AEFNet: An adaptive external attention-enhanced fusion network for multimodal emotion recognition

Multimodal emotion recognition (MER) aims to integrate various information sources to infer human emotions accurately. Most existing work focuses on fusion techniques, however, they often fail to effectively capture modal interactions and neglect the optimization of modality weights, thereby limitin...

Descripció completa

Dades bibliogràfiques

Autors principals:	Jinhang Liu, Ziyuan Chen, Zhiwei Ye, Jun Shen, Bin Hu, Yong Luo, Ting Cai, Wen Zhou, Jixin Zhang, Lingyu Yan
Format:	Artigo
Idioma:	Inglês
Publicat:	Elsevier 2025-11-01
Col·lecció:	Alexandria Engineering Journal
Matèries:	Multimodal emotion recognition Multimodal feature extractor Transformer External attention Hierarchical gated fusion
Accés en línia:	http://www.sciencedirect.com/science/article/pii/S1110016825011147
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!