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

This paper presents a holistic approach to saliency-guided visual attentionmodeling (SVAM) for use by autonomous underwater robots. Our proposed model,named SVAM-Net, integrates deep visual features at various scales and semanticsfor effective salient object detection (SOD) in natural underwater images. TheSVAM-Net architecture is configured in a unique way to jointly accommodatebottom-up and top-down learning within two separate branches of the networkwhile sharing the same encoding layers. We design dedicated spatial attentionmodules (SAMs) along these learning pathways to exploit the coarse-level andfine-level semantic features for SOD at four stages of abstractions. Thebottom-up branch performs a rough yet reasonably accurate saliency estimationat a fast rate, whereas the deeper top-down branch incorporates a residualrefinement module (RRM) that provides fine-grained localization of the salientobjects. Extensive performance evaluation of SVAM-Net on benchmark datasetsclearly demonstrates its effectiveness for underwater SOD. We also validate itsgeneralization performance by several ocean trials' data that include testimages of diverse underwater scenes and waterbodies, and also images withunseen natural objects. Moreover, we analyze its computational feasibility forrobotic deployments and demonstrate its utility in several important use casesof visual attention modeling.

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots