{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:03:52Z","timestamp":1772823832332,"version":"3.50.1"},"reference-count":47,"publisher":"Tech Science Press","issue":"1","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"vor","delay-in-days":242,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.066476","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T11:14:57Z","timestamp":1753269297000},"page":"1427-1456","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["TGICP: A Text-Gated Interaction Network with Inter-Sample Commonality Perception for Multimodal Sentiment Analysis"],"prefix":"10.32604","volume":"85","author":[{"given":"Erlin","family":"Tian","sequence":"first","affiliation":[]},{"given":"Shuai","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Min","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yushan","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Yihong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zuhe","family":"Li","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"124236","DOI":"10.1016\/j.eswa.2024.124236","article-title":"Hierarchical denoising representation disentanglement and dual-channel cross-modal-context interaction for multimodal sentiment analysis","volume":"252","author":"Li","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"6558","DOI":"10.18653\/v1\/P19-1656","author":"Tsai","year":"2019","journal-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics; 2019 Jul; Florence, Italy"},{"key":"ref3","series-title":"Proceedings of the 28th ACM International Conference on Multimedia; 2020 Oct; Seattle, WA, USA","first-page":"1122","article-title":"MISA: modality-invariant and -specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"key":"ref4","first-page":"4730","author":"Wu","year":"2021","journal-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021; 2021 Aug; Online"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"110847","DOI":"10.1016\/j.patcog.2024.110847","article-title":"Sentiment analysis based on text information enhancement and multimodal feature fusion","volume":"156","author":"Liu","year":"2024","journal-title":"Pattern Recognit"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: a survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref7","first-page":"1103","author":"Zadeh","year":"2017","journal-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing; 2017 Sep; Copenhagen, Denmark"},{"key":"ref8","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence; 2018 Apr; New Orleans, LA, USA","first-page":"692","article-title":"Multi-attention recurrent network for human communication comprehension","author":"Zadeh","year":"2018"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.18653\/v1\/P18-1209","author":"Liu","year":"2018","journal-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2018 Jul; Melbourne, VIC, Australia"},{"key":"ref10","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"35","author":"Yu","year":"2021 May","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref11","series-title":"Proceedings of the 2016 IEEE 16th International Conference on Data Mining (ICDM)","first-page":"439","article-title":"Convolutional MKL based multimodal emotion recognition and sentiment analysis","author":"Poria","year":"2016 Dec 12\u201315"},{"key":"ref12","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence; 2018 Apr 2\u20137","first-page":"691","article-title":"Memory fusion network for multi-view sequential learning","author":"Zadeh"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.knosys.2018.07.041","article-title":"Multimodal sentiment analysis using hierarchical fusion with context modeling","volume":"161","author":"Majumder","year":"2018","journal-title":"Knowl-Based Syst"},{"key":"ref14","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017 Dec 4\u20139; Long Beach, CA, USA","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref15","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2021 Jun 19\u201325; Nashville, TN, USA","first-page":"2554","article-title":"Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences","author":"Lv","year":"2021"},{"key":"ref16","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; 2020 Jul; Online","first-page":"2359","article-title":"Integrating multimodal information in large pretrained transformers","author":"Rahman","year":"2020"},{"key":"ref17","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing; 2021 Nov; Online","first-page":"9180","article-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"107222","DOI":"10.1016\/j.neunet.2025.107222","article-title":"TF-BERT: tensor-based fusion BERT for multimodal sentiment analysis","volume":"185","author":"Hou","year":"2025","journal-title":"Neural Netw"},{"key":"ref19","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence","first-page":"348","article-title":"DarkRank: accelerating deep metric learning via cross sample similarities transfer","author":"Chen","year":"2018"},{"key":"ref20","series-title":"Proceedings of the 5th ACM International Conference on Multimedia in Asia; 2024; Tainan, Taiwan","first-page":"28","article-title":"I2SRM: intra- and inter-sample relationship modeling for multimodal information extraction","author":"Huang","year":"2024"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"121282","DOI":"10.1016\/j.ins.2024.121282","article-title":"Enhancing multimodal depression detection with intra- and inter-sample contrastive learning","volume":"684","author":"Li","year":"2024","journal-title":"Inf Sci"},{"key":"ref22","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2024 Aug; Bangkok, Thailand","first-page":"18","article-title":"Unsupervised multimodal clustering for semantics discovery in multimodal utterances","author":"Zhang","year":"2024"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/s00530-024-01421-w","article-title":"Text-centered cross-sample fusion network for multimodal sentiment analysis","volume":"30","author":"Huang","year":"2024","journal-title":"Multimed Syst"},{"key":"ref24","first-page":"8992","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis","volume":"34","author":"Sun","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/TASLP.2021.3068598","article-title":"Analyzing multimodal sentiment via acoustic- and visual-LSTM with channel-aware temporal convolution network","volume":"29","author":"Mai","year":"2021","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref26","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers); 2019 Jun; Minneapolis, MN, USA","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref27","first-page":"1218","author":"Liu","year":"2021","journal-title":"Proceedings of the 20th Chinese National Conference on Computational Linguistics; 2021 Aug; Huhhot, China"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"109259","DOI":"10.1016\/j.patcog.2022.109259","article-title":"TETFN: a text enhanced transformer fusion network for multimodal sentiment analysis","volume":"136","author":"Wang","year":"2023","journal-title":"Pattern Recognit"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"110502","DOI":"10.1016\/j.knosys.2023.110502","article-title":"TeFNA: text-centered fusion network with crossmodal attention for multimodal sentiment analysis","volume":"269","author":"Huang","year":"2023","journal-title":"Knowl Based Syst"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1007\/s10489-024-06150-1","article-title":"Text-dominant multimodal perception network for sentiment analysis based on cross-modal semantic enhancements","volume":"55","author":"Li","year":"2024","journal-title":"Appl Intell"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"6975","DOI":"10.18653\/v1\/2020.emnlp-main.567","author":"Ke","year":"2020","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"173","DOI":"10.3115\/1073445.1073478","author":"Toutanova","year":"2003","journal-title":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology\u2014Volume 1"},{"key":"ref33","author":"Baccianella","year":"2010","journal-title":"Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910)"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1007\/s42761-023-00191-4","article-title":"Py-feat: python facial expression analysis toolbox","volume":"4","author":"Cheong","year":"2023 Dec 1","journal-title":"Affect Sci"},{"key":"ref35","series-title":"Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"960","article-title":"A collaborative voice analysis repository for speech technologies","author":"Degottex","year":"2014"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TMM.2022.3183830","article-title":"Cross-modal enhancement network for multimodal sentiment analysis","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans Multimed"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3542927","article-title":"Multimodal graph for unaligned multimodal sequence analysis via graph convolution and graph pooling","volume":"19","author":"Mai","year":"2023","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"ref38","series-title":"2015 IEEE Information Theory Workshop (ITW)","first-page":"1","article-title":"Deep learning and the information bottleneck principle","author":"Tishby","year":"2015"},{"key":"ref39","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8886","article-title":"Deep learning under privileged information using heteroscedastic dropout","author":"Lambert","year":"2018"},{"key":"ref40","unstructured":"van Den OA, Li Y, Vinyals O. Representation learning with contrastive predictive coding. arXiv:1807.03748. 2018."},{"key":"ref41","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L-P. MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv:1606.06259. 2016. doi: 10.48550\/arXiv.1606.06259."},{"key":"ref42","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"Zadeh","year":"2018"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"4217","DOI":"10.1109\/TMM.2023.3321404","article-title":"SGIR: star graph-based interaction for efficient and robust multimodal representation","volume":"26","author":"Ding","year":"2024","journal-title":"IEEE Trans Multimed"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"111346","DOI":"10.1016\/j.knosys.2023.111346","article-title":"TMBL: transformer-based multimodal binding learning model for multimodal sentiment analysis","volume":"285","author":"Huang","year":"2024","journal-title":"Knowl Based Syst"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"125148","DOI":"10.1016\/j.eswa.2024.125148","article-title":"Frame-level nonverbal feature enhancement based sentiment analysis","volume":"258","author":"Zheng","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"8383","DOI":"10.1109\/TMM.2023.3344358","article-title":"Dominant single-modal supplementary fusion (SIMSUF) for multimodal sentiment analysis","volume":"26","author":"Huang","year":"2024","journal-title":"IEEE Trans Multimed"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1109\/TAFFC.2024.3423671","article-title":"Multi-level contrastive learning: hierarchical alleviation of heterogeneity in multimodal sentiment analysis","volume":"16","author":"Fan","year":"2025","journal-title":"IEEE Trans Affect Comput"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-85-1\/TSP_CMC_66476\/TSP_CMC_66476.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:06:14Z","timestamp":1763345174000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v85n1\/63538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.066476","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2025-04-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-29","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}