Research map / Label-efficient and robust learning / Recognition and long-tail
Context-Aware Correlation Filter 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 |
|---|---|---|---|
| Add context patches as a regularizer to MOSSE | MOSSE · OTB-100 | precision: 0.414 -> 0.598 | Helped |
| Add context patches as a regularizer to MOSSE | MOSSE · OTB-100 | success: 0.311 -> 0.447 | Helped |
| Add context patches as a regularizer to DCF | DCF · OTB-100 | precision: 0.690 -> 0.744 | Helped |
| Add context patches as a regularizer to DCF | DCF · OTB-100 | success: 0.475 -> 0.511 | Helped |
| Add context patches as a regularizer to SAMF | SAMF · OTB-100 | precision: 0.743 -> 0.793 | Helped |
| Add context patches as a regularizer to SAMF | SAMF · OTB-100 | success: 0.535 -> 0.575 | Helped |
| Add context patches as a regularizer to STAPLE | STAPLE · OTB-100 | precision: 0.784 -> 0.810 | Helped |
| Add context patches as a regularizer to STAPLE | STAPLE · OTB-100 | success: 0.579 -> 0.598 | Helped |
| Use context patches instead of the target-adaptive framework with SAMF | SAMF · OTB-100 | success: 0.549 -> 0.575 | Helped |
| Use context patches instead of the target-adaptive framework with DCF | DCF · OTB-100 | success: 0.504 -> 0.511 | Helped |
| Use context patches instead of the target-adaptive framework with MOSSE | MOSSE · OTB-100 | success: 0.413 -> 0.447 | Helped |
Closest papers by meaning
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.91)
- High-Speed Tracking With Multi-Kernel Correlation Filters (CVPR 2018 · similarity 0.89)
- Context-Aware Deep Feature Compression for High-Speed Visual Tracking (CVPR 2018 · similarity 0.89)
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.89)
- Visual Tracking via Adaptive Spatially-Regularized Correlation Filters (CVPR 2019 · similarity 0.88)
- Less Is More: Token Context-Aware Learning for Object Tracking (AAAI 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.