Research map / Detection and segmentation / Tracking
Robust Estimation of Similarity Transformation for Visual Object 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 |
|---|---|---|---|
| Replace the original scale estimator with the log-polar estimator | ECO · OTB-2013 | success: 67.8% -> 69.1% | Helped |
| Replace the original scale estimator with the log-polar estimator | ECO · OTB-2015 | success: 66.8% -> 67.3% | Helped |
| Replace the original scale estimator with the log-polar estimator | SAMF · SAMF speed evaluation | FPS: 20.95 -> 86.75 FPS; 4.14X | Helped |
| Replace the original scale estimator with the log-polar estimator | ECO · ECO speed evaluation | FPS: 2.58 -> 9.88 FPS; 3.82X | Helped |
| Add BCD optimization to the tracker (ablation) | LDES · POT scale-attributed videos | precision: 0.6461 -> 0.7858 | Helped |
| Add BCD optimization to the tracker (ablation) | LDES · POT scale-attributed videos | success: 0.4724 -> 0.5298 | Helped |
| Add BCD optimization to the tracker (ablation) | LDES · POT all 210 sequences | precision: 0.4775 -> 0.5064 | Helped |
| Add BCD optimization to the tracker (ablation) | LDES · POT occlusion-attributed videos | precision: 0.6679 -> 0.6277 | Hurt |
| Turn off BCD and estimate object status only once per frame (ablation) | LDES · OTB benchmark | FPS: 20 fps -> 82 fps | Helped |
| Add BCD optimization (ablation) | LDES · POT rotation-attributed videos | precision: 0.6461 -> 0.6898 | Mixed |
Closest papers by meaning
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.91)
- Robust Visual Tracking via Local-Global Correlation Filter (AAAI 2017 · similarity 0.90)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.88)
- SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking (AAAI 2024 · similarity 0.86)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.86)
- UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (AAAI 2024 · 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.