TACFN: Transformer-Based Adaptive Cross-Modal Fusion Network for Multimodal Emotion Recognition

TACFN: Transformer-Based Adaptive Cross-Modal Fusion Network for Multimodal Emotion Recognition

The fusion technique is the key to the multimodal emotion recognition task. Recently, cross-modal attention-based fusion methods have demonstrated high performance and strong robustness. However, cross-modal attention suffers from redundant features and does not capture complementary features well....

Full description

Bibliographic Details
Main Authors: Feng Liu, Ziwang Fu, Yunlong Wang, Qijian Zheng
Format: Article
Language:English
Published: Tsinghua University Press 2023-12-01
Series:CAAI Artificial Intelligence Research
Subjects:
multimodal emotion recognition
multimodal fusion
adaptive cross-modal blocks
transformer
computational perception
Online Access:https://www.sciopen.com/article/10.26599/AIR.2023.9150019

Internet

https://www.sciopen.com/article/10.26599/AIR.2023.9150019

Similar Items