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

The saliency ranking task is recently proposed to study the visual behaviorthat humans would typically shift their attention over different objects of ascene based on their degrees of saliency. Existing approaches focus on learningeither object-object or object-scene relations. Such a strategy follows theidea of object-based attention in Psychology, but it tends to favor thoseobjects with strong semantics (e.g., humans), resulting in unrealistic saliencyranking. We observe that spatial attention works concurrently with object-basedattention in the human visual recognition system. During the recognitionprocess, the human spatial attention mechanism would move, engage, anddisengage from region to region (i.e., context to context). This inspires us tomodel the region-level interactions, in addition to the object-level reasoning,for saliency ranking. To this end, we propose a novel bi-directional method tounify spatial attention and object-based attention for saliency ranking. Ourmodel includes two novel modules: (1) a selective object saliency (SOS) modulethat models objectbased attention via inferring the semantic representation ofthe salient object, and (2) an object-context-object relation (OCOR) modulethat allocates saliency ranks to objects by jointly modeling the object-contextand context-object interactions of the salient objects. Extensive experimentsshow that our approach outperforms existing state-of-theart methods. Our codeand pretrained model are available at https://github.com/GrassBro/OCOR.

Bi-directional Object-context Prioritization Learning for Saliency Ranking