Research map / Learning theory and algorithms / Kernels and regression theory
High-Speed Tracking With Multi-Kernel Correlation Filters
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 |
|---|---|---|---|
| Optimize an upper bound of the MKCF objective and incorporate historical samples with per-kernel weights | MKCFup versus MKCF · OTB2013 | average precision: 6.8% | Helped |
| Optimize an upper bound of the MKCF objective and incorporate historical samples with per-kernel weights | MKCFup versus MKCF · OTB2013 | AUC: 7.7% | Helped |
| Use the proposed upper-bound objective and training scheme | MKCFup versus fMKCF · OTB2013 | average precision: 4.9% | Helped |
| Use the proposed upper-bound objective and training scheme | MKCFup versus fMKCF · OTB2013 | AUC: 6.1% | Helped |
| Use the proposed upper-bound objective and training scheme | MKCFup versus KCF · OTB2013 | AUC: about 16% | Helped |
| Use the proposed upper-bound objective and training scheme | MKCFup versus KCFscale · OTB2013 | AUC: about 7% | Helped |
| Use MKCFup instead of ECO_HC | Trackers on the full OTB2013 and NfS benchmarks · OTB2013 and NfS | precision and AUC | Hurt |
| Use MKCFup instead of ECO_HC on small-move sequences | Trackers · NfS small-move sequences | average precision: 0.5% | Helped |
Closest papers by meaning
- Context-Aware Correlation Filter Tracking (CVPR 2017 · similarity 0.89)
- Correlation Tracking via Joint Discrimination and Reliability Learning (CVPR 2018 · similarity 0.87)
- Multi-Cue Correlation Filters for Robust Visual Tracking (CVPR 2018 · similarity 0.87)
- ECO: Efficient Convolution Operators for Tracking (CVPR 2017 · similarity 0.86)
- DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction (CVPR 2024 · similarity 0.83)
- Sampling-Resilient Multi-Object Tracking (AAAI 2024 · similarity 0.83)
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.