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

Video-to-video translation aims to generate video frames of a target domainfrom an input video. Despite its usefulness, the existing networks requireenormous computations, necessitating their model compression for wide use.While there exist compression methods that improve computational efficiency invarious image/video tasks, a generally-applicable compression method forvideo-to-video translation has not been studied much. In response, we presentShortcut-V2V, a general-purpose compression framework for video-to-videotranslation. Shourcut-V2V avoids full inference for every neighboring videoframe by approximating the intermediate features of a current frame from thoseof the previous frame. Moreover, in our framework, a newly-proposed blockcalled AdaBD adaptively blends and deforms features of neighboring frames,which makes more accurate predictions of the intermediate features possible. Weconduct quantitative and qualitative evaluations using well-knownvideo-to-video translation models on various tasks to demonstrate the generalapplicability of our framework. The results show that Shourcut-V2V achievescomparable performance compared to the original video-to-video translationmodel while saving 3.2-5.7x computational cost and 7.8-44x memory at test time.

Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction