Research map / Video / Video segmentation and tracking
Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SSLTM instead of IFR | VSPW-FULL video segmentation · VSPW-FULL validation | mIoU: 38.43 -> 40.62 | Helped |
| Use SSLTM instead of IFR | one-frame-per-video VSPW segmentation · VSPW-SF validation | mIoU: 37.35 -> 39.79 | Helped |
| Use SSLTM instead of TMANet | CityScapes video segmentation · CityScapes validation | mIoU: 78.50 -> 79.69 | Helped |
| Add STT short-term temporal modeling (ablation) | UperNet on VSPW-SF · VSPW-SF validation | mIoU: 33.92 -> 36.72 | Helped |
| Add STT short-term temporal modeling (ablation) | UperNet on VSPW-SF · VSPW-SF validation | mVC8: 82.09 -> 87.06 | Helped |
| Add RFCE using a distant reference frame (ablation) | UperNet + STT on VSPW-SF · VSPW-SF validation | mIoU: 36.72 -> 38.75 | Helped |
| Add RFCE using a distant reference frame (ablation) | UperNet + STT on VSPW-SF · VSPW-SF validation | mVC8: 87.06 -> 87.17 | Helped |
| Add GCC global category context (ablation) | UperNet + STT + RFCE on VSPW-SF · VSPW-SF validation | mIoU: 38.75 -> 39.79 | Helped |
| Add GCC global category context (ablation) | UperNet + STT + RFCE on VSPW-SF · VSPW-SF validation | mVC8: 87.17 -> 87.25 | Helped |
| Use distant reference context rather than query-frame self-context (QFCE) (ablation) | UperNet + STT on VSPW-SF · VSPW-SF validation | mIoU: 37.56 -> 38.75 | Helped |
| Use distant reference context rather than query-frame self-context (QFCE) (ablation) | UperNet + STT on VSPW-SF · VSPW-SF validation | mVC8: 87.10 -> 87.17 | Helped |
| Combine SSLTM with MeanTeacher pseudo-labeling | SSLTM on VSPW-SF · VSPW-SF validation | mIoU: 39.79 -> 40.49 | Helped |
Closest papers by meaning
- Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction (CVPR 2022 · similarity 0.89)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation (CVPR 2024 · similarity 0.88)
- Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation (CVPR 2026 · similarity 0.88)
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation (CVPR 2025 · 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.