Skip to content

Similar papers

Open access Sep 2026

MG2CL: Multi-Granularity Graph Contrastive Learning for Skeleton-Based Action Recognition

Skeleton-based action recognition has gained increasing attention as a robust alternative to RGB-based methods due to its resilience to background clutter and lighting variations. Existing approaches have achieved notable progress, particularly with graph-based models that capture topological and temporal patterns of h...

Pensong Wang, Zhi-Ze Wu, Xin Chen et al. · 0 citations
Open access Sep 2026

DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition

Robust skeleton-based action recognition requires representations that capture a wide spectrum of motions, from subtle to moderate and strong ones. Existing methods often focus on strong motions. This paper introduces DiMoP, a masking- and diffusion-driven motion representation learning method with frame-level pseudo-c...

Shanaka Ramesh Gunasekara, Wan-Qing Li, Nikalal Kaldera et al. · 0 citations
Open access Aug 2026

Graph Topology-Guided Multi-Task Learning for Fall Detection

The proposed MTC-DETR framework outperforms 14 state-of-the-art methods, proving its robustness and potential for real-world fall detection applications, and is deployed on the Leju Kuavo 5 Robot.

Xiang-Tao Zhao, Pei-Lin Jin · 0 citations
Aug 2026

Spatio-temporal local graph convolutional network for skeleton-based action recognition

A novel approach called Spatio-Temporal Local Graph Convolutional Network, which consists of a Partitioning Module (PM), a Spatio-Temporal Graph Convolution (ST-GC) module and a Joint Prototype Loss (JPL) function, which facilitates the capture of local relationships between joints.

Wen-Peng Wang, Guo-Long Qin, Xi-Zhan Gao et al. · 0 citations
Open access Aug 2026

Motion-Guided Dynamic-Graph Construction with Kinematic-Aware Transformer for Skeleton Action Recognition

A single-stream architecture that constructs an action-specific skeleton graph directly from motion and processes it with a kinematic-aware Transformer, and demonstrates that the approach achieves competitive performance compared to state-of-the-art architectures.

K. Khudaybergenov, A. Marakhimov · 1 citation
Aug 2026

Self-supervised skeleton action recognition based on graph prototype learning

This work presents a novel self-supervised architecture centered on graph prototype learning that sets a new state-of-the-art on the ARMM dataset with an accuracy of 95.70%, substantiating the efficacy and transferability of prototype-guided self-supervised learning for skeleton-based action representation.

Zhijie Xu, Hong-Wei Chen, Xia Li · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.