Audio-Visual Compound Expression Recognition Method based on Late Modality Fusion and Rule-based Decision

arXiv:2403.12687v1 Announce Type: cross
Abstract: This paper presents the results of the SUN team for the Compound Expressions Recognition Challenge of the 6th ABAW Competition. We propose a novel audio-visual method for compound expression recognition. Our method relies on emotion recognition models that fuse modalities at the emotion probability level, while decisions regarding the prediction of compound expressions are based on predefined rules. Notably, our method does not use any training data specific to the target task. The method is …

abstract arxiv audio challenge competition cs.cv cs.lg decision emotion fusion novel paper recognition results team type visual