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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

With efficient appearance learning models, Discriminative Correlation Filter(DCF) has been proven to be very successful in recent video object trackingbenchmarks and competitions. However, the existing DCF paradigm suffers fromtwo major issues, i.e., spatial boundary effect and temporal filterdegradation. To mitigate these challenges, we propose a new DCF-based trackingmethod. The key innovations of the proposed method include adaptive spatialfeature selection and temporal consistent constraints, with which the newtracker enables joint spatial-temporal filter learning in a lower dimensionaldiscriminative manifold. More specifically, we apply structured spatialsparsity constraints to multi-channel filers. Consequently, the process oflearning spatial filters can be approximated by the lasso regularisation. Toencourage temporal consistency, the filter model is restricted to lie aroundits historical value and updated locally to preserve the global structure inthe manifold. Last, a unified optimisation framework is proposed to jointlyselect temporal consistency preserving spatial features and learndiscriminative filters with the augmented Lagrangian method. Qualitative andquantitative evaluations have been conducted on a number of well-knownbenchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123 andVOT2018. The experimental results demonstrate the superiority of the proposedmethod over the state-of-the-art approaches.

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking