Dual-branch differential channel hypergraph convolutional network for human skeleton based action recognition
Dong Chen, Kaichen She, Peisong Wu, Mingdong Chen, Chuanqi Li, Xiyu Liu, Xiyu Liu, Xiyu Liu, Xiyu Liu
TL;DR
This paper introduces a new neural network for action recognition using human skeleton data that better captures complex joint relationships.
Contribution
The paper proposes a dual-branch hypergraph convolutional network that integrates spatio-temporal and channel-differential features for improved action recognition.
Findings
The proposed DBC-HCN model achieves 96.9% accuracy on the cross X-View benchmark of the NTU RGB+D 60 dataset.
The model outperforms existing methods by combining static and dynamic hypergraphs with channel optimization.
The dual-stream architecture enhances action feature representation through spatio-temporal and channel-differential analysis.
Abstract
Graph Convolutional Networks (GCNs) perform well in skeleton action recognition tasks, but their pairwise node connections make it difficult to effectively model high-order dependencies between non-adjacent joints. To address this issue, hypergraph methods have emerged with the aim of capturing complex associations between multiple joints. However, existing methods either rely on static hypergraph structures or fail to fully exploit feature interactions between channels, limiting their ability to adapt to complex action patterns. Therefore, we propose the Dual-Branch Differential Channel Hypergraph Convolutional Network (DBC-HCN), which leverages hypergraphs’ ability to represent a priori non-natural dependencies in skeletal structures. It extracts spatio-temporal topological information and higher-order correlations by integrating static and dynamic hypergraphs, leveraging channel…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23
Figure 24
Figure 25
Figure 26
Figure 27
Figure 28
Figure 29
Figure 30
Figure 31
Figure 32
Figure 33
Figure 34
Figure 35
Figure 36
Figure 37
Figure 38
Figure 39
Figure 40
Figure 41
Figure 42
Figure 43
Figure 44
Figure 45
Figure 46
Figure 47
Figure 48
Figure 49
Figure 50Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Gait Recognition and Analysis · Anomaly Detection Techniques and Applications