Hybrid Multimodal Fusion for Humor Detection

TL;DR

This paper introduces a hybrid multimodal fusion approach combining transformer and BiLSTM models to improve humor detection in audiovisual recordings of football press conferences, achieving high accuracy.

Contribution

The paper proposes a novel hybrid fusion strategy for multimodal data that enhances humor detection performance over existing methods.

Findings

Achieved an AUC of 0.8972 on the test set.

Demonstrated the effectiveness of hybrid fusion in multimodal humor detection.

Validated the approach on real-world audiovisual data.

Abstract

In this paper, we present our solution to the MuSe-Humor sub-challenge of the Multimodal Emotional Challenge (MuSe) 2022. The goal of the MuSe-Humor sub-challenge is to detect humor and calculate AUC from audiovisual recordings of German football Bundesliga press conferences. It is annotated for humor displayed by the coaches. For this sub-challenge, we first build a discriminant model using the transformer module and BiLSTM module, and then propose a hybrid fusion strategy to use the prediction results of each modality to improve the performance of the model. Our experiments demonstrate the effectiveness of our proposed model and hybrid fusion strategy on multimodal fusion, and the AUC of our proposed model on the test set is 0.8972.