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 is a commercially-important application, butone under-appreciated limitation is that such applications require makingpredictions on out-of-sample distributions, where target images have differentproperties from the images the model was trained on. How well -- or how badly-- do facial expression recognition models do on unseen target domains? Weprovide a systematic and critical evaluation of transfer learning --specifically, domain generalization -- in facial expression recognition. Usinga state-of-the-art model with twelve datasets (six collected in-lab and six``in-the-wild"), we conduct extensive round-robin-style experiments to evaluateclassification accuracies when given new data from an unseen dataset. We alsoperform multi-source experiments to examine a model's ability to generalizefrom multiple source datasets, including (i) within-setting (e.g., lab to lab),(ii) cross-setting (e.g., in-the-wild to lab), and (iii) leave-one-outsettings. Finally, we compare our results with three commercially-availablesoftware. We find sobering results: the accuracy of single- and multi-sourcedomain generalization is only modest. Even for the best-performing multi-sourcesettings, we observe average classification accuracies of 65.6% (range:34.6%-88.6%; chance: 14.3%), corresponding to an average drop of 10.8percentage points from the within-corpus classification performance (mean:76.4%). We discuss the need for regular, systematic investigations into thegeneralizability of affective computing models and applications.

Critically examining the Domain Generalizability of Facial Expression Recognition models