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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Contrastive learning applied to self-supervised representation learning hasseen a resurgence in deep models. In this paper, we find that existingcontrastive learning based solutions for self-supervised video recognitionfocus on inter-variance encoding but ignore the intra-variance existing inclips within the same video. We thus propose to learn dual representations foreach clip which (\romannumeral 1) encode intra-variance through a shuffle-rankpretext task; (\romannumeral 2) encode inter-variance through a temporalcoherent contrastive loss. Experiment results show that our method plays anessential role in balancing inter and intra variances and brings consistentperformance gains on multiple backbones and contrastive learning frameworks.Integrated with SimCLR and pretrained on Kinetics-400, our method achieves$\textbf{82.0\%}$ and $\textbf{51.2\%}$ downstream classification accuracy onUCF101 and HMDB51 test sets respectively and $\textbf{46.1\%}$ video retrievalaccuracy on UCF101, outperforming both pretext-task based and contrastivelearning based counterparts. Our code is available at\href{https://github.com/lzhangbj/DualVar}{https://github.com/lzhangbj/DualVar}.

Inter-intra Variant Dual Representations forSelf-supervised Video Recognition