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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Jing, Zhu, Anqi, Lin, Jingyu, Ke, Qiuhong, Chen, Cunjian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916531806404608
author Xu, Jing
Zhu, Anqi
Lin, Jingyu
Ke, Qiuhong
Chen, Cunjian
author_facet Xu, Jing
Zhu, Anqi
Lin, Jingyu
Ke, Qiuhong
Chen, Cunjian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20633
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection
Xu, Jing
Zhu, Anqi
Lin, Jingyu
Ke, Qiuhong
Chen, Cunjian
Computer Vision and Pattern Recognition
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.
title Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.20633