For visual tracking methods based on kernel support vector machines (SVMs), data sampling is usually adopted to reduce the computational cost in training. In addition …
D Yuan, N Fan, Z He - Knowledge-Based Systems, 2020 - Elsevier
Discriminative correlation filters (DCFs) have been widely used in the tracking community recently. DCFs-based trackers utilize samples generated by circularly shifting from an image …
Correlation filters (CFs) have been extensively used in tracking tasks due to their high efficiency although most of them regard the tracked target as a whole and are minimally …
B Huang, T Xu, S Jiang, Y Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Discriminative Correlation Filter (DCF) based trackers are quite efficient in tracking objects by exploiting the circulant structure. The kernel trick further improves the performance of …
J Zhang, Y Liu, H Liu, J Wang, Y Zhang - Applied Intelligence, 2022 - Springer
In recent years, the ensembled trackers composed of multi-level features from the pre- trained Convolutional Neural Network (CNN) have achieved top performance in visual …
D Yuan, X Zhang, J Liu, D Li - Multimedia Tools and Applications, 2019 - Springer
Common tracking algorithms only use a single feature to describe the target appearance, which makes the appearance model easily disturbed by noise. Furthermore, the tracking …
K Dai, D Wang, H Lu, C Sun… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
In this work, we propose a novel adaptive spatially-regularized correlation filters (ASRCF) model to simultaneously optimize the filter coefficients and the spatial regularization weight …
E Gundogdu, AA Alatan - IEEE Transactions on Image …, 2018 - ieeexplore.ieee.org
During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in this family of trackers …
Z Chen, Z Hong, D Tao - arXiv preprint arXiv:1509.05520, 2015 - arxiv.org
Over these years, Correlation Filter-based Trackers (CFTs) have aroused increasing interests in the field of visual object tracking, and have achieved extremely compelling …