Spatial enhancement and temporal constraint for weakly supervised action localization

Xiaolei Qin, Yongxin Ge*, Hui Yu, Feiyu Chen, Dan Yang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Weakly supervised temporal action localization (WSTAL) is a practical but challenging issue in video understanding. However, most existing methods have to activate background snippets or deactivate action snippets in cases of no boundary annotations, which inevitably affects the localization of action instances. In this letter, we propose a spatial enhancement and temporal constraint (SETC) model to address this problem from three aspects. Specifically, we first propose a spatial enhancement module to enhance the discrimination of the extracted features. Then we leverage the instance sparse constraint to restrain the drastic fluctuation class activation sequence (CAS). Finally, we use the confidence connectivity enhancement to connect the snippets that are broken up by mistake. Experiments on THUMOS'14 and ActivityNet datasets validate the efficacy of SETC against existing state-of-the-artWSTAL algorithms.

Original languageEnglish
Pages (from-to)1520-1524
Number of pages5
JournalIEEE Signal Processing Letters
Volume27
DOIs
Publication statusPublished - 27 Aug 2020

Keywords

  • Confidence connectivity enhancement
  • Instance sparse constraint
  • Spatial enhancement
  • Weakly supervised temporal action localization

Fingerprint

Dive into the research topics of 'Spatial enhancement and temporal constraint for weakly supervised action localization'. Together they form a unique fingerprint.

Cite this