CLIP-guided Prototype Modulating for Few-shot Action Recognition

Few-shot action recognition is a promising direction to alleviate the data labeling problem, which aims to identify unseen classes with a few labeled videos.

Data and Resources

Cite this as

Xiang Wang, Shiwei Zhang, Jun Cen, Changxin Gao, Yingya Zhang, Deli Zhao, Nong Sang (2024). Dataset: CLIP-guided Prototype Modulating for Few-shot Action Recognition. https://doi.org/10.57702/kjqerdn8

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Xiang Wang
More Authors
Shiwei Zhang
Jun Cen
Changxin Gao
Yingya Zhang
Deli Zhao
Nong Sang
Homepage https://github.com/alibaba-mmai-research/CLIP-FSAR