Novel Image Captioning
1 085
12.1
Microsoft Research335 тыс
Следующее
15.09.20 – 1 3121:05:15Популярные
02.11.23 – 5041:26:11
14.02.23 – 2 0801:23:27Опубликовано 11 сентября 2020, 20:19
When does a machine “understand” an image? One definition is when it can generate a novel caption that summarizes the salient content within an image. This content may include objects that are present, their attributes, actions, or their relations with each other. Determining the salient content requires not only knowing the contents of an image, but also deducing which aspects of the scene may be interesting or novel through commonsense knowledge. This video demonstrates the quality of the latest image captioning model (after) compared with the old model (before).
Свежие видео
2 дня – 26 61517:42
7 дней – 8 4200:33
9 дней – 6 1729:19
10 дней – 1 1335:36Случайные видео
43 дня – 782 8036:40
326 дней – 2 0690:29
08.12.23 – 16 11216:23
05.09.23 – 4 2091:44
12.06.21 – 229 2497:55
27.01.15 – 43 76726:49
3 дня – 684:07
5 дней – 2523:58
9 дней – 9 8620:18
11 дней – 432:46
12 дней – 10 7341:07
17 дней – 7551:08
2 дня – 23630:45