Research map / Video / Video segmentation and tracking
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Check 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 grid-based memory matching with temporal feature aggregation and score reweighting | VISOLO · YouTube-VIS 2019 val | AP: 36.8 -> 38.6 | Helped |
| Use grid-based memory matching with temporal feature aggregation and score reweighting | VISOLO · YouTube-VIS 2021 val | AP: 34.2 -> 36.9 | Helped |
| Add score reweighting (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 34.6 -> 35.6 | Helped |
| Add temporal aggregation for category features (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 34.6 -> 36.4 | Helped |
| Add score reweighting to category temporal aggregation (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 36.4 -> 37.7 | Helped |
| Add temporal aggregation for mask features (ablation) | VISOLO with SR and category TA · YouTube-VIS 2019 val | AP: 37.7 -> 38.6 | Helped |
| Store 2 rather than every 5 intermediate frames (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 38.6 -> 36.7 | Hurt |
| Store 10 rather than every 5 intermediate frames (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 38.6 -> 37.5 | Hurt |
| Store 20 rather than every 5 intermediate frames (ablation) | VISOLO · YouTube-VIS 2019 val | FPS: 40.0 -> 38.7 | Hurt |
| Use every 5 intermediate frames instead of storing only 2 frames (ablation) | VISOLO · YouTube-VIS 2019 val | AP: 36.7 -> 38.6 | Helped |
Closest papers by meaning
- InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation (NeurIPS 2022 · similarity 0.90)
- End-to-End Video Instance Segmentation With Transformers (CVPR 2021 · similarity 0.90)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.88)
- Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation (AAAI 2025 · similarity 0.87)
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation (CVPR 2025 · similarity 0.86)
- Aligning Instance Brownian Bridge with Texts for Open-Vocabulary Video Instance Segmentation (AAAI 2025 · similarity 0.85)
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.