MMLForge Search models, datasets, tasks… Start free
Home › Models › Video Classification › microsoft/xclip-base-patch32
X

microsoft/xclip-base-patch32

Video Classification·microsoft· 73.8K· 114
transformers mit Video Classification 196.6M params arxiv:2208.02816license:mitregion:us

X-CLIP model (base-sized, patch resolution of 32) trained fully-supervised 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.

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull microsoft/xclip-base-patch32

Model details

Task
Video Classification
Provider
microsoft
Framework
transformers
Parameters
196.6M
Size
1.5 GB
License
mit
Downloads
73.8K
Likes
114
Paper
arXiv:2208.02816
Updated
2024-02-04

About microsoft/xclip-base-patch32

X-CLIP model (base-sized, patch resolution of 32) trained fully-supervised 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.

Related Video Classification

V MCG-NJU/videomae-base Video Classification ·94.2M params 204.0K 55 🤗 HF V facebook/vjepa2-vitl-fpc64-256 Video Classification ·326.0M params 174.1K 203 🤗 HF V facebook/vjepa2-vith-fpc64-256 Video Classification ·653.9M params 149.9K 20 🤗 HF V facebook/vjepa2-vitg-fpc64-256 Video Classification ·1.0B params 141.6K 56 🤗 HF V Nikeytas/videomae-crime-detector-maxdata-v1 Video Classification ·86.2M params 54.7K 🤗 HF V MCG-NJU/videomae-base-finetuned-kinetics Video Classification ·86.5M params 38.4K 50 🤗 HF

Browse all Video Classification models →