Grounded Visual Generation
539
16.3
Microsoft Research321 тыс
Следующее
15.09.21 – 1 1801:23:19Популярные
96 дней – 1 2725:28
Опубликовано 15 сентября 2021, 18:44
Multi-modal data provides an exciting opportunity to train grounded generative models that synthesize images consistent with real world phenomena. In this talk, I will share several of our recent efforts towards creating grounded visual generation models: (1) introducing user attention grounding for text-to-image synthesis, (2) improving text-to-image generation results with stronger language grounding, and (3) taking steps towards creating spatially grounded world models for embodied vision-and-language tasks.
Speaker: Jing Yu Koh, Google
MSR Deep Learning team: microsoft.com/en-us/research/g...
Speaker: Jing Yu Koh, Google
MSR Deep Learning team: microsoft.com/en-us/research/g...
Свежие видео
4 дня – 2 9000:21
6 дней – 45 1410:29
10 дней – 810:58
13 дней – 2 3067:44
97 дней – 14 908 4830:36Случайные видео
163 дня – 127 5528:17
244 дня – 19229:45
357 дней – 6900:32
02.06.22 – 1 717 53415:15
26.02.13 – 78 75430:55
11 дней – 45617:34
18 часов – 26 8848:11
3 дня – 5 2320:08
3 дня – 519 9170:58
10 дней – 5061:25
12 дней – 2792:45
13 дней – 980:47
14 дней – 2 819 07514:45
5 часов – 517:49