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

Facial Expression Recognition (FER) is a crucial task in affective computing,but its conventional focus on the seven basic emotions limits its applicabilityto the complex and expanding emotional spectrum. To address the issue of newand unseen emotions present in dynamic in-the-wild FER, we propose a novelvision-language model that utilises sample-level text descriptions (i.e.captions of the context, expressions or emotional cues) as natural languagesupervision, aiming to enhance the learning of rich latent representations, forzero-shot classification. To test this, we evaluate using zero-shotclassification of the model trained on sample-level descriptions on fourpopular dynamic FER datasets. Our findings show that this approach yieldssignificant improvements when compared to baseline methods. Specifically, forzero-shot video FER, we outperform CLIP by over 10\% in terms of WeightedAverage Recall and 5\% in terms of Unweighted Average Recall on severaldatasets. Furthermore, we evaluate the representations obtained from thenetwork trained using sample-level descriptions on the downstream task ofmental health symptom estimation, achieving performance comparable or superiorto state-of-the-art methods and strong agreement with human experts. Namely, weachieve a Pearson's Correlation Coefficient of up to 0.85 on schizophreniasymptom severity estimation, which is comparable to human experts' agreement.The code is publicly available at: https://github.com/NickyFot/EmoCLIP.

EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition