Research map / Video / Video segmentation and tracking
TCOVIS: Temporally Consistent Online Video Instance Segmentation
Junlong Li, Bingyao Yu, Yongming Rao, Jie Zhou, Jiwen Lu
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 |
|---|---|---|---|
| Replace local matching and propagating with global instance assignment (ablation) | TCOVIS ResNet-50 · YouTube-VIS 2021 | AP: 47.4 -> 48.6 | Improved |
| Add spatio-temporal enhancement module on top of global assignment (ablation) | TCOVIS ResNet-50 · YouTube-VIS 2021 | AP: 48.6 -> 49.5 | Improved |
| Add both GIA and STE over LocPro baseline (ablation) | TCOVIS ResNet-50 · YouTube-VIS 2019 | AP: 50.6 -> 52.3 | Improved |
| Use cross-attention with shared positional embedding instead of concatenation for STE (ablation) | STE · YouTube-VIS 2021 | AP: 47.9 -> 49.5 | Improved |
| Add self-attention layer before cross-attention in STE (ablation) | STE · YouTube-VIS 2021 | AP: 49.5 -> 48.2 | Hurt |
| Apply enhancement at every decoder layer (decoder modulation) (ablation) | STE · YouTube-VIS 2021 | AP: 49.5 -> 48.5 | Hurt |
| Share positional embedding between spatial feature and query of same instance (ablation) | STE · YouTube-VIS 2021 | AP: 48.8 -> 49.5 | Improved |
| Decode spatial features of all instances rather than only the instance itself (ablation) | STE · YouTube-VIS 2021 | AP: 49.2 -> 49.5 | Improved |
| TCOVIS versus online GenVIS with Swin-L | TCOVIS · YouTube-VIS 2022 | AP: 45.1 -> 51.0 | Improved |
| TCOVIS versus online GenVIS with ResNet-50 | TCOVIS · OVIS | AP: 35.8 -> 35.3 | Hurt |
| TCOVIS versus IDOL with Swin-L | TCOVIS · YouTube-VIS 2019 | AP: 64.3 -> 64.1 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports TCOVIS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement (ECCV 2024 · better on 3 of 4 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
- CTVIS: Consistent Training for Online Video Instance Segmentation (ICCV 2023 · similarity 0.90)
- VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation (CVPR 2022 · similarity 0.89)
- Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation (AAAI 2025 · similarity 0.89)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.89)
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation (CVPR 2025 · similarity 0.87)
- Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation (AAAI 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.
