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

Human emotions involve basic and compound facial expressions. However,current research on facial expression recognition (FER) mainly focuses on basicexpressions, and thus fails to address the diversity of human emotions inpractical scenarios. Meanwhile, existing work on compound FER relies heavily onabundant labeled compound expression training data, which are often laboriouslycollected under the professional instruction of psychology. In this paper, westudy compound FER in the cross-domain few-shot learning setting, where only afew images of novel classes from the target domain are required as a reference.In particular, we aim to identify unseen compound expressions with the modeltrained on easily accessible basic expression datasets. To alleviate theproblem of limited base classes in our FER task, we propose a novel EmotionGuided Similarity Network (EGS-Net), consisting of an emotion branch and asimilarity branch, based on a two-stage learning framework. Specifically, inthe first stage, the similarity branch is jointly trained with the emotionbranch in a multi-task fashion. With the regularization of the emotion branch,we prevent the similarity branch from overfitting to sampled base classes thatare highly overlapped across different episodes. In the second stage, theemotion branch and the similarity branch play a "two-student game" toalternately learn from each other, thereby further improving the inferenceability of the similarity branch on unseen compound expressions. Experimentalresults on both in-the-lab and in-the-wild compound expression datasetsdemonstrate the superiority of our proposed method against severalstate-of-the-art methods.

When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework