Research map / Detection and segmentation / Tracking
MC-HOG Correlation Tracking with Saliency Proposal
Guibo Zhu, Jinqiao Wang, Yi Wu, Xiaoyu Zhang, Hanqing Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| extract HOG in 11 color-naming channels instead of gray (ablation) | KCF tracker · OTB-2013 | mean distance precision: 74.3% -> 77.8% | Improved |
| extract HOG in 11 color-naming channels instead of gray (ablation) | KCF tracker · OTB-2013 | success rate: 51.7% -> 55.0% | Improved |
| add saliency proposals with re-ranking (ablation) | MC-HOG tracker · OTB-2013 | success rate: 55.0% -> 56.9% | Improved |
| add saliency proposals with re-ranking (ablation) | MC-HOG tracker · OTB-2013 | mean distance precision: relative gain of 4.6% | Improved |
| use HOG in Luv rather than gray (ablation) | KCF tracker · OTB-2013 | mean distance precision: 74.3% -> 76.8% | Improved |
| use HOG in XYZ or LMS rather than gray (ablation) | KCF tracker · OTB-2013 | mean distance precision: 74.3% -> 60.0% (XYZ), 61.2% (LMS) | Hurt |
| use HOG in RGB or YCbCr rather than gray (ablation) | KCF tracker · OTB-2013 | mean distance precision: 74.3% -> 72.1% (RGB), 72.0% (YCbCr) | Hurt |
| use 11-channel color naming HOG rather than gray (ablation) | KCF tracker · OTB-2013 | speed (mean FPS): 35.9 -> 16.5 | Hurt |
Closest papers by meaning
- Saliency-Associated Object Tracking (ICCV 2021 · similarity 0.87)
- Staple: Complementary Learners for Real-Time Tracking (CVPR 2016 · similarity 0.86)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.86)
- Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning (ECCV 2016 · similarity 0.86)
- Correlation-Aware Deep Tracking (CVPR 2022 · similarity 0.86)
- Learning Multi-Task Correlation Particle Filters for Visual Tracking (TPAMI 2018 · 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.
