Research map / Detection and segmentation / Tracking
Multi-Task Correlation Particle Filter for Robust Object 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 |
|---|---|---|---|
| add the multi-task correlation filter to the particle-filter tracker (ablation) | CPF · OTB-2013 | AUC: 65.7 -> 67.7 | Helped |
| add the multi-task correlation filter to the particle-filter tracker (ablation) | CPF · OTB-2015 | AUC: 61.2 -> 62.8 | Helped |
| add particle filtering to the multi-task correlation filter (ablation) | MCF · OTB-2013 | AUC: 60.7 -> 67.7 | Helped |
| add particle filtering to the multi-task correlation filter (ablation) | MCF · OTB-2015 | AUC: 56.6 -> 62.8 | Helped |
| use 10 rather than 100 particles (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 65.1 | Hurt |
| use 30 rather than 100 particles (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 65.9 | Hurt |
| use 50 rather than 100 particles (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 66.1 | Hurt |
| set particle scale to 0.005 rather than 0.01 (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 65.2 | Hurt |
| set particle scale to 0.02 rather than 0.01 (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 66.1 | Hurt |
| set particle scale to 0.05 rather than 0.01 (ablation) | MCPF · OTB-2013 | AUC: 67.7 -> 64.1 | Hurt |
| combine multi-task correlation filtering with particle sampling | MCPF · Temple Color | AUC: +6.1% versus CF2 | Helped |
Closest papers by meaning
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.89)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.89)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.88)
- Context-Aware Correlation Filter Tracking (CVPR 2017 · similarity 0.87)
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.87)
- Robust Visual Tracking via Local-Global Correlation Filter (AAAI 2017 · similarity 0.86)
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.