# High-speed Tracking with Multi-kernel Correlation Filters

arXiv: https://arxiv.org/abs/1806.06418 · HTML: https://mlsanity.com/paper/1806.06418/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2018.

## Built on by (most cited first, 6 of 6)

- [Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking](https://mlsanity.com/paper/2101.08466/) (2021)
- [SiamCorners: Siamese Corner Networks for Visual Tracking](https://mlsanity.com/paper/2104.07303/) (2021)
- [3D Visual Tracking Framework with Deep Learning for Asteroid Exploration](https://mlsanity.com/paper/2111.10737/) (2021)
- [NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking](https://mlsanity.com/paper/2410.20421/) (2024)
- [Benchmarking Deep Trackers on Aerial Videos](https://mlsanity.com/paper/2103.12924/) (2021)
- [GenTrack: A New Generation of Multi-Object Tracking](https://mlsanity.com/paper/2510.24399/) (2025)

## Abstract (arXiv)

Correlation filter (CF) based trackers are currently ranked top in terms of their performances. Nevertheless, only some of them, such as KCF~citehenriques15 and MKCF~citetangm15, are able to exploit the powerful discriminability of non-linear kernels. Although MKCF achieves more powerful discriminability than KCF through introducing multi-kernel learning (MKL) into KCF, its improvement over KCF is quite limited and its computational burden increases significantly in comparison with KCF. In this paper, we will introduce the MKL into KCF in a different way than MKCF. We reformulate the MKL version of CF objective function with its upper bound, alleviating the negative mutual interference of different kernels significantly. Our novel MKCF tracker, MKCFup, outperforms KCF and MKCF with large margins and can still work at very high fps. Extensive experiments on public datasets show that our method is superior to state-of-the-art algorithms for target objects of small move at very high speed.