Research map / Video / Video segmentation and tracking
Video State-Changing Object Segmentation
Jiangwei Yu, Xiang Li, Xinran Zhao, Hongming Zhang, Yu-Xiong 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 |
|---|---|---|---|
| fine-tune with first/last frame cycle consistency (no teacher-student loss) (ablation) | XMem · VSCOS | J&F: 66.7 -> 73.6 | Improved |
| add EMA teacher-student Dice loss to fine-tuning (ablation) | XMem-SC · VSCOS | J&F: 73.6 -> 75.1 | Improved |
| add Contrastive Random Walk auxiliary loss (ablation) | XMem-SC · VSCOS | J&F: 75.1 -> 75.4 | Improved |
| add optical flow features via flow encoder fusion (ablation) | XMem-SC · VSCOS | J&F: 75.4 -> 76.5 | Improved |
| apply VSCOS adaptation to DeAOT | DeAOT · VSCOS | J&F: 73.3 -> 77.1 | Improved |
| apply VSCOS adaptation to XMem on novel state changes with seen objects | XMem · VSCOS open-vocab novel state changes + seen objects | J&F: 63.0 -> 64.1 | Improved |
| fine-tune without teacher-student loss (ablation) | XMem fine-tuning · VSCOS | training stability | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- XMem — XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model (ECCV 2022) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Breaking the "Object" in Video Object Segmentation (CVPR 2023 · similarity 0.92)
- Learning Object State Changes in Videos: An Open-World Perspective (CVPR 2024 · similarity 0.90)
- LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation (TPAMI 2025 · similarity 0.90)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.89)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.89)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
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.
