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

Video Salient Document Detection (VSDD) is an essential task of practicalcomputer vision, which aims to highlight visually salient document regions invideo frames. Previous techniques for VSDD focus on learning features withoutconsidering the cooperation among and across the appearance and motion cues andthus fail to perform in practical scenarios. Moreover, most of the previoustechniques demand high computational resources, which limits the usage of suchsystems in resource-constrained settings. To handle these issues, we proposeVS-Net, which captures multi-scale spatiotemporal information with the help ofdilated depth-wise separable convolution and Approximation Rank Pooling. VS-Netextracts the key features locally from each frame across embedding sub-spacesand forwards the features between adjacent and parallel nodes, enhancing modelperformance globally. Our model generates saliency maps considering both thebackground and foreground simultaneously, making it perform better inchallenging scenarios. The immense experiments regulated on the benchmarkMIDV-500 dataset show that the VS-Net model outperforms state-of-the-artapproaches in both time and robustness measures.

VS-Net: Multiscale Spatiotemporal Features for Lightweight Video Salient Document Detection