Zero-shot Compound Expression Recognition with Visual Language Model at the 6th ABAW Challenge

arXiv:2403.11450v1 Announce Type: new
Abstract: Conventional approaches to facial expression recognition primarily focus on the classification of six basic facial expressions. Nevertheless, real-world situations present a wider range of complex compound expressions that consist of combinations of these basics ones due to limited availability of comprehensive training datasets. The 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW) offered unlabeled datasets containing compound expressions. In this study, we propose a zero-shot approach for recognizing compound expressions by leveraging a …

abstract arxiv availability basic basics challenge classification cs.cv focus language language model recognition six training type visual visual language model world zero-shot