UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition

Myung, Woomin; Su, Nan; Xue, Jing-Hao; Wang, Guijin; (2024) DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition. IEEE Transactions on Image Processing 10.1109/tip.2024.3378886. (In press). Green open access

[thumbnail of WoominMyung-TIP-2024.pdf] Text
WoominMyung-TIP-2024.pdf - Accepted Version

Download (4MB)

Abstract

Graph convolutional networks (GCN) have recently been studied to exploit the graph topology of the human body for skeleton-based action recognition. However, most of these methods unfortunately aggregate messages via an inflexible pattern for various action samples, lacking the awareness of intra-class variety and the suitableness for skeleton sequences, which often contain redundant or even detrimental connections. In this paper, we propose a novel Deformable Graph Convolutional Network (DeGCN) to adaptively capture the most informative joints. The proposed DeGCN learns the deformable sampling locations on both spatial and temporal graphs, enabling the model to perceive discriminative receptive fields. Notably, considering human action is inherently continuous, the corresponding temporal features are defined in a continuous latent space. Furthermore, we design an innovative multi-branch framework, which not only strikes a better trade-off between accuracy and model size, but also elevates the effect of ensemble between the joint and bone modalities remarkably. Extensive experiments show that our proposed method achieves state-of-the-art performances on three widely used datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA.

Type: Article
Title: DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tip.2024.3378886
Publisher version: http://dx.doi.org/10.1109/tip.2024.3378886
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Convolution , Adaptation models , Topology , Deformable models , Correlation , Convolutional neural networks , Laplace equations
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10189813
Downloads since deposit
29Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item