Research map / Label-efficient and robust learning / Recognition and long-tail
Dividing and Aggregating Network for Multi-view Action Recognition
Dongang Wang, Wanli Ouyang, Wen Li, Dong Xu
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 message passing module to multi-branch + fusion (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 90.7% -> 92.0% | Improved |
| add view-prediction-guided fusion module (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 90.9% -> 92.0% | Improved |
| add message passing to basic multi-branch module (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 89.8% -> 90.9% | Improved |
| add fusion module to basic multi-branch module (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 89.8% -> 90.7% | Improved |
| use view-specific branches with shared CNN instead of TSN (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 85.4% -> 89.8% | Improved |
| shared view-independent CNN instead of separate ensemble TSN per view (ablation) | DA-Net · NTU RGB+D cross-view | two-stream accuracy: 87.8% -> 89.8% | Improved |
| add message passing to RGB stream (ablation) | DA-Net · NTU RGB+D cross-view | RGB-stream accuracy: 73.9% -> 74.5% | Improved |
| DA-Net instead of TSN | DA-Net · NTU RGB+D cross-subject | accuracy: 84.93% -> 88.12% | Improved |
| DA-Net instead of TSN | DA-Net · NTU RGB+D cross-view | accuracy: 85.36% -> 91.96% | Improved |
| DA-Net instead of TSN | DA-Net · NUMA cross-subject | average accuracy: 90.3% -> 92.1% | Improved |
| DA-Net instead of TSN for unseen view | DA-Net · NUMA cross-view train {2,3} test 1 | accuracy: 76.8% -> 83.1% | Improved |
Closest papers by meaning
- Multi-view Action Recognition using Cross-view Video Prediction (ECCV 2020 · similarity 0.88)
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition (AAAI 2024 · similarity 0.88)
- Generative Multi-View Human Action Recognition (ICCV 2019 · similarity 0.87)
- Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition (ECCV 2016 · similarity 0.86)
- MVFNet: Multi-View Fusion Network for Efficient Video Recognition (AAAI 2021 · similarity 0.86)
- Prompt-guided Disentangled Representation for Action Recognition (NeurIPS 2025 · similarity 0.84)
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.
