Research map / Video / Video segmentation and tracking
Temporal-aware Query Routing for Real-time Video Instance Segmentation
Zesen Cheng, Kehan Li, Yian Zhao, Hang Zhang, Chang Liu, Jie Chen
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 TAR router to MinVIS (small) | MinVIS · YouTubeVIS 2019 | FPS: 24.7 -> 34.6 | Improved |
| add TAR router to MinVIS (small) | MinVIS · YouTubeVIS 2019 | AP: 47.4 -> 48.4 | Improved |
| add TAR router to DVIS++ (small) | DVIS++ · YouTubeVIS 2019 | FPS: 22.4 -> 32.8 | Improved |
| add TAR to DVIS++ (large) | DVIS++ · YouTubeVIS 2019 | inference time (ms): 135.9 -> 124.7 | Improved |
| add TAR to MinVIS (small) | MinVIS · OVIS | AP: 25.0 -> 27.4 | Improved |
| add TAR to DVIS++ (small) | DVIS++ · OVIS | AP75: 37.3 -> 36.2 | Hurt |
| add cross-attention synchronizer before router (ablation) | TAR+MinVIS · YouTubeVIS 2019 | mAP: 45.1 -> 48.4 | Improved |
| use bipartite matching synchronizer instead of cross-attention (ablation) | TAR+MinVIS · YouTubeVIS 2019 | mAP: 48.4 -> 46.4 | Hurt |
| add router on top of cross-attention synchronizer (ablation) | TAR+MinVIS · YouTubeVIS 2019 | FPS: 24.2 -> 34.6 | Improved |
| add Flash Attention 2 to MinVIS (ablation) | MinVIS · YouTubeVIS 2019 | FPS: 24.7 -> 27.8 | Improved |
| add operation fusion to MinVIS (ablation) | MinVIS · YouTubeVIS 2019 | FPS: 24.7 -> 27.2 | Improved |
| combine TAR with Flash Attention 2 and operation fusion (ablation) | TAR+MinVIS · YouTubeVIS 2019 | FPS: 31.7 -> 34.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MinVIS — MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training (NeurIPS 2022) · better on 7 of 7 shared results
- DVIS++ — DVIS++: Improved Decoupled Framework for Universal Video Segmentation (TPAMI 2025) · 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
- InstanceFormer: An Online Video Instance Segmentation Framework (AAAI 2023 · similarity 0.90)
- End-to-End Video Instance Segmentation With Transformers (CVPR 2021 · similarity 0.89)
- Efficient Temporal Action Segmentation via Boundary-aware Query Voting (NeurIPS 2024 · similarity 0.89)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.87)
- Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation (AAAI 2025 · similarity 0.86)
- SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis (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.
