Task
Video Classification
S
StreamFormer/streamformer-timesformer
Video Classification·StreamFormer· 35· 4
StreamFormer backbone model pre-trained on Global-, Temporal- and Spatial- granularities. It was introduced in the paper Learning Streaming Video Representation via Multitask Training and first released in this repository.
# pull & run locally
pip install mlforge-sdk && mlforge pull StreamFormer/streamformer-timesformer
pip install mlforge-sdk && mlforge pull StreamFormer/streamformer-timesformer
Model details
Provider
StreamFormer
Parameters
130.1M
Size
496 MB
License
cc-by-nc-4.0
Downloads
35
Likes
4
Paper
arXiv:2504.20041
Updated
2025-08-10
About StreamFormer/streamformer-timesformer
StreamFormer backbone model pre-trained on Global-, Temporal- and Spatial- granularities. It was introduced in the paper Learning Streaming Video Representation via Multitask Training and first released in this repository.