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

Existing unsupervised video-to-video translation methods fail to producetranslated videos which are frame-wise realistic, semantic informationpreserving and video-level consistent. In this work, we propose UVIT, a novelunsupervised video-to-video translation model. Our model decomposes the styleand the content, uses the specialized encoder-decoder structure and propagatesthe inter-frame information through bidirectional recurrent neural network(RNN) units. The style-content decomposition mechanism enables us to achievestyle consistent video translation results as well as provides us with a goodinterface for modality flexible translation. In addition, by changing the inputframes and style codes incorporated in our translation, we propose a videointerpolation loss, which captures temporal information within the sequence totrain our building blocks in a self-supervised manner. Our model can producephoto-realistic, spatio-temporal consistent translated videos in a multimodalway. Subjective and objective experimental results validate the superiority ofour model over existing methods. More details can be found on our projectwebsite: https://uvit.netlify.com

Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning