Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition

TL;DR

This paper introduces a joint learning framework that leverages skeleton data to simultaneously improve interacted object localization and human action recognition by mutually assisting each task, utilizing temporal consistency constraints.

Contribution

The proposed method is the first to jointly model interacted object localization and human action recognition based on skeleton data, with mutual assistance and temporal constraints.

Findings

Achieves state-of-the-art or competitive results on multiple datasets.

Effectively localizes interacted objects without ground-truth labels.

Demonstrates the benefit of joint learning for action recognition.

Abstract

Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the action of persons. In this paper, we propose a joint learning framework for mutually assisted "interacted object localization" and "human action recognition" based on skeleton data. The two tasks are serialized together and collaborate to promote each other, where preliminary action type derived from skeleton alone helps improve interacted object localization, which in turn provides valuable cues for the final human action recognition. Besides, we explore the temporal consistency of interacted object as constraint to better localize the interacted object with the absence of ground-truth labels. Extensive experiments on the datasets of SYSU-3D, NTU60 RGB+D, Northwestern-UCLA and UAV-Human show that our method achieves the best or competitive performance with the state-of-the-art methods for human action recognition. Visualization results show that our method can also provide reasonable interacted object localization results.