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

Multimodal analysis has recently drawn much interest in affective computing,since it can improve the overall accuracy of emotion recognition over isolateduni-modal approaches. The most effective techniques for multimodal emotionrecognition efficiently leverage diverse and complimentary sources ofinformation, such as facial, vocal, and physiological modalities, to providecomprehensive feature representations. In this paper, we focus on dimensionalemotion recognition based on the fusion of facial and vocal modalitiesextracted from videos, where complex spatiotemporal relationships may becaptured. Most of the existing fusion techniques rely on recurrent networks orconventional attention mechanisms that do not effectively leverage thecomplimentary nature of audio-visual (A-V) modalities. We introduce across-attentional fusion approach to extract the salient features across A-Vmodalities, allowing for accurate prediction of continuous values of valenceand arousal. Our new cross-attentional A-V fusion model efficiently leveragesthe inter-modal relationships. In particular, it computes cross-attentionweights to focus on the more contributive features across individualmodalities, and thereby combine contributive feature representations, which arethen fed to fully connected layers for the prediction of valence and arousal.The effectiveness of the proposed approach is validated experimentally onvideos from the RECOLA and Fatigue (private) data-sets. Results indicate thatour cross-attentional A-V fusion model is a cost-effective approach thatoutperforms state-of-the-art fusion approaches. Code is available:\url{https://github.com/praveena2j/Cross-Attentional-AV-Fusion}

Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition