Research map / Label-efficient and robust learning / Test-time adaptation
EVEE: Event-Based Online Adaptation for Matching on Unknown Targets
Zejing Zhao, Cheng Ju, Yanwen Zhang, Akio NAMIKI
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 real event input (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 79.9 -> 81.4 | Improved |
| add proxy events (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.1 -> 81.4 | Improved |
| add Event Voting Bank (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 79.8 -> 81.4 | Improved |
| add online learning (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.8 -> 81.4 | Improved |
| add temporal fusion in pre-training (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 74.9 -> 81.4 | Improved |
| add Haar-wavelet contour extractor in pre-training (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.6 -> 81.4 | Improved |
| add multi-thread training with best-weight broadcasting and loss threshold over single thread (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.4 -> 81.4 | Improved |
| add wavelet sharpening and open-close filtering in EVB (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.1 -> 81.4 | Improved |
| add ReWeight in the matcher (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 81.2 -> 81.4 | Improved |
| add EVB priors in the matcher (ablation) | EVEE · NAVI-MultiView | pose ACC@10 (%): 80.9 -> 81.4 | Improved |
| add event input to SP+LG | SP+LG · NAVI-MultiView | pose ACC@10 (%): 78.4 -> 77.8 | Hurt |
| use event input (time cost) (ablation) | EVEE · NAVI-MultiView | runtime (FPS): 54.49 -> 51.31 | Hurt |
Closest papers by meaning
- Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras (ECCV 2026 · similarity 0.87)
- ReTracker: Exploring Image Matching for Robust Online Any Point Tracking (ICCV 2025 · similarity 0.86)
- Detect by Track: Making Detector-Free Matcher Trackable (ECCV 2026 · similarity 0.85)
- EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching (ICCV 2025 · similarity 0.85)
- Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (ECCV 2018 · similarity 0.85)
- EventFly: Event Camera Perception from Ground to the Sky (CVPR 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.
