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

Depth information has been proved beneficial in RGB-D salient objectdetection (SOD). However, depth maps obtained often suffer from low quality andinaccuracy. Most existing RGB-D SOD models have no cross-modal interactions oronly have unidirectional interactions from depth to RGB in their encoderstages, which may lead to inaccurate encoder features when facing low qualitydepth. To address this limitation, we propose to conduct progressivebi-directional interactions as early in the encoder stage, yielding a novelbi-directional transfer-and-selection network named BTS-Net, which adopts a setof bi-directional transfer-and-selection (BTS) modules to purify featuresduring encoding. Based on the resulting robust encoder features, we also designan effective light-weight group decoder to achieve accurate final saliencyprediction. Comprehensive experiments on six widely used datasets demonstratethat BTS-Net surpasses 16 latest state-of-the-art approaches in terms of fourkey metrics.

BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection