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

In this work, we address the problem of learning an ensemble of specialistnetworks using multimodal data, while considering the realistic and challengingscenario of possible missing modalities at test time. Our goal is to leveragethe complementary information of multiple modalities to the benefit of theensemble and each individual network. We introduce a novel DistillationMultiple Choice Learning framework for multimodal data, where differentmodality networks learn in a cooperative setting from scratch, strengtheningone another. The modality networks learned using our method achievesignificantly higher accuracy than if trained separately, due to the guidanceof other modalities. We evaluate this approach on three video actionrecognition benchmark datasets. We obtain state-of-the-art results incomparison to other approaches that work with missing modalities at test time.

DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition