Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yifei, Peng, Kunyu, Roitberg, Alina, Schneider, David, Zhang, Jiaming, Zheng, Junwei, Chen, Yufan, Liu, Ruiping, Yang, Kailun, Stiefelhagen, Rainer
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915244248399872
author Chen, Yifei
Peng, Kunyu
Roitberg, Alina
Schneider, David
Zhang, Jiaming
Zheng, Junwei
Chen, Yufan
Liu, Ruiping
Yang, Kailun
Stiefelhagen, Rainer
author_facet Chen, Yifei
Peng, Kunyu
Roitberg, Alina
Schneider, David
Zhang, Jiaming
Zheng, Junwei
Chen, Yufan
Liu, Ruiping
Yang, Kailun
Stiefelhagen, Rainer
contents To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods. In this work, we propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. First, we pre-train the model on occluded skeleton sequences. Then, we introduce a cluster-agnostic KNN imputer that performs semantic grouping using k-means clustering on sequence embeddings. It imputes missing skeleton data by applying K-Nearest Neighbors in the latent space, leveraging nearby sample representations to restore occluded joints. This imputation generates more complete skeleton sequences, which significantly benefits downstream self-supervised models. To further enhance learning, the OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training. Our method achieves state-of-the-art performance on the occluded versions of the NTU-60 and NTU-120 datasets, demonstrating its robustness and effectiveness under challenging conditions. Code is available at https://github.com/cyfml/OPSTL.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12029
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
Chen, Yifei
Peng, Kunyu
Roitberg, Alina
Schneider, David
Zhang, Jiaming
Zheng, Junwei
Chen, Yufan
Liu, Ruiping
Yang, Kailun
Stiefelhagen, Rainer
Computer Vision and Pattern Recognition
Multimedia
Robotics
Image and Video Processing
To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods. In this work, we propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. First, we pre-train the model on occluded skeleton sequences. Then, we introduce a cluster-agnostic KNN imputer that performs semantic grouping using k-means clustering on sequence embeddings. It imputes missing skeleton data by applying K-Nearest Neighbors in the latent space, leveraging nearby sample representations to restore occluded joints. This imputation generates more complete skeleton sequences, which significantly benefits downstream self-supervised models. To further enhance learning, the OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training. Our method achieves state-of-the-art performance on the occluded versions of the NTU-60 and NTU-120 datasets, demonstrating its robustness and effectiveness under challenging conditions. Code is available at https://github.com/cyfml/OPSTL.
title Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
topic Computer Vision and Pattern Recognition
Multimedia
Robotics
Image and Video Processing
url https://arxiv.org/abs/2309.12029