Research map / Reinforcement learning / Visual and representation RL
Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning
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 supervised pretraining on fully labeled training videos (ablation) | ADNet-init · OTB-100 | precision (20px): +3.6% | Helped |
| add supervised pretraining on partially labeled training videos (ablation) | ADNet-init · OTB-100 | precision (20px): +2.6% | Helped |
| use partially labeled rather than fully labeled training data (ablation) | ADNet+SL · OTB-100 | precision (20px): 1.0% lower | Hurt |
| add reinforcement learning after supervised pretraining (ablation) | ADNet+SL · OTB-100 | precision (20px): +1.9% | Helped |
| add reinforcement learning after semi-supervised pretraining (ablation) | ADNet+SS · OTB-100 | precision (20px): +1.0% | Helped |
| reduce online-adaptation samples, update frequency, and redetection candidates for the fast variant (ablation) | ADNet · OTB-100 | precision (20px): 3% performance degradation | Hurt |
Closest papers by meaning
- Visual Tracking via Hierarchical Deep Reinforcement Learning (AAAI 2021 · similarity 0.91)
- Online Decision Based Visual Tracking via Reinforcement Learning (NeurIPS 2020 · similarity 0.89)
- End-to-end Active Object Tracking via Reinforcement Learning (ICML 2018 · similarity 0.88)
- POST: POlicy-Based Switch Tracking (AAAI 2020 · similarity 0.85)
- Unsupervised Video Object Segmentation for Deep Reinforcement Learning (NeurIPS 2018 · similarity 0.85)
- DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors (NeurIPS 2024 · similarity 0.83)
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.