Research map / Label-efficient and robust learning / Recognition and long-tail
Correlation Tracking via Joint Discrimination and Reliability 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 |
|---|---|---|---|
| jointly learn a local response consistency-constrained base filter and reliability weight map (ablation) | Baseline · OTB-2015 | distance precision: +3.5% | Helped |
| jointly learn a local response consistency-constrained base filter and reliability weight map (ablation) | Baseline · OTB-2015 | AUC: +2.3% | Helped |
| jointly learn a local response consistency-constrained base filter and reliability weight map (ablation) | Baseline · VOT-2016 | EAO: +6.9% | Helped |
| add reliability weight map learning (ablation) | Baseline+LRC · OTB-2015 | AUC: +1.5% | Helped |
| add reliability weight map learning (ablation) | Baseline+LRC · VOT-2016 | EAO: +2.3% | Helped |
| use DRT instead of ECO | visual tracking · VOT-2016 | EAO: 0.374 -> 0.442 | Helped |
| use DRT instead of ECO | visual tracking · VOT-2016 | robustness raw value (R): 0.200 -> 0.140 | Helped |
| use DRT instead of SSAT | visual tracking · VOT-2016 | accuracy raw value (A): 0.577 -> 0.569 | Hurt |
Closest papers by meaning
- Context-Aware Correlation Filter Tracking (CVPR 2017 · similarity 0.91)
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.90)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.90)
- Discriminative Correlation Filter With Channel and Spatial Reliability (CVPR 2017 · similarity 0.90)
- Staple: Complementary Learners for Real-Time Tracking (CVPR 2016 · similarity 0.88)
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.88)
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.