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

Multiview recognition has been well studied in the literature and achievesdecent performance in object recognition and retrieval task. However, mostprevious works rely on supervised learning and some impractical underlyingassumptions, such as the availability of all views in training and inferencetime. In this work, the problem of multiview self-supervised learning (MV-SSL)is investigated, where only image to object association is given. Given thissetup, a novel surrogate task for self-supervised learning is proposed bypursuing "object invariant" representation. This is solved by randomlyselecting an image feature of an object as object prototype, accompanied withmultiview consistency regularization, which results in view invariantstochastic prototype embedding (VISPE). Experiments shows that the recognitionand retrieval results using VISPE outperform that of other self-supervisedlearning methods on seen and unseen data. VISPE can also be applied tosemi-supervised scenario and demonstrates robust performance with limited dataavailable. Code is available at https://github.com/chihhuiho/VISPE

Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition