Research map / Video / Video segmentation and tracking
E-MaT:Event-oriented Mamba for Egocentric Point Tracking
Han Han, Wei Zhai, Baocai Yin, Yang Cao, Bin Li, Zheng-jun Zha
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 motion-adaptive suppression (MAS) (ablation) | E-MaT with EOM · DVS-EgoPoints | delta_avg: 38.6 -> 39.8 | Improved |
| add MAS (ablation) | E-MaT with EOM · DVS-EgoPoints | delta*_avg: 67.3 -> 67.8 | Improved |
| motion-guided EOM scan instead of fixed scan direction (H) (ablation) | Mamba encoder · DVS-EgoPoints | delta_avg: 37.2 -> 38.6 | Improved |
| use multiple fixed scan directions instead of one (ablation) | Mamba encoder · DVS-EgoPoints | delta_avg: 37.2 -> 36.3 (four directions) | Hurt |
| use time surface instead of event count or voxel grid (ablation) | E-MaT input · DVS-EgoPoints | delta_avg | Improved |
| use 40ms temporal window for time surface (ablation) | E-MaT input · DVS-EgoPoints | delta_avg | Improved |
| use four refinement iterations rather than fewer or more (ablation) | E-MaT · DVS-EgoPoints | delta_avg | Improved |
| E-MaT event tracker vs CoTracker3 video tracker | E-MaT · DVS-EgoPoints | delta_avg: 36.1 -> 39.8 | Improved |
| E-MaT vs CoTracker3 on in-view accuracy | E-MaT · DVS-EgoPoints | IVA: 99.8 -> 91.2 | Hurt |
| E-MaT vs CoTracker3 on out-of-view accuracy | E-MaT · DVS-EgoPoints | OOVA: 19.7 -> 50.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ETAP — ETAP: Event-based Tracking of Any Point (CVPR 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video (CVPR 2025 · similarity 0.88)
- EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset (NeurIPS 2023 · similarity 0.87)
- Instance Tracking in 3D Scenes from Egocentric Videos (CVPR 2024 · similarity 0.86)
- EgoMo3R: Joint Egocentric Motion and Scene Reconstruction (NeurIPS 2026 · similarity 0.86)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.86)
- Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input (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.
