Research map / Detection and segmentation / Tracking
Online Decision Based Visual Tracking via Reinforcement Learning
Read the paperCheck 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 |
|---|---|---|---|
| switch between FCT and SiamFC with learned decision module vs FCT alone (ablation) | DTNet · OTB2015 | AUC: 0.616 -> 0.660 | Helped |
| switch between FCT and SiamFC vs SiamFC alone (ablation) | DTNet · OTB2015 | AUC: 0.582 -> 0.660 | Helped |
| learned HRL decision module vs manually designed rule-based switch (ablation) | DTNet · OTB2015 | AUC: 0.544 -> 0.660 | Helped |
| learned decision module vs rule-based switch (ablation) | DTNet · LaSOT | AUC: 0.283 -> 0.360 | Helped |
| learned decision module vs rule-based switch (ablation) | DTNet · speed | fps: 19 -> 36 | Helped |
| add third tracker (ACT+FCT+SiamFC vs FCT+SiamFC) (ablation) | DTNet · OTB2015 | AUC: 0.660 -> 0.665 | Helped |
| add third tracker (ACT+FCT+SiamFC vs FCT+SiamFC) (ablation) | DTNet · speed | fps: 36 -> 23 | Hurt |
| combine ATOM and SiamRPN++ with decision module (ablation) | DTNet · OTB2015 | AUC: 0.696 -> 0.701 | Helped |
| combine ATOM and SiamRPN++ with decision module (ablation) | DTNet · LaSOT | AUC: 0.515 -> 0.516 | Helped |
| combine ACT and SiamFC with decision module (ablation) | DTNet · VOT18 | EAO: 0.296 -> 0.303 vs ACT | Mixed |
Closest papers by meaning
- Visual Tracking via Hierarchical Deep Reinforcement Learning (AAAI 2021 · similarity 0.92)
- POST: POlicy-Based Switch Tracking (AAAI 2020 · similarity 0.90)
- Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning (CVPR 2017 · similarity 0.89)
- End-to-end Active Object Tracking via Reinforcement Learning (ICML 2018 · similarity 0.88)
- RELO: Reinforcement Learning to Localize for Visual Object Tracking (ICML 2026 · similarity 0.86)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 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.