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 recent progress in artificial intelligence has led to an ever-increasingusage of images and videos by machine analysis algorithms, mainly neuralnetworks. Nonetheless, compression, storage and transmission of media havetraditionally been designed considering human beings as the viewers of thecontent. Recent research on image and video coding for machine analysis hasprogressed mainly in two almost orthogonal directions. The first is representedby end-to-end (E2E) learned codecs which, while offering high performance onimage coding, are not yet on par with state-of-the-art conventional videocodecs and lack interoperability. The second direction considers using theVersatile Video Coding (VVC) standard or any other conventional video codec(CVC) together with pre- and post-processing operations targeting machineanalysis. While the CVC-based methods benefit from interoperability and broadhardware and software support, the machine task performance is often lower thanthe desired level, particularly in low bitrates. This paper proposes a hybridcodec for machines called NN-VVC, which combines the advantages of anE2E-learned image codec and a CVC to achieve high performance in both image andvideo coding for machines. Our experiments show that the proposed systemachieved up to -43.20% and -26.8% Bj{\o}ntegaard Delta rate reduction over VVCfor image and video data, respectively, when evaluated on multiple differentdatasets and machine vision tasks. To the best of our knowledge, this is thefirst research paper showing a hybrid video codec that outperforms VVC onmultiple datasets and multiple machine vision tasks.

NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines