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/

Zendy Plus

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

Zendy Tools

Zendy Open

Most existing compound facial expression recognition (FER) methods rely onlarge-scale labeled compound expression data for training. However, collectingsuch data is labor-intensive and time-consuming. In this paper, we address thecompound FER task in the cross-domain few-shot learning (FSL) setting, whichrequires only a few samples of compound expressions in the target domain.Specifically, we propose a novel cascaded decomposition network (CDNet), whichcascades several learn-to-decompose modules with shared parameters based on asequential decomposition mechanism, to obtain a transferable feature space. Toalleviate the overfitting problem caused by limited base classes in our task, apartial regularization strategy is designed to effectively exploit the best ofboth episodic training and batch training. By training across similar tasks onmultiple basic expression datasets, CDNet learns the ability oflearn-to-decompose that can be easily adapted to identify unseen compoundexpressions. Extensive experiments on both in-the-lab and in-the-wild compoundexpression datasets demonstrate the superiority of our proposed CDNet againstseveral state-of-the-art FSL methods. Code is available at:https://github.com/zouxinyi0625/CDNet.

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition