SF-Net: Single-Frame Supervision for Temporal Action Localization
收藏DataCite Commons2025-01-02 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/206dda56-2c3e-411d-818b-727e82c8aa8f
下载链接
链接失效反馈官方服务：
资源简介：
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.
提供机构：
TIB
创建时间：
2025-01-02
