Research map / Architectures and efficiency / CNN design
Recurrently Target-Attending Tracking
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 multi-directional RNN confidence maps to weight correlation-filter learning | RTT versus SAMF · tracking benchmark [44] | VOR: about 2.1% | Helped |
| Use multi-directional RNN confidence maps to weight correlation-filter learning | RTT versus SAMF · tracking benchmark [44] | CLE: about 4.7% | Helped |
| Use RTT's reliable-part weighting and confidence-map approach instead of the standard HOG-based scale-adaptive tracker | RTT versus SA · tracking benchmark [44] | VOR: about 5% | Helped |
| Use RTT's reliable-part weighting and confidence-map approach instead of the standard HOG-based scale-adaptive tracker | RTT versus SA · tracking benchmark [44] | CLE: about 10% | Helped |
Closest papers by meaning
- Online Multi-Target Tracking Using Recurrent Neural Networks (AAAI 2017 · similarity 0.90)
- Attentional Correlation Filter Network for Adaptive Visual Tracking (CVPR 2017 · similarity 0.88)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.87)
- Correlation-Aware Deep Tracking (CVPR 2022 · similarity 0.87)
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.86)
- RTracker: Recoverable Tracking via PN Tree Structured Memory (CVPR 2024 · 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.