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

Multi-view clustering (MVC) can explore common semantics from unsupervisedviews generated by different sources, and thus has been extensively used inapplications of practical computer vision. Due to the spatio-temporalasynchronism, multi-view data often suffer from view missing and are unalignedin real-world applications, which makes it difficult to learn consistentrepresentations. To address the above issues, this work proposes a deep MVCframework where data recovery and alignment are fused in a hierarchicallyconsistent way to maximize the mutual information among different views andensure the consistency of their latent spaces. More specifically, we firstleverage dual prediction to fill in missing views while achieving theinstance-level alignment, and then take the contrastive reconstruction toachieve the class-level alignment. To the best of our knowledge, this could bethe first successful attempt to handle the missing and unaligned data problemseparately with different learning paradigms. Extensive experiments on publicdatasets demonstrate that our method significantly outperforms state-of-the-artmethods on multi-view clustering even in the cases of view missing andunalignment.

Hierarchical Mutual Information Analysis: Towards Multi-view Clustering in The Wild