paper-with-me

홈 › Papers

Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning

2026-02-26 · Taishu Arashima, Hiroshi Kera, Kazuhiko Kawamoto arxiv

Human trajectory prediction plays a crucial role in applications such as autonomous navigation and video surveillance. While recent works have explored the integration of human skeleton sequences to complement trajectory information, skeleton data in real-world environments often suffer from missing joints caused by occlusions. These disturbances significantly degrade prediction accuracy, indicating the need for more robust skeleton representations. We propose a robust trajectory prediction method that incorporates a self-supervised skeleton representation model pretrained with masked autoencoding. Experimental results in occlusion-prone scenarios show that our method improves robustness to missing skeletal data without sacrificing prediction accuracy, and consistently outperforms baseline models in clean-to-moderate missingness regimes.

📄 PDF Abstract BibTeX arXiv:2602.22791

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningTrajectory Prediction

Similar Papers 제목 키워드 기반

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

2022-07-20 · Yuxiao Chen, Long Zhao, Jianbo Yuan, Yu Tian 외

Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skel…

Action DetectionAction RecognitionContrastive Learningmotion prediction+1

SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification

2021-07-05 · Haocong Rao, Xiping Hu, Jun Cheng, Bin Hu

Person re-identification via 3D skeletons is an emerging topic with great potential in security-critical applications. Existing methods typically learn body and motion features from the body-joint trajectory, whereas the…

Person Re-IdentificationRelation Network

MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition

2020-10-12 · Lilang Lin, Sijie Song, Wenhan Yan, Jiaying Liu

In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come acros…

Action RecognitionContrastive Learningmotion predictionRepresentation Learning+2

Contrastive Self-Supervised Learning for Skeleton Representations

2022-11-10 · Nico Lingg, Miguel Sarabia, Luca Zappella, Barry-John Theobald

Human skeleton point clouds are commonly used to automatically classify and predict the behaviour of others. In this paper, we use a contrastive self-supervised learning method, SimCLR, to learn representations that capt…

Graph Neural Networkmotion predictionSelf-Supervised Learning

Deep self-supervised learning with visualisation for automatic gesture recognition

2024-06-18 · Fabien Allemand, Alessio Mazzela, Jun Villette, Decky Aspandi 외

Gesture is an important mean of non-verbal communication, with visual modality allows human to convey information during interaction, facilitating peoples and human-machine interactions. However, it is considered difficu…

Gesture RecognitionSelf-Supervised Learning