{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:29:31Z","timestamp":1763202571622,"version":"3.37.3"},"reference-count":49,"publisher":"Wiley","license":[{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"],"award-info":[{"award-number":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"],"award-info":[{"award-number":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009377","name":"Education Department of Hunan Province","doi-asserted-by":"publisher","award":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"],"award-info":[{"award-number":["U1934219","52172403","62173137","2021JJ50001","2021JJ30217","19A137"]}],"id":[{"id":"10.13039\/100009377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2022,1,24]]},"abstract":"<jats:p>Multimodal sentiment analysis (MSA) aims to infer emotions from linguistic, auditory, and visual sequences. Multimodal information representation method and fusion technology are keys to MSA. However, the problem of difficulty in fully obtaining heterogeneous data interactions in MSA usually exists. To solve these problems, a new framework, namely, dynamic invariant-specific representation fusion network (DISRFN), is put forward in this study. Firstly, in order to effectively utilize redundant information, the joint domain separation representations of all modes are obtained through the improved joint domain separation network. Then, the hierarchical graph fusion net (HGFN) is used for dynamically fusing each representation to obtain the interaction of multimodal data for guidance in the sentiment analysis. Moreover, comparative experiments are performed on popular MSA data sets MOSI and MOSEI, and the research on fusion strategy, loss function ablation, and similarity loss function analysis experiments is designed. The experimental results verify the effectiveness of the DISRFN framework and loss function.<\/jats:p>","DOI":"10.1155\/2022\/2105593","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T02:35:05Z","timestamp":1643078105000},"page":"1-14","source":"Crossref","is-referenced-by-count":8,"title":["Dynamic Invariant-Specific Representation Fusion Network for Multimodal Sentiment Analysis"],"prefix":"10.1155","volume":"2022","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3650-3270","authenticated-orcid":true,"given":"Jing","family":"He","sequence":"first","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7307-9675","authenticated-orcid":true,"given":"Haonan","family":"Yanga","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9800-3984","authenticated-orcid":true,"given":"Changfan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6968-5990","authenticated-orcid":true,"given":"Hongrun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifu","family":"Xua","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.006"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6610997"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1117\/1.oe.51.11.117201"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2019.2957872"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2013.03.004"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.2316\/journal.206.2017.5.206-5027"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.003"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2932564"},{"first-page":"5634","article-title":"Memory fusion network for multiview sequential learning","author":"A. Zadeh","key":"9"},{"first-page":"2236","article-title":"multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"A. Zadeh","key":"10"},{"first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"A. Zadeh","key":"11"},{"first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality -specific factors","author":"Z. Liu","key":"12"},{"first-page":"343","article-title":"Domain separation networks","author":"K. Bousmalis","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3028452"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"author":"J. Kim","key":"16","article-title":"Edge-labeling graph neural network for few-shot learning"},{"first-page":"481","article-title":"Conquer and combine: hierarchical feature fusion network with local and global perspectives for multimodal affective computing","author":"S. J. Mai","key":"17"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2925966"},{"first-page":"150","article-title":"multimodal language analysis with recurrent multistage fusion","author":"P. P. Liang","key":"19"},{"first-page":"5642","article-title":"Multi-attention recurrent network for human communication comprehension","author":"A. Zadeh","key":"20"},{"first-page":"1","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","author":"M. Hou","key":"21"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3000510"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3074757"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"first-page":"163","article-title":"Multimodal sentiment analysis with word-level fusion and reinforcement learning","author":"M. H. Chen","key":"25"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107905"},{"key":"27","article-title":"Variational graph autoencoders for multiview canonical correlation analysis","volume":"104","author":"Y. Kaloga","year":"2021","journal-title":"Signal Processing"},{"article-title":"Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis","author":"S. Verma","key":"28","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM50108.2020.00065"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.032"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"author":"Y. H. H. Tsai","key":"32","article-title":"Learning factorized multimodal representations"},{"first-page":"2599","article-title":"Strong and simple baselines for multimodal utterance embeddings","author":"P. P. Liang","key":"33"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107479"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105381"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.04.037"},{"key":"37","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MMUL.2021.3069097","article-title":"Modeling incongruity between modalities for multimodal sarcasm detection","volume":"28","author":"Y. Wu","year":"2021","journal-title":"IEEE Multimedia"},{"author":"F. Chen","key":"38","article-title":"Complementary Fusion of Multi-Features and Multi-Modalities in Sentiment Analysis"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2916887"},{"first-page":"1122","article-title":"MISA: Modality-invariant and -specific representations for multimodal sentiment analysis","author":"D. Hazarika","key":"41"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2753232"},{"author":"W. Zellinge","key":"43","article-title":"CMD for Domain-Invariant Representation learning"},{"first-page":"159","article-title":"Adversary guided asymmetric hashing for cross-modal retrieval","author":"W. Gu","key":"44"},{"key":"45","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2021.3078074"},{"first-page":"960","article-title":"COVAREP-A collaborative voice analysis repository for speech technologies","author":"G. Degottex","key":"46"},{"first-page":"7747","article-title":"Unsupervised domain clusters in pretrained language models","author":"R. Aharoni","key":"47"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107907"},{"key":"49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.090"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2022\/2105593.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2022\/2105593.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2022\/2105593.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T02:35:10Z","timestamp":1643078110000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cin\/2022\/2105593\/"}},"subtitle":[],"editor":[{"given":"Zhongxu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,1,24]]},"references-count":49,"alternative-id":["2105593","2105593"],"URL":"https:\/\/doi.org\/10.1155\/2022\/2105593","relation":{},"ISSN":["1687-5273","1687-5265"],"issn-type":[{"type":"electronic","value":"1687-5273"},{"type":"print","value":"1687-5265"}],"subject":[],"published":{"date-parts":[[2022,1,24]]}}}