New top story on Hacker News: Vid2Seq: A pretrained visual language model for describing multi-event videos

Vid2Seq: A pretrained visual language model for describing multi-event videos
7 by og_kalu | 2 comments on Hacker News.


March 18, 2023 at 02:24AM og_kalu 7 https://ift.tt/41IwJ78 Vid2Seq: A pretrained visual language model for describing multi-event videos 2 https://ift.tt/FQMf1bm