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

Multi-modal affect recognition models leverage complementary information indifferent modalities to outperform their uni-modal counterparts. However, dueto the unavailability of modality-specific sensors or data, multi-modal modelsmay not be always employable. For this reason, we aim to improve theperformance of uni-modal affect recognition models by transferring knowledgefrom a better-performing (or stronger) modality to a weaker modality duringtraining. Our proposed multi-modal training framework for cross-modal knowledgetransfer relies on two main steps. First, an encoder-classifier model createstask-specific representations for the stronger modality. Then, cross-modaltranslation generates multi-modal intermediate representations, which are alsoaligned in the latent space with the stronger modality representations. Toexploit the contextual information in temporal sequential affect data, we useBi-GRU and transformer encoder. We validate our approach on two multi-modalaffect datasets, namely CMU-MOSI for binary sentiment classification and RECOLAfor dimensional emotion regression. The results show that the proposed approachconsistently improves the uni-modal test-time performance of the weakermodalities.

Cross-Modal Knowledge Transfer via Inter-Modal Translation and Alignment for Affect Recognition