Research map / Video / Action recognition
Hypergraph-Based Multi-View Action Recognition Using Event Cameras
Yue Gao, Jiaxuan Lu, Siqi Li, Yipeng Li, Shaoyi Du
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hypergraph neural network fusion with vertex attention to multi-view baseline | Multi-view baseline · DHP19 (cross-subject) | Top-1 accuracy: 81.43 -> 92.42 | Improved |
| add hypergraph neural network fusion with vertex attention to multi-view baseline | Multi-view baseline · THU-MV-EACT-50 (cross-subject) | Top-1 accuracy: 92.53 -> 95.74 | Improved |
| add hypergraph fusion to multi-view baseline | Multi-view baseline · DHP19 (cross-view) | Top-1 accuracy: 39.28 -> 51.63 | Improved |
| add hypergraph fusion to multi-view baseline | Multi-view baseline · THU-MV-EACT-50 (cross-view) | Top-1 accuracy: 54.38 -> 58.54 | Improved |
| use multiple views instead of single view | Single-view baseline · DHP19 (cross-subject) | Top-1 accuracy: 78.94 -> 81.43 | Improved |
| use multiple views instead of single view | Single-view baseline · THU-MV-EACT-50 (cross-view) | Top-1 accuracy: 47.98 -> 54.38 | Improved |
| replace graph (GNN) fusion with hypergraph fusion | HyperMV-GNN · DHP19 (cross-view) | Top-1 accuracy: 47.62 -> 51.63 | Improved |
| combine KNN-based hyperedges with rule-based hyperedges (ablation) | HyperMV with rule-based hyperedges · THU-MV-EACT-50 (cross-subject) | Top-1 accuracy: 93.89 -> 95.74 | Improved |
| combine rule-based hyperedges with KNN-based hyperedges (ablation) | HyperMV with KNN-based hyperedges · DHP19 (cross-view) | Top-1 accuracy: 47.80 -> 51.63 | Improved |
| add vertex attention mechanism (ablation) | HyperMV · THU-MV-EACT-50 (cross-subject) | Top-1 accuracy: 93.42 -> 95.74 | Improved |
| add vertex attention mechanism (ablation) | HyperMV · THU-MV-EACT-50 (cross-view) | Top-1 accuracy: 57.21 -> 58.54 | Improved |
| add vertex attention mechanism (ablation) | HyperMV-GNN · THU-MV-EACT-50 (cross-subject) | Top-1 accuracy: 93.02 -> 94.82 | Improved |
Closest papers by meaning
- Action Recognition and Benchmark Using Event Cameras (TPAMI 2023 · similarity 0.88)
- Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms (IJCV 2026 · similarity 0.87)
- DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition (ECCV 2024 · similarity 0.86)
- Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections (ICCV 2025 · similarity 0.86)
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition (AAAI 2024 · similarity 0.86)
- Multi-view Action Recognition using Cross-view Video Prediction (ECCV 2020 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
