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

We introduce ReConvNet, a recurrent convolutional architecture forsemi-supervised video object segmentation that is able to fast adapt itsfeatures to focus on any specific object of interest at inference time.Generalization to new objects never observed during training is known to be ahard task for supervised approaches that would need to be retrained. To tacklethis problem, we propose a more efficient solution that learns spatio-temporalfeatures self-adapting to the object of interest via conditional affinetransformations. This approach is simple, can be trained end-to-end and doesnot necessarily require extra training steps at inference time. Our methodshows competitive results on DAVIS2016 with respect to state-of-the artapproaches that use online fine-tuning, and outperforms them on DAVIS2017.ReConvNet shows also promising results on the DAVIS-Challenge 2018 winning the$10$-th position.

ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation