Research map / 3D vision / Human pose estimation
Learning Topology-Aware Dynamic Associations for Robust Multi-Person Pose Estimation
Shengnan Hu, Yandong Liu, Jiangnan Liu, Yahong Chen
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 dynamic keypoint box modulation (ablation) | TopoDA baseline · CrowdPose test | AP: 68.7 -> 69.8 | Improved |
| add cross-keypoint learning (ablation) | TopoDA baseline · CrowdPose test | AP: 68.7 -> 70.0 | Improved |
| add locally-aware feature alignment (LAFA) (ablation) | TopoDA baseline · CrowdPose test | AP: 68.7 -> 70.3 | Improved |
| combine all three modules (DKBM, CL, LAFA) (ablation) | TopoDA baseline · CrowdPose test | AP: 68.7 -> 71.4 | Improved |
| use deformable (DCNv4) offset alignment instead of direct fusion (ablation) | TopoDA LAFA · CrowdPose test | AP: 70.7 -> 71.4 | Improved |
| use DCNv4 offset alignment instead of offset addition (ablation) | TopoDA LAFA · CrowdPose test | AP: 70.9 -> 71.4 | Improved |
| use DCNv4 offset alignment instead of standard convolution offsets (ablation) | TopoDA LAFA · CrowdPose test | AP: 71.1 -> 71.4 | Improved |
| use LAFA instead of FPN as feature pyramid (ablation) | TopoDA · CrowdPose test | AP: 70.1 -> 71.4 | Improved |
| use LAFA instead of BiFPN as feature pyramid (ablation) | TopoDA · CrowdPose test | AP: 70.8 -> 71.4 | Improved |
| add dynamic keypoint box constraint loss L_dk (ablation) | TopoDA · CrowdPose test | AP | Improved |
Closest papers by meaning
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.88)
- DGCN: Dynamic Graph Convolutional Network for Efficient Multi-Person Pose Estimation (AAAI 2020 · similarity 0.87)
- Temporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking (ECCV 2020 · similarity 0.87)
- Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation (ECCV 2020 · similarity 0.87)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.86)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.85)
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.
