SF-Net: Single-Frame Supervision for Temporal Action Localization

This paper proposes a method for temporal action localization using single-frame supervision. The authors use a unified system called SF-Net to predict actionness scores and mine pseudo action and background frames.

Data and Resources

Cite this as

Fan Ma, Linchao Zhu, Yi Yang, Shengxin Zha, Gourab Kundu, Matt Feiszli, Zheng Shou (2025). Dataset: SF-Net: Single-Frame Supervision for Temporal Action Localization. https://doi.org/10.57702/65l6es0b

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2003.06845
Author Fan Ma
More Authors
Linchao Zhu
Yi Yang
Shengxin Zha
Gourab Kundu
Matt Feiszli
Zheng Shou
Homepage https://github.com/Flowerfan/SF-Net