facebookresearch/TimeSformer
TimeSformer is a transformer-based model for video classification using space-time attention that achieves state-of-the-art results on action recognition benchmarks.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of the TimeSformer model for video understanding. The model uses a transformer architecture with space-time attention to process video sequences, treating each frame as a separate patch and attending across both spatial and temporal dimensions. Pretrained models are provided for Kinetics-400, Kinetics-600, Something-Something-V2, and HowTo100M datasets.
Frequently asked
- What is facebookresearch/TimeSformer?
- TimeSformer is a transformer-based model for video classification using space-time attention that achieves state-of-the-art results on action recognition benchmarks.
- Is TimeSformer open source?
- Yes — facebookresearch/TimeSformer is an open-source project tracked on heatdrop.
- What language is TimeSformer written in?
- facebookresearch/TimeSformer is primarily written in Python.
- How popular is TimeSformer?
- facebookresearch/TimeSformer has 1.9k stars on GitHub.
- Where can I find TimeSformer?
- facebookresearch/TimeSformer is on GitHub at https://github.com/facebookresearch/TimeSformer.