Research map / Video / Video segmentation and tracking
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Jinze Chen, Yang Wang, Yang Cao, Feng Wu, 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 |
|---|---|---|---|
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · Synthetic DVS, n=0.05–0.25 | MIoU: 90.82 -> 94.63; 88.97 -> 93.71; 87.15 -> 92.95; 81.53 -> 89.99; 60.61 -> 79.52 | Improved |
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · EED Fast moving drone | MIoU: 27.17 -> 53.92 | Improved |
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · EED Lighting variations | MIoU: 30.95 -> 48.33 | Improved |
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · EED What is background? | MIoU: 68.43 -> 93.33 | Improved |
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · EED Occluded sequence | MIoU: 69.66 -> 83.23; 86.12 | Hurt |
| Use progressive mutual optimization of motion estimation and event denoising | ProgressiveMotionSeg · EED Multiple objects scene | MIoU: 41.63 -> 51.11 | Improved |
| Add seven progressive motion-estimation and event-denoising iterations (ablation) | ProgressiveMotionSeg · Synthetic DVS, n=0.25 | MIoU | Improved |
| Use the proposed sharpness loss instead of VI (ablation) | ProgressiveMotionSeg · Synthetic DVS, n=0.25 | MIoU: 73.03 -> 79.52 | Improved |
| Use the proposed sharpness loss instead of MIG (ablation) | ProgressiveMotionSeg · Synthetic DVS, n=0.25 | MIoU: 59.16 -> 79.52 | Improved |
| Use the proposed sharpness loss instead of MIH (ablation) | ProgressiveMotionSeg · Synthetic DVS, n=0.25 | MIoU: 72.52 -> 79.52 | Improved |
| Map temporal correlation to event confidence with Tanh (ablation) | ProgressiveMotionSeg ED module · Synthetic DVS | MIoU | Improved |
Closest papers by meaning
- Simultaneous Motion And Noise Estimation with Event Cameras (ICCV 2025 · similarity 0.89)
- Low Cost and Latency Event Camera Background Activity Denoising (TPAMI 2022 · similarity 0.89)
- Event-Based Motion Segmentation by Motion Compensation (ICCV 2019 · similarity 0.88)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.86)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.85)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · 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.
