Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization

TL;DR

This paper introduces SMEN, a framework that enhances weakly supervised temporal action localization by effectively capturing slow-motion action segments, addressing the challenge of detecting slow-paced actions in videos.

Contribution

The paper proposes a novel SMEN framework with a mining module and a localization module to improve sensitivity to slow-motion actions in WTAL models.

Findings

SMEN improves slow-motion action detection accuracy.

Framework is adaptable to existing WTAL networks.

Experimental results show high performance on benchmarks.

Abstract

Weakly supervised temporal action localization (WTAL) aims to localize actions in untrimmed videos with only weak supervision information (e.g. video-level labels). Most existing models handle all input videos with a fixed temporal scale. However, such models are not sensitive to actions whose pace of the movements is different from the ``normal" speed, especially slow-motion action instances, which complete the movements with a much slower speed than their counterparts with a normal speed. Here arises the slow-motion blurred issue: It is hard to explore salient slow-motion information from videos at ``normal" speed. In this paper, we propose a novel framework termed Slow Motion Enhanced Network (SMEN) to improve the ability of a WTAL network by compensating its sensitivity on slow-motion action segments. The proposed SMEN comprises a Mining module and a Localization module. The mining module generates mask to mine slow-motion-related features by utilizing the relationships between the normal motion and slow motion; while the localization module leverages the mined slow-motion features as complementary information to improve the temporal action localization results. Our proposed framework can be easily adapted by existing WTAL networks and enable them be more sensitive to slow-motion actions. Extensive experiments on three benchmarks are conducted, which demonstrate the high performance of our proposed framework.