Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection

TL;DR

This paper introduces Skeleton-OOD, an end-to-end skeleton-based model designed to improve out-of-distribution human action detection accuracy, outperforming existing methods on multiple large-scale datasets.

Contribution

The paper presents a novel end-to-end skeleton-based model for OOD human action detection, addressing limitations of prior RGB-based and post-hoc methods.

Findings

Skeleton-OOD outperforms state-of-the-art methods on NTU-RGB+D 60, NTU-RGB+D 120, and Kinetics-400 datasets.

Classic OOD detection techniques are effective in skeleton-based action recognition.

The approach ensures high accuracy in in-distribution action recognition while effectively rejecting OOD samples.

Abstract

Human action recognition is crucial in computer vision systems. However, in real-world scenarios, human actions often fall outside the distribution of training data, requiring a model to both recognize in-distribution (ID) actions and reject out-of-distribution (OOD) ones. Despite its importance, there has been limited research on OOD detection in human actions. Existing works on OOD detection mainly focus on image data with RGB structure, and many methods are post-hoc in nature. While these methods are convenient and computationally efficient, they often lack sufficient accuracy, fail to consider the exposure of OOD samples, and ignore the application in skeleton structure data. To address these challenges, we propose a novel end-to-end skeleton-based model called Skeleton-OOD, which is committed to improving the effectiveness of OOD tasks while ensuring the accuracy of ID recognition. Through extensive experiments conducted on NTU-RGB+D 60, NTU-RGB+D 120, and Kinetics-400 datasets, Skeleton-OOD demonstrates the superior performance of our proposed approach compared to state-of-the-art methods. Our findings underscore the effectiveness of classic OOD detection techniques in the context of skeleton-based action recognition tasks, offering promising avenues for future research in this field. Code is available at https://github.com/YilliaJing/Skeleton-OOD.git.