Research map / Detection and segmentation / Tracking
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning
Yao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, Li Zhang
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 |
|---|---|---|---|
| use sparsity-related losses (l1, l1l2, l2,1) instead of squared loss (ablation) | KCF correlation filter · OTB 51 sequences, occlusion | precision / success rate | Improved |
| use l1l2 loss instead of squared loss (ablation) | KCF correlation filter · OTB deformation sequences | precision / success rate | Improved |
| use l2,1 loss instead of squared loss (ablation) | KCF correlation filter · OTB deformation sequences | precision / success rate | No clear effect |
| use l1 loss instead of squared loss (ablation) | KCF correlation filter · OTB deformation sequences | precision / success rate | Improved |
| use sparsity-related losses instead of squared loss (ablation) | KCF correlation filter · OTB illumination change sequences | precision / success rate | No clear effect |
| use sparsity-related losses instead of squared loss (ablation) | KCF correlation filter · OTB scale variation sequences | precision / success rate | Mixed |
| use sparsity-related losses instead of squared loss (ablation) | KCF correlation filter · OTB rotation sequences | precision / success rate | Improved |
| use l1l2 loss instead of squared loss (ablation) | KCF correlation filter · filter peak stability, occlusion (faceocc2) | peak value sensitivity | Improved |
| use proposed trackers instead of top five trackers in the benchmark | Struck, SCM, TLD, ASLA, CXT · OTB 51 sequences | precision (rho=20): 14% | Improved |
Closest papers by meaning
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.92)
- Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking (IJCV 2018 · similarity 0.91)
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.91)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.90)
- Robust Visual Tracking via Local-Global Correlation Filter (AAAI 2017 · similarity 0.90)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.90)
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.
