paper-with-me

Papers

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

2024-03-25 · IEEE Transactions on Image Processing 2024 3 · Woomin Myung, Nan Su, Jing-Hao Xue, Guijin Wang

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.

📄 PDF Abstract BibTeX

Code (1)

WoominM/DeGCN_pytorch 공식 구현 pytorch

Tasks

Action RecognitionSkeleton Based Action Recognition

Similar Papers 제목 키워드 기반

Part-based Graph Convolutional Network for Action Recognition

2018-09-13 · Kalpit Thakkar, P. J. Narayanan

Human actions comprise of joint motion of articulated body parts or `gestures'. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges. Graph convol…

Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition

2024-11-19 · Zeyu Liang, Hailun Xia, Naichuan Zheng, Huan Xu

Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). However, most of these methods tend to construct complex topology learning mechanisms whi…

Action RecognitionSkeleton Based Action Recognition

Sign Language Recognition via Deformable 3D Convolutions and Modulated Graph Convolutional Networks

2023-06-07 · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023 6 · Katerina Papadimitriou, Gerasimos Potamianos

Automatic sign language recognition (SLR) remains challenging, especially when employing RGB video alone (i.e., with no depth or special glove-based input) and under a signer-independent (SI) framework, due to inter-pers…

graph constructionSign Language Recognition

Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition

2018-05-16 · Xikun Zhang, Chang Xu, Xinmei Tian, DaCheng Tao

This paper investigates body bones from skeleton data for skeleton based action recognition. Body joints, as the direct result of mature pose estimation technologies, are always the key concerns of traditional action rec…

Action RecognitionPose EstimationSkeleton Based Action RecognitionTemporal Action Localization

Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

2021-12-20 · Jinfeng Wei, Yunxin Wang, Mengli Guo, Pei Lv 외

Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent the motion information contained in skele…

Action RecognitionSkeleton Based Action Recognition