Research map / Video / Video segmentation and tracking
RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation
Kai Zhu, Zhenyu Cui, Zehua Zang, Jiahuan Zhou
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 |
|---|---|---|---|
| add second SSM path with refined forgetting gate (vs single vanilla SSM) (ablation) | RS-SSM · VSPW (MiT-B1) | mIoU: 38.8 -> 41.7 | Improved |
| add dual-path refinement (vs two vanilla SSM paths) (ablation) | RS-SSM · VSPW (MiT-B5) | mIoU: 49.0 -> 51.6 | Improved |
| add CwAP adaptive guidance (vs simple inverted gate) (ablation) | RS-SSM · VSPW (MiT-B5) | mIoU: 50.2 -> 51.6 | Improved |
| add CwAP adaptive guidance (vs simple inverted gate) (ablation) | RS-SSM · VSPW (Swin-S) | mIoU: 51.6 -> 52.2 | Improved |
| RS-SSM vs TV3S with MiT-B5 | RS-SSM · VSPW | mIoU: 49.8 -> 51.6 | Improved |
| RS-SSM vs TV3S with MiT-B1 | RS-SSM · Cityscapes | mIoU: 75.6 -> 78.3 | Improved |
| RS-SSM vs TV3S with MiT-B5 on NYUv2 | RS-SSM · NYUv2 | mIoU: 46.9 -> 49.1 | Improved |
| RS-SSM vs TV3S on efficiency, MiT-B5 | RS-SSM · VSPW | FPS: 14.0 -> 20.2 | Improved |
Closest papers by meaning
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · similarity 0.88)
- Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation (CVPR 2023 · similarity 0.87)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.85)
- SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost (CVPR 2025 · similarity 0.85)
- State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding (NeurIPS 2025 · similarity 0.84)
- MaskViM: Domain Generalized Semantic Segmentation with State Space Models (AAAI 2025 · similarity 0.84)
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.
