Most of the correlation filter-based trackers learn a 1D correlation filter for scale search. The
scale searching space of 1D scale filter is discrete, which results in high computation …

Tracking with kernelized correlation filters (KCF) is an excellent object tracking algorithm,
which is widely concerned. In KCF, each candidate patch in tracked region corresponds to a …

There has been an increasing interest in the use of correlation filters for visual object
tracking due to their impressive tracking performance. However, existing correlation filter …

The correlation filters tracker allows features from multiple channels. The fusion of features
by simply summing over them in an Euclidean space would destroy the inherent geometry …

Recently, object tracking model based on correlation filter has achieved great success.
However, most of these methods relying on correlation filter train many classifiers …

Correlation filters tracking algorithm, one of the famous tracking algorithm, has been widely
explored in visual tracking domain because of its high accuracy. In this work, we proposed a …

During the tracking, kernelized correlation filters cannot handle this situation well when the
target occluded seriously, changes scale and goes out of view. To solve the above problem …

Adaptive kernelized correlation Filter (AKCF) approach is designed to achieve an accurate
and stable tracking for the moving target with fast motion and background clutter. The …

Unlike deep learning which requires large training datasets, correlation filter-based trackers
like Kernelized Correlation Filter (KCF) uses implicit properties of tracked images (circulant …

To solve the problem that Circulant Structure of tracking-by-detection with Kernels (CSK) is
difficult to adapt to the target scale change, a multi-scale kernel correlation filter classifier …