Multi-kernel Correlation Filter for Visual Tracking

Tang, Ming; Feng, Jiayi

doi:10.1109/iccv.2015.348

Cited by 144 publications

(94 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, spatial-temporal context [86] and kernel tricks [27] are used to improve the learning formulation with the consideration of local appearance and nonlinear metric, respectively. The DCF paradigm has further been extended by exploiting scale detection [41,14,16], structural patch analysis [42,46,45], multi-clue fusion [71,50,28,4,72], sparse representation [88,90], support vector machine [75,92], enhanced sampling mechanisms [89,54] and end-to-end deep neural networks [73,67].…”

Section: Related Workmentioning

confidence: 99%

Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking

Feng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

196

118

View full text Add to dashboard Cite

We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking. The key innovation of the proposed method is to perform group feature selection across both channel and spatial dimensions, thus to pinpoint the structural relevance of multi-channel features to the filtering system. In contrast to the widely used spatial regularisation or feature selection methods, to the best of our knowledge, this is the first time that channel selection has been advocated for DCF-based tracking. We demonstrate that our GFS-DCF method is able to significantly improve the performance of a DCF tracker equipped with deep neural network features. In addition, our GFS-DCF enables joint feature selection and filter learning, achieving enhanced discrimination and interpretability of the learned filters.To further improve the performance, we adaptively integrate historical information by constraining filters to be smooth across temporal frames, using an efficient lowrank approximation. By design, specific temporal-spatialchannel configurations are dynamically learned in the tracking process, highlighting the relevant features, and alleviating the performance degrading impact of less discriminative representations and reducing information redundancy. The experimental results obtained on OTB2013, OTB2015, VOT2017, VOT2018 and TrackingNet demonstrate the merits of our GFS-DCF and its superiority over the state-of-the-art trackers. The code is publicly available at https://github.com/XU-TIANYANG/ GFS-DCF.

show abstract

Section: Related Workmentioning

confidence: 99%

Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking

Feng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

196

118

View full text Add to dashboard Cite

show abstract

“…Then KSR algorithm is integrated into particle filter framework. Tang and Feng [60] proposed multi-kernel correlation filter(MKCF) based tracker that incorporates both strengths of multiple channels and multiple kernels.…”

Section: Kernel Based Trackingmentioning

confidence: 99%

A Review of Object Detection and Tracking Methods

2017

IJAERD

View full text Add to dashboard Cite

“…MKCF [37] extends the correlation filter based tracker to the multiple kernel version. For suppressing the unwanted boundary effects, SRDCF [38] introduces a spatial regularization component in the learning to penalize correlation filter coefficients depending on their spatial location.…”

Section: Introductionmentioning

confidence: 99%