典型文献
Cross-Modal Complementary Network with Hierarchical Fusion for Multimodal Sentiment Classification
文献摘要：
Multimodal Sentiment Classification(MSC)uses multimodal data,such as images and texts,to identify the users'sentiment polarities from the information posted by users on the Internet.MSC has attracted considerable attention because of its wide applications in social computing and opinion mining.However,improper correlation strategies can cause erroneous fusion as the texts and the images that are unrelated to each other may integrate.Moreover,simply concatenating them modal by modal,even with true correlation,cannot fully capture the features within and between modals.To solve these problems,this paper proposes a Cross-Modal Complementary Network(CMCN)with hierarchical fusion for MSC.The CMCN is designed as a hierarchical structure with three key modules,namely,the feature extraction module to extract features from texts and images,the feature attention module to learn both text and image attention features generated by an image-text correlation generator,and the cross-modal hierarchical fusion module to fuse features within and between modals.Such a CMCN provides a hierarchical fusion framework that can fully integrate different modal features and helps reduce the risk of integrating unrelated modal features.Extensive experimental results on three public datasets show that the proposed approach significantly outperforms the state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
Cheng Peng;Chunxia Zhang;Xiaojun Xue;Jiameng Gao;Hongjian Liang;Zhengdong Niu
作者机构：
School of Computer Science and Technology,Beijing Institute of Technology,Beijing 100081,China;School of Information,Production and Systems,Waseda University,Fukuoka 808-0135,Japan
文献出处：
引用格式：
[1]Cheng Peng;Chunxia Zhang;Xiaojun Xue;Jiameng Gao;Hongjian Liang;Zhengdong Niu-.Cross-Modal Complementary Network with Hierarchical Fusion for Multimodal Sentiment Classification)[J].清华大学学报自然科学版（英文版）,2022(04):664-679
A类：
modals,CMCN
B类：
Cross,Modal,Complementary,Network,Hierarchical,Fusion,Multimodal,Sentiment,Classification,MSC,uses,multimodal,such,images,texts,identify,users,sentiment,polarities,from,information,posted,by,Internet,has,attracted,considerable,attention,because,its,wide,applications,social,computing,opinion,mining,However,improper,correlation,strategies,erroneous,fusion,that,are,unrelated,each,other,may,integrate,Moreover,simply,concatenating,them,even,true,cannot,fully,capture,features,within,between,To,solve,these,problems,this,paper,proposes,hierarchical,designed,structure,three,key,modules,namely,extraction,learn,both,generated,generator,cross,fuse,Such,provides,framework,different,helps,reduce,risk,integrating,Extensive,experimental,results,public,datasets,show,proposed,approach,significantly,outperforms,state,art,methods
AB值：
0.53254
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
