Husformer: A Multimodal Transformer for Multimodal Human State Recognition

Human state recognition is a critical topic with pervasive and important applications in human-machine systems. Multi-modal fusion, which entails integrating metrics from various data sources, has proven to be a potent method for boosting recognition performance. Although recent multi-modal-based models have shown promising results, they often fall short in fully leveraging sophisticated fusion strategies essential for modeling adequate cross-modal dependencies in the fusion representation. Instead, they rely on costly and inconsistent feature crafting and alignment. To address this limitation, we propose an end-toend multi-modal transformer framework for multi-modal human state recognition called Husformer . Specifically, we propose using cross-modal transformers, which inspire one modality to reinforce itself through directly attending to latent relevance revealed in other modalities, to fuse different modalities while ensuring sufficient awareness of the cross-modal interactions introduced. Subsequently, we utilize a self-attention transformer to further prioritize contextual information in the fusion representation. Extensive experiments on two human emotion corpora (DEAP and WESAD) and two cognitive load datasets (MOCAS and CogLoad) demonstrate that in the recognition of the human state, our Husformer outperforms both state-of-the-art multi-modal baselines and the use of a single modality by a large margin, especially when dealing with raw multi-modal features. We also conducted an ablation study to show the benefits of each component in Husformer . Experimental details and source code are available at: https://github.com/SMARTlab-Purdue/Husformer .