001599_14.jpg",
            "r001599_15.jpg",
            "r001599_16.jpg",
            "r001599_17.jpg",
            "r001599_18.jpg",
            "r001599_19.jpg",
            "r001599_20.jpg",
            "r001599_21.jpg",
            "r001599_22.jpg",
            "r001599_23.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 uses a camera,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r101298",
        "images": [
            "r101298_00.jpg",
            "r101298_01.jpg",
            "r101298_02.jpg",
            "r101298_03.jpg",
            "r101298_04.jpg",
            "r101298_05.jpg",
            "r101298_06.jpg",
            "r101298_07.jpg",
            "r101298_08.jpg",
            "r101298_09.jpg",
            "r101298_10.jpg",
            "r101298_11.jpg",
            "r101298_12.jpg",
            "r101298_13.jpg",
            "r101298_14.jpg",
            "r101298_15.jpg",
            "r101298_16.jpg",
            "r101298_17.jpg",
            "r101298_18.jpg",
            "r101298_19.jpg",
            "r101298_20.jpg",
            "r101298_21.jpg",
            "r101298_22.jpg",
            "r101298_23.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 baseball game is being played in a stadium with a large crowd of people watching.,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r000688",
        "images": [
            "r000688_00.jpg",
            "r000688_01.jpg",
            "r000688_02.jpg",
            "r000688_03.jpg",
            "r000688_04.jpg",
            "r000688_05.jpg",
            "r000688_06.jpg",
            "r000688_07.jpg",
            "r000688_08.jpg",
            "r000688_09.jpg",
            "r000688_10.jpg",
            "r000688_11.jpg",
            "r000688_12.jpg",
            "r000688_13.jpg",
            "r000688_14.jpg",
            "r000688_15.jpg",
            "r000688_16.jpg",
            "r000688_17.jpg",
            "r000688_18.jpg",
            "r000688_19.jpg",
            "r000688_20.jpg",
            "r000688_21.jpg",
            "r000688_22.jpg",
            "r000688_23.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 child furthest to the right dips her hand into the bowl shared by the other children.,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    },
    {
        "id": "r104350",
        "images": [
            "r104350_00.jpg",
            "r104350_01.jpg",
            "r104350_02.jpg",
            "r104350_03.jpg",
            "r104350_04.jpg",
            "r104350_05.jpg",
            "r104350_06.jpg",
            "r104350_07.jpg",
            "r104350_08.jpg",
            "r104350_09.jpg",
            "r104350_10.jpg",
            "r104350_11.jpg",
            "r104350_12.jpg",
            "r104350_13.jpg",
            "r104350_14.jpg",
            "r104350_15.jpg",
            "r104350_16.jpg",
            "r104350_17.jpg",
            "r104350_18.jpg",
            "r104350_19.jpg",
            "r104350_20.jpg",
            "r104350_21.jpg",
            "r104350_22.jpg",
            "r104350_23.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 young man is talking to a young woman in a room with books on the shelves.,\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> <image> <image> <image> <image> <image> <image> <image> <image> \n"
            },
            {
                "from": "gpt",
                "value": "visual quality: 3\n object consistency: 3\n dynamic degree: 3\n motion smoothness: 3\n text-to-video alignment: 3\n factual consistency: 3\n overall score: 3\n"
            }
        ]
    }
]