HCAM -- 多模态情感识别的层级交叉关注模型（英文版）

英文标题：HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition中文摘要：本文提出了一种基于 HCAM 方法的跨模态情绪识别模型，使用神经网络模型组合音频和文本数据，在 IEMOCAP、MELD 和 CMU-MOSI 三个数据集上达到了最先进的结果。英文摘要：Emotion recognition in conversations is challenging due to the multi-modalnature of the emotion expression. We propose a hierarchical cross-attentionmodel (HCAM) approach to multi-modal emotion recognition using a combination ofrecurrent and co-attention neural network models. The input to the modelconsists of two mo