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

TL;DR

This paper introduces a zero-shot method for recognizing complex facial compound expressions in-the-wild by combining pretrained visual language models with CNNs, addressing dataset limitations.

Contribution

It presents a novel zero-shot recognition approach for compound expressions using visual language models integrated with CNNs, suitable for limited data scenarios.

Findings

Effective recognition of compound expressions in-the-wild

Utilizes pretrained visual language models for zero-shot learning

Addresses data scarcity in facial expression recognition

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 pretrained visual language model integrated with some traditional CNN networks.