Research map / Detection and segmentation / Tracking
Structural Correlation Filter for Robust Visual 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 |
|---|---|---|---|
| Use SCF's jointly learned part filters and structural constraints instead of KCF | Correlation-filter tracking · 50 benchmark sequences | OP (%): 62.3 -> 79.7; 17.4% | Helped |
| Use SCF's jointly learned part filters and structural constraints instead of DSST | Correlation-filter tracking · 50 benchmark sequences | OP (%): 66.7 -> 79.7; 13% | Helped |
| Use SCF's jointly learned part filters and structural constraints instead of KCF | Correlation-filter tracking · 50 benchmark sequences | DP (%): 74.0 -> 86.6; 12.6% | Helped |
| Use SCF's jointly learned part filters and structural constraints instead of DSST | Correlation-filter tracking · 50 benchmark sequences | DP (%): 73.7 -> 86.6; 12.9% | Helped |
| Use SCF's jointly learned part filters and structural constraints instead of KCF | Correlation-filter tracking · 50 benchmark sequences | CLE (pixels): 35.5 -> 22.5; 13.0 pixels | Helped |
| Use SCF's jointly learned part filters and structural constraints instead of DSST | Correlation-filter tracking · 50 benchmark sequences | CLE (pixels): 41.3 -> 22.5; 18.8 pixels | Helped |
| Use SCF instead of MUSTer | Visual tracking · 50 benchmark sequences | CLE (pixels): 17.3 -> 22.5 | Hurt |
Closest papers by meaning
- Robust Visual Tracking via Local-Global Correlation Filter (AAAI 2017 · similarity 0.93)
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.91)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.90)
- Multi-Task Correlation Particle Filter for Robust Object Tracking (CVPR 2017 · similarity 0.89)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.89)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.84)
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.