Research map / Video / Video segmentation and tracking
End-to-End Learning of Object Motion Estimation from Retinal Events for Event-Based Object Tracking
Haosheng Chen, David Suter, Qiangqiang Wu, Hanzi Wang
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 |
|---|---|---|---|
| Use event-based RMRNet instead of the strongest conventional tracker, ECO | object tracking · ECD shapes_translation | AOR: 0.823 -> 0.836 | Improved |
| Use event-based RMRNet instead of the strongest conventional tracker | object tracking · ECD shapes_6dof | AOR: 0.847 -> 0.866 | Improved |
| Use event-based RMRNet instead of the strongest conventional tracker | object tracking · ECD poster_6dof | AOR: 0.846 -> 0.859 | Improved |
| Use event-based RMRNet instead of ECO | object tracking · ECD slider_depth | AOR: 0.947 -> 0.915 | Hurt |
| Use RMRNet rather than the strongest conventional tracker | object tracking · EED fast_drone | AOR: 0.830 -> 0.892 | Improved |
| Use RMRNet rather than ECO | object tracking · EED light_variations | AOR: 0.782 -> 0.802 | Improved |
| Use event-based RMRNet rather than ATOM | object tracking · EED what_is_background | AOR: 0.725 -> 0.202 | Hurt |
| Use RMRNet rather than ATOM | object tracking · EED occlusions | AOR: 0.387 -> 0.716 | Improved |
| Add TSLTD instead of classical Time-Surface encoding (ablation) | RMRNet · ECD shapes_translation | AOR: 0.491 -> 0.836 | Improved |
| Add TSLTD instead of classical Time-Surface encoding (ablation) | RMRNet · ECD shapes_6dof | AOR: 0.467 -> 0.866 | Improved |
| Add TSLTD instead of classical Time-Surface encoding (ablation) | RMRNet · ECD poster_6dof | AOR: 0.504 -> 0.859 | Improved |
| Add TSLTD instead of classical Time-Surface encoding (ablation) | RMRNet · ECD slider_depth | AOR: 0.814 -> 0.915 | Improved |
Closest papers by meaning
- End-to-End Learning of Representations for Asynchronous Event-Based Data (ICCV 2019 · similarity 0.90)
- EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · similarity 0.89)
- Event-based Asynchronous Sparse Convolutional Networks (ECCV 2020 · similarity 0.88)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- Fully Spiking Neural Networks for Unified Frame-Event Object Tracking (NeurIPS 2025 · similarity 0.87)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · 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.
