Tri-CLT: Learning Tri-Modal Representations with Contrastive Learning and Transformer for Multimodal Sentiment Recognition

Zhiyong Yang 0003, Zijian Li, Dongdong Zhu, Yu Zhou. Tri-CLT: Learning Tri-Modal Representations with Contrastive Learning and Transformer for Multimodal Sentiment Recognition. ITC, 53(1):206-219, 2024. [doi]

Abstract

Abstract is missing.