Research map / Detection and segmentation / Tracking
Fast Template Matching and Update for Video Object Tracking and 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 RL to choose template updates and matching/re-detection decisions | Fast Template Matching and Update · DAVIS 2017 | J: 69.1 vs 68.4 | Helped |
| use RL-controlled template updating instead of no template updates (ablation) | Fast Template Matching and Update · DAVIS 2017 | J_m: 27.3 -> 69.1 | Helped |
| use RL-controlled template updating instead of always updating with IOU matching (ablation) | Fast Template Matching and Update · DAVIS 2017 | J_m: 63.1 -> 69.1 | Helped |
| use RL-controlled template updating and matching instead of always updating with appearance matching (ablation) | Fast Template Matching and Update · DAVIS 2017 | J_m: 67.2 -> 69.1 | Helped |
| replace IOU-only matching with appearance-only matching (ablation) | simple-update tracker · DAVIS 2017 | J_m: 63.1 -> 67.2 | Helped |
| replace IOU-only matching with appearance-only matching (ablation) | simple-update tracker · DAVIS 2017 | t(s): 0.03 -> 1.10 | Hurt |
| remove appearance-based re-detection (ablation) | Fast Template Matching and Update · DAVIS 2017 | J_m: 68.1 -> 69.1 | Hurt |
| train with supervised fixed labels instead of reinforcement learning (ablation) | Fast Template Matching and Update · DAVIS 2017 | J_m: 69.1 -> 60.2 | Hurt |
| replace the one-stage segmentation network with Mask R-CNN (ablation) | Fast Template Matching and Update · VOS evaluation | running time per frame: around 90ms -> around 150ms | Hurt |
| replace the one-stage segmentation network with Mask R-CNN (ablation) | Fast Template Matching and Update · VOS evaluation | accuracy | Helped |
Closest papers by meaning
- Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching (CVPR 2020 · similarity 0.88)
- Reinforcement Cutting-Agent Learning for Video Object Segmentation (CVPR 2018 · similarity 0.88)
- Learning to Track Instances without Video Annotations (CVPR 2021 · similarity 0.88)
- State-Aware Tracker for Real-Time Video Object Segmentation (CVPR 2020 · similarity 0.87)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.87)
- When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation (NeurIPS 2026 · 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.