Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos
This addresses the need for real-time human motion recognition in human-robot interaction, though it appears incremental as it builds on existing frameworks.
The paper tackles online action detection in videos by exploring temporal context and human movement dynamics using Temporal Recurrent Networks, achieving state-of-the-art results on the THUMOS'14 dataset.
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.