Research map / Video / Video segmentation and tracking
State-Aware Tracker for Real-Time Video Object 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 |
|---|---|---|---|
| Add SiamFC++ tracking to Naive Seg (ablation) | Naive Seg · DAVIS2017-Val | J & F: +13.5 | Helped |
| Add correlated feature (ablation) | Track-Seg · DAVIS2017-Val | J & F: +2.3 | Helped |
| Add Global Modeling Loop (ablation) | Track-Seg with correlated feature · DAVIS2017-Val | J & F: +4.8 | Helped |
| Add Cropping Strategy Loop (ablation) | Track-Seg with correlated feature and Global Modeling Loop · DAVIS2017-Val | J & F: +3.6 | Helped |
| Use a dynamic global representation instead of first frame plus previous frame (ablation) | SAT global modeling · DAVIS2017-Val | J & F: -1.2 | Helped |
| Use a dynamic global representation instead of only the first frame (ablation) | SAT global modeling · DAVIS2017-Val | J & F: -2.6 | Helped |
| Weight global updates with the estimated state score (ablation) | SAT global modeling · DAVIS2017-Val | J & F: -1.2 | Helped |
| Filter background pixels before updating the global representation (ablation) | SAT global modeling · DAVIS2017-Val | J & F: -5.6 | Helped |
| Filter background pixels rather than concatenate the mask with images (ablation) | SAT global modeling · DAVIS2017-Val | J & F: -5.8 | Helped |
| Add Global Modeling Loop (ablation) | Track-Seg with correlated feature and Cropping Strategy Loop · DAVIS2017-Val | J & F: -6.4 | Helped |
| Add correlated feature (ablation) | Track-Seg with Global Modeling Loop and Cropping Strategy Loop · DAVIS2017-Val | J & F: -4.3 | Helped |
| Add tracking to Naive Seg with correlated feature and Global Modeling Loop (ablation) | Naive Seg · DAVIS2017-Val | J & F: -12.2 | Helped |
Closest papers by meaning
- Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching (CVPR 2020 · similarity 0.89)
- Fast Online Object Tracking and Segmentation: A Unifying Approach (CVPR 2019 · similarity 0.88)
- Learning Position and Target Consistency for Memory-Based Video Object Segmentation (CVPR 2021 · similarity 0.88)
- Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement (NeurIPS 2020 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · 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.