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

Co-saliency detection aims to detect common salient objects from a group ofrelevant images. Some attempts have been made with the Fully ConvolutionalNetwork (FCN) framework and achieve satisfactory detection results. However,due to stacking convolution layers and pooling operation, the boundary detailstend to be lost. In addition, existing models often utilize the extractedfeatures without discrimination, leading to redundancy in representation sinceactually not all features are helpful to the final prediction and some evenbring distraction. In this paper, we propose a co-attention module embedded FCNframework, called as Co-Attention FCN (CA-FCN). Specifically, the co-attentionmodule is plugged into the high-level convolution layers of FCN, which canassign larger attention weights on the common salient objects and smaller oneson the background and uncommon distractors to boost final detectionperformance. Extensive experiments on three popular co-saliency benchmarkdatasets demonstrate the superiority of the proposed CA-FCN, which outperformsstate-of-the-arts in most cases. Besides, the effectiveness of our newco-attention module is also validated with ablation studies.

Co-Saliency Detection with Co-Attention Fully Convolutional Network