eprintid: 10189813 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/18/98/13 datestamp: 2024-03-27 16:20:51 lastmod: 2024-03-27 16:20:51 status_changed: 2024-03-27 16:20:51 type: article metadata_visibility: show sword_depositor: 699 creators_name: Myung, Woomin creators_name: Su, Nan creators_name: Xue, Jing-Hao creators_name: Wang, Guijin title: DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition ispublished: inpress divisions: UCL divisions: B04 divisions: C06 divisions: F61 keywords: Convolution , Adaptation models , Topology , Deformable models , Correlation , Convolutional neural networks , Laplace equations note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. 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. date: 2024 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: http://dx.doi.org/10.1109/tip.2024.3378886 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2262735 doi: 10.1109/tip.2024.3378886 lyricists_name: Xue, Jinghao lyricists_id: JXUEX60 actors_name: Xue, Jinghao actors_id: JXUEX60 actors_role: owner full_text_status: public publication: IEEE Transactions on Image Processing citation: 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 <https://doi.org/10.1109/tip.2024.3378886>. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10189813/1/WoominMyung-TIP-2024.pdf