microsoft / xclip-base-patch16-zero-shot
Other195M270.5K35Updated Sep 12, 2023
Downloads
270.5K
Likes
35
Last updated
Sep 12, 2023
License
mit
X-CLIP model (base-sized, patch resolution of 16) trained on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository.
Tasks & library
- video classification
- transformers
Tags
- transformers
- pytorch
- xclip
- feature-extraction
- vision
- video-classification
Technical specifications
Parameters195M
Librarytransformers
Languagesen
Licensemit