检索结果-南通市图书馆

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

CAAI Artificial Intelligence Research 2023年第1期2卷 75-82页

作者： Feng Liu Ziwang Fu Yunlong Wang Qijian Zheng School of Computer Science and Technology East China Normal UniversityShanghai 200062China MTlab Meitu(China)LimitedBeijing 100876China Institute of Acoustics University of Chinese Academy of SciencesBeijing 100084China

The fusion technique is the key to the multimodal emotion recognition ***,cross-modal attention-based fusion methods have demonstrated high performance and strong ***,cross-modal attention suffers from redundant features and does not capture complementary features *** find that it is not necessary to use the entire information of one modality to reinforce the other during cross-modal interaction,and the features that can reinforce a modality may contain only a part of *** this end,we design an innovative Transformer-based Adaptive Cross-modal Fusion Network(TACFN).Specifically,for the redundant features,we make one modality perform intra-modal feature selection through a self-attention mechanism,so that the selected features can adaptively and efficiently interact with another *** better capture the complementary information between the modalities,we obtain the fused weight vector by splicing and use the weight vector to achieve feature reinforcement of the *** apply TCAFN to the RAVDESS and IEMOCAP *** fair comparison,we use the same unimodal representations to validate the effectiveness of the proposed fusion *** experimental results show that TACFN brings a significant performance improvement compared to other methods and reaches the state-of-the-art *** code and models could be accessed from https://***/shuzihuaiyu/TACFN.

关键词： multimodal emotion recognition multimodal fusion adaptive cross-modal blocks Transformer computational perception

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：