Research map / Video / Video segmentation and tracking
SWEM: Towards Real-Time Video Object Segmentation With Sequential Weighted Expectation-Maximization
Zhihui Lin, Tianyu Yang, Maomao Li, Ziyu Wang, Chun Yuan, Wenhao Jiang, Wei Liu
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 adaptive pixel weights rather than fixed mask weights (ablation) | SWEM · DAVIS 2017 val | J&F: 77.6 -> 81.9 | Improved |
| Use 128 rather than 32 bases (ablation) | SWEM · DAVIS 2017 val | J&F: 80.2 -> 81.9 | Improved |
| Increase the number of bases from 128 to 256 (ablation) | SWEM · DAVIS 2017 val | J&F: 81.9 -> 82.0 | No clear effect |
| Increase SWEM iterations from 1 to 4 (ablation) | SWEM · DAVIS 2017 val | J&F: 77.9 -> 81.9 | Improved |
| Increase SWEM iterations from 4 to 7 (ablation) | SWEM · DAVIS 2017 val | J&F: 81.9 -> 79.8 | Hurt |
| Use 64 rather than 8 permutation-invariant features (ablation) | SWEM · DAVIS 2017 val | J&F: 81.0 -> 81.9 | Improved |
| Increase permutation-invariant features from 64 to 128 (ablation) | SWEM · DAVIS 2017 val | J&F: 81.9 -> 81.6 | Hurt |
| Set the similarity temperature to τ=0.05 rather than τ=1 (ablation) | SWEM · DAVIS 2017 val | J&F: 66.7 -> 81.9 | Improved |
Closest papers by meaning
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- Learning Position and Target Consistency for Memory-Based Video Object Segmentation (CVPR 2021 · similarity 0.87)
- LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation (TPAMI 2025 · similarity 0.86)
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.86)
- Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective (IJCV 2022 · similarity 0.86)
- RMem: Restricted Memory Banks Improve Video Object Segmentation (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.
