Tightly Connecting Vision and Language
1 124
12.1
Microsoft Research333 тыс
Следующее
15.09.21 – 1 2321:00:42Популярные
188 дней – 10 00726:38
328 дней – 1 57053:47Опубликовано 15 сентября 2021, 18:52
Remarkable progress has been made at the intersection of vision and language. While showing great promise, current vision and language models may only weakly "connect" the two modalities and often fail in the wild. In this talk, I will present our recent efforts aiming to bridge this gap along two dimensions: informativeness and controllability. In particular, I will describe how we can leverage large-scale datasets, including our recently-released CC12M and Localized Narratives, to benefit existing vision-and-language tasks as well as to enable new applications.
Speaker: Soravit (Beer) Changpinyo, Google
MSR Deep Learning team: microsoft.com/en-us/research/g...
Speaker: Soravit (Beer) Changpinyo, Google
MSR Deep Learning team: microsoft.com/en-us/research/g...
Свежие видео
6 дней – 79 6536:39
9 дней – 710:48
10 дней – 3621:00
14 дней – 2003:01
17 дней – 1 4360:15
20 дней – 951:28Случайные видео
139 дней – 106 9234:52
18.08.23 – 55 6760:56
26.06.23 – 499 3972:33
21.03.23 – 37 2326:00
14.01.22 – 3 2500:31
14.11.20 – 188 9361:18
11 часов – 6147:41
1 день – 2 2935:10
1 день – 30 0585:38
3 дня – 12 99118:09
9 дней – 1 38312:52
14 дней – 4201:59
15 дней – 5 8072:58
1 день – 1 6105:01