Research map / Video / Video segmentation and tracking
Self-Supervised Video Object Segmentation by Motion Grouping
Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie
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 PWC-Net flow with the proposed model instead of CIS (ablation) | motion grouping model · DAVIS2016 | J mean: outperforms CIS by about 4.5 points | Improved |
| use RAFT flow instead of PWC-Net (ablation) | motion grouping model · DAVIS2016 | J mean | Improved |
| add instance normalization (ablation) | motion grouping model · DAVIS2016 | J mean | Improved |
| increase grouping iterations from T=3 to T=5 (ablation) | motion grouping model · DAVIS2016 | J mean | Improved |
| increase grouping iterations to T=8 (ablation) | motion grouping model · DAVIS2016 | J mean | Hurt |
| add temporal consistency loss (ablation) | motion grouping model · DAVIS2016 | J mean | Improved |
| add entropy regularization (ablation) | motion grouping model · DAVIS2016 | J mean | Improved |
| self-supervised flow-only grouping vs CIS (no post-processing) | motion grouping model · DAVIS2016 | J mean: +9.1% | Improved |
| use flow-only grouping vs CIS on camouflage | motion grouping model · MoCA | success rate: 14% | Improved |
| use flow-only grouping vs supervised COD | motion grouping model · MoCA | J: 18.5% on Jaccard | Improved |
Closest papers by meaning
- Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation (ECCV 2024 · similarity 0.89)
- It’s Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos (ECCV 2016 · similarity 0.89)
- Learning to Segment Moving Objects (IJCV 2018 · similarity 0.88)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.87)
- Segment Any Motion in Videos (CVPR 2025 · similarity 0.87)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.87)
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.
