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

The Object-Based Image Coding (OBIC) that was extensively studied about twodecades ago, promised a vast application perspective for both ultra-low bitratecommunication and high-level semantical content understanding, but it hadrarely been used due to the inefficient compact representation of object witharbitrary shape. A fundamental issue behind is how to efficiently process thearbitrary-shaped objects at a fine granularity (e.g., feature element or pixelwise). To attack this, we have proposed to apply the element-wise masking andcompression by devising an object segmentation network for image layerdecomposition, and parallel convolution-based neural image compression networksto process masked foreground objects and background scene separately. Allcomponents are optimized in an end-to-end learning framework to intelligentlyweigh their (e.g., object and background) contributions for visually pleasantreconstruction. We have conducted comprehensive experiments to evaluate theperformance on PASCAL VOC dataset at a very low bitrate scenario (e.g.,$\lesssim$0.1 bits per pixel - bpp) which have demonstrated noticeablesubjective quality improvement compared with JPEG2K, HEVC-based BPG and anotherlearned image compression method. All relevant materials are made publiclyaccessible at https://njuvision.github.io/Neural-Object-Coding/.

Object-Based Image Coding: A Learning-Driven Revisit