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

The lack of data and the difficulty of multimodal fusion have always beenchallenges for multimodal emotion recognition (MER). In this paper, we proposeto use pretrained models as upstream network, wav2vec 2.0 for audio modalityand BERT for text modality, and finetune them in downstream task of MER to copewith the lack of data. For the difficulty of multimodal fusion, we use aK-layer multi-head attention mechanism as a downstream fusion module. Startingfrom the MER task itself, we design two auxiliary tasks to alleviate theinsufficient fusion between modalities and guide the network to capture andalign emotion-related features. Compared to the previous state-of-the-artmodels, we achieve a better performance by 78.42% Weighted Accuracy (WA) and79.71% Unweighted Accuracy (UA) on the IEMOCAP dataset.

Using Auxiliary Tasks In Multimodal Fusion Of Wav2vec 2.0 And BERT For Multimodal Emotion Recognition