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 paper, we consider the problem of multimodal data analysis with a usecase of audiovisual emotion recognition. We propose an architecture capable oflearning from raw data and describe three variants of it with distinct modalityfusion mechanisms. While most of the previous works consider the ideal scenarioof presence of both modalities at all times during inference, we evaluate therobustness of the model in the unconstrained settings where one modality isabsent or noisy, and propose a method to mitigate these limitations in a formof modality dropout. Most importantly, we find that following this approach notonly improves performance drastically under the absence/noisy representationsof one modality, but also improves the performance in a standard ideal setting,outperforming the competing methods.

Self-attention fusion for audiovisual emotion recognition with incomplete data