Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos

TL;DR

This paper advances online action detection in videos by leveraging temporal context and human movement dynamics, employing various architectures within the Temporal Recurrent Networks framework, and achieving state-of-the-art results on THUMOS'14.

Contribution

It introduces an approach that effectively combines features to improve real-time action detection using temporal context and movement dynamics within the TRN framework.

Findings

Significant improvement over baseline methods

Achieved state-of-the-art results on THUMOS'14

Demonstrated effectiveness of feature combination strategies

Abstract

Nowadays, the interaction between humans and robots is constantly expanding, requiring more and more human motion recognition applications to operate in real time. However, most works on temporal action detection and recognition perform these tasks in offline manner, i.e. temporally segmented videos are classified as a whole. In this paper, based on the recently proposed framework of Temporal Recurrent Networks, we explore how temporal context and human movement dynamics can be effectively employed for online action detection. Our approach uses various state-of-the-art architectures and appropriately combines the extracted features in order to improve action detection. We evaluate our method on a challenging but widely used dataset for temporal action localization, THUMOS'14. Our experiments show significant improvement over the baseline method, achieving state-of-the art results on THUMOS'14.