Research map / Architectures and efficiency / CNN design
Learning Spatial-Aware Regressions for Visual Tracking
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 |
|---|---|---|---|
| Add the cross-patch similarity (CPS) kernel (ablation) | Baseline KRR and CNN tracker · OTB-2015 | precision: +5.35% relative performance gain | Helped |
| Add the cross-patch similarity (CPS) kernel (ablation) | Baseline KRR and CNN tracker · OTB-2015 | success plot: +6.93% relative performance gain | Helped |
| Add spatially regularized kernels (SRK) (ablation) | Baseline KRR and CNN tracker · OTB-2015 | precision | Helped |
| Add spatially regularized kernels (SRK) (ablation) | Baseline KRR and CNN tracker · OTB-2015 | success plot | Helped |
| Add CPS and SRK (ablation) | Baseline KRR and CNN tracker · OTB-2015 | precision: +9.75% relative gain | Helped |
| Add CPS and SRK (ablation) | Baseline KRR and CNN tracker · OTB-2015 | success plot: +10.89% relative gain | Helped |
| Combine spatial-aware KRR and CNN responses | LSART · VOT-2017 | EAO: 12.94% relative performance gain over CFCF | Helped |
| Use LSART instead of ECO | VOT-2017 · VOT-2017 | EAO: 15.36% relative gain | Helped |
| Use LSART instead of ECO | LSART · OTB-2015, in-plane rotation attribute | precision: 1.8% | Helped |
| Use LSART instead of the second-best tracker | LSART · OTB-2015, deformation attribute | precision: 4.3% | Helped |
Closest papers by meaning
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.88)
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.88)
- Release the Power of Online-Training for Robust Visual Tracking (AAAI 2020 · similarity 0.87)
- Multiple Object Tracking With Correlation Learning (CVPR 2021 · similarity 0.87)
- STCT: Sequentially Training Convolutional Networks for Visual Tracking (CVPR 2016 · similarity 0.87)
- Efficient Motion Prompt Learning for Robust Visual Tracking (ICML 2025 · 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.