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

Occlusion relationship reasoning demands closed contour to express theobject, and orientation of each contour pixel to describe the orderrelationship between objects. Current CNN-based methods neglect two criticalissues of the task: (1) simultaneous existence of the relevance and distinctionfor the two elements, i.e, occlusion edge and occlusion orientation; and (2)inadequate exploration to the orientation features. For the reasons above, wepropose the Occlusion-shared and Feature-separated Network (OFNet). On onehand, considering the relevance between edge and orientation, two sub-networksare designed to share the occlusion cue. On the other hand, the whole networkis split into two paths to learn the high-level semantic features separately.Moreover, a contextual feature for orientation prediction is extracted, whichrepresents the bilateral cue of the foreground and background areas. Thebilateral cue is then fused with the occlusion cue to precisely locate theobject regions. Finally, a stripe convolution is designed to further aggregatefeatures from surrounding scenes of the occlusion edge. The proposed OFNetremarkably advances the state-of-the-art approaches on PIOD and BSDS ownershipdataset. The source code is available at https://github.com/buptlr/OFNet.

Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning