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 clustering (MVC) aims to reveal the underlying structure ofmultiview data by categorizing data samples into clusters. Deep learning-basedmethods exhibit strong feature learning capabilities on large-scale datasets.For most existing deep MVC methods, exploring the invariant representations ofmultiple views is still an intractable problem. In this paper, we propose across-view contrastive learning (CVCL) method that learns view-invariantrepresentations and produces clustering results by contrasting the clusterassignments among multiple views. Specifically, we first employ deepautoencoders to extract view-dependent features in the pretraining stage. Then,a cluster-level CVCL strategy is presented to explore consistent semantic labelinformation among the multiple views in the fine-tuning stage. Thus, theproposed CVCL method is able to produce more discriminative cluster assignmentsby virtue of this learning strategy. Moreover, we provide a theoreticalanalysis of soft cluster assignment alignment. Extensive experimental resultsobtained on several datasets demonstrate that the proposed CVCL methodoutperforms several state-of-the-art approaches.

Deep Multiview Clustering by Contrasting Cluster Assignments