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
16 by og_kalu | 3 comments on Hacker News.


Comments

Popular posts from this blog

New top story on Hacker News: Show HN: Zipy.ai - Like Sentry + Hotjar, but with less noise

Seattle Is Socialism’s Laboratory, and It’s Not Pretty

Scallops row warnings 'fell on deaf ears', say UK fishermen, after French 'hurl rocks and smoke bombs' at boats