VideoCLIP: Contrastive Pre-Training for Zero-Shot Video-Text Understanding (arxiv.org) 1 points by LuisMondragon 4y ago ↗ HN
[–] sharemywin 4y ago ↗ Not sure if this is the same thing?https://github.com/openai/CLIP [–] LuisMondragon 4y ago ↗ Not the same. CLIP is trained with pairs of images and texts, whereas VideoCLIP uses pairs of videos and texts.
[–] LuisMondragon 4y ago ↗ Not the same. CLIP is trained with pairs of images and texts, whereas VideoCLIP uses pairs of videos and texts.
2 comments
[ 2.8 ms ] story [ 17.5 ms ] threadhttps://github.com/openai/CLIP