# Kernel Cross-Correlator

arXiv: https://arxiv.org/abs/1709.05936 · HTML: https://mlsanity.com/paper/1709.05936/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

## Built on by (most cited first, 12 of 12)

- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking](https://mlsanity.com/paper/2106.08816/) (2021)
- [All-Day Object Tracking for Unmanned Aerial Vehicle](https://mlsanity.com/paper/2101.08446/) (2021)
- [Towards Real-World Visual Tracking with Temporal Contexts](https://mlsanity.com/paper/2308.10330/) (2023)
- [Deep Graph Reprogramming](https://mlsanity.com/paper/2304.14593/) (2023)
- [ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking](https://mlsanity.com/paper/2106.02495/) (2021)
- [Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking](https://mlsanity.com/paper/2104.03114/) (2021)
- [Mutation Sensitive Correlation Filter for Real-Time UAV Tracking with Adaptive Hybrid Label](https://mlsanity.com/paper/2106.08073/) (2021)
- [Unsupervised Online Learning for Robotic Interestingness with Visual Memory](https://mlsanity.com/paper/2111.09793/) (2021)
- [Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform](https://mlsanity.com/paper/2211.03635/) (2022)
- [Low-Light Object Tracking: A Benchmark](https://mlsanity.com/paper/2408.11463/) (2024)
- [A Framework for Analyzing Cross-correlators using Price's Theorem and Piecewise-Linear Decomposition](https://mlsanity.com/paper/2304.09242/) (2023)

## Abstract (arXiv)

Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking. Beyond the linear cross-correlator, this paper proposes a kernel cross-correlator (KCC) that breaks traditional limitations. First, by introducing the kernel trick, the KCC extends the linear cross-correlation to non-linear space, which is more robust to signal noises and distortions. Second, the connection to the existing works shows that KCC provides a unified solution for correlation filters. Third, KCC is applicable to any kernel function and is not limited to circulant structure on training data, thus it is able to predict affine transformations with customized properties. Last, by leveraging the fast Fourier transform (FFT), KCC eliminates direct calculation of kernel vectors, thus achieves better performance yet still with a reasonable computational cost. Comprehensive experiments on visual tracking and human activity recognition using wearable devices demonstrate its robustness, flexibility, and efficiency. The source codes of both experiments are released at https://github.com/wang-chen/KCC