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

We propose a lossy image compression system using the deep-learningautoencoder structure to participate in the Challenge on Learned ImageCompression (CLIC) 2018. Our autoencoder uses the residual blocks with skipconnections to reduce the correlation among image pixels and condense the inputimage into a set of feature maps, a compact representation of the originalimage. The bit allocation and bitrate control are implemented by using theimportance maps and quantizer. The importance maps are generated by a separateneural net in the encoder. The autoencoder and the importance net are trainedjointly based on minimizing a weighted sum of mean squared error, MS-SSIM, anda rate estimate. Our aim is to produce reconstructed images with goodsubjective quality subject to the 0.15 bits-per-pixel constraint.

An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU