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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep unfolded neural networks are designed by unrolling the iterations ofoptimization algorithms. They can be shown to achieve faster convergence andhigher accuracy than their optimization counterparts. This paper proposes a newdeep-unfolding-based network design for the problem of Robust PrincipalComponent Analysis (RPCA) with application to video foreground-backgroundseparation. Unlike existing designs, our approach focuses on modeling thetemporal correlation between the sparse representations of consecutive videoframes. To this end, we perform the unfolding of an iterative algorithm forsolving reweighted $\ell_1$-$\ell_1$ minimization; this unfolding leads to adifferent proximal operator (a.k.a. different activation function) adaptivelylearned per neuron. Experimentation using the moving MNIST dataset shows thatthe proposed network outperforms a recently proposed state-of-the-art RPCAnetwork in the task of video foreground-background separation.

A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation