English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Discriminative Correlation Filters (DCF) are efficient in visual tracking butsuffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) hasbeen suggested to resolve this issue by enforcing spatial penalty on DCFcoefficients, which, inevitably, improves the tracking performance at the priceof increasing complexity. To tackle online updating, SRDCF formulates its modelon multiple training images, further adding difficulties in improvingefficiency. In this work, by introducing temporal regularization to SRDCF withsingle sample, we present our spatial-temporal regularized correlation filters(STRCF). Motivated by online Passive-Agressive (PA) algorithm, we introduce thetemporal regularization to SRDCF with single sample, thus resulting in ourspatial-temporal regularized correlation filters (STRCF). The STRCF formulationcan not only serve as a reasonable approximation to SRDCF with multipletraining samples, but also provide a more robust appearance model than SRDCF inthe case of large appearance variations. Besides, it can be efficiently solvedvia the alternating direction method of multipliers (ADMM). By incorporatingboth temporal and spatial regularization, our STRCF can handle boundary effectswithout much loss in efficiency and achieve superior performance over SRDCF interms of accuracy and speed. Experiments are conducted on three benchmarkdatasets: OTB-2015, Temple-Color, and VOT-2016. Compared with SRDCF, STRCF withhand-crafted features provides a 5 times speedup and achieves a gain of 5.4%and 3.6% AUC score on OTB-2015 and Temple-Color, respectively. Moreover, STRCFcombined with CNN features also performs favorably against state-of-the-artCNN-based trackers and achieves an AUC score of 68.3% on OTB-2015.

Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking