{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:33:00Z","timestamp":1780687980631,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020033"],"award-info":[{"award-number":["LQ24F020033"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020033"],"award-info":[{"award-number":["LQ24F020033"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020033"],"award-info":[{"award-number":["LQ24F020033"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020033"],"award-info":[{"award-number":["LQ24F020033"]}]},{"name":"Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province","award":["2020E10010"],"award-info":[{"award-number":["2020E10010"]}]},{"name":"Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province","award":["2020E10010"],"award-info":[{"award-number":["2020E10010"]}]},{"name":"Key Research and Development Project of Zhejiang ProvinceKey Research and Development Project of Zhejiang Province","award":["2023C03026, 2021C03001"],"award-info":[{"award-number":["2023C03026, 2021C03001"]}]},{"name":"Key Research and Development Project of Zhejiang ProvinceKey Research and Development Project of Zhejiang Province","award":["2023C03026, 2021C03001"],"award-info":[{"award-number":["2023C03026, 2021C03001"]}]},{"name":"Key Research and Development Project of Zhejiang ProvinceKey Research and Development Project of Zhejiang Province","award":["2023C03026, 2021C03001"],"award-info":[{"award-number":["2023C03026, 2021C03001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U20B2074"],"award-info":[{"award-number":["U20B2074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06729-y","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T14:40:59Z","timestamp":1734705659000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MECG: modality-enhanced convolutional graph for unbalanced multimodal representations"],"prefix":"10.1007","volume":"81","author":[{"given":"Jiajia","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanzeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,20]]},"reference":[{"key":"6729_CR1","unstructured":"Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: ICML"},{"key":"6729_CR2","doi-asserted-by":"crossref","unstructured":"Nasersharif B, Ebrahimpour M, Naderi N (2023) Multi-layer maximum mean discrepancy in auto-encoders for cross-corpus speech emotion recognition. J Supercomput 1\u201319","DOI":"10.1007\/s11227-023-05161-y"},{"key":"6729_CR3","doi-asserted-by":"crossref","unstructured":"Zhang M, Li X, Wu F (2023) Moka-ada: adversarial domain adaptation with model-oriented knowledge adaptation for cross-domain sentiment analysis. J Supercomput 1\u201320","DOI":"10.1007\/s11227-023-05191-6"},{"key":"6729_CR4","doi-asserted-by":"crossref","unstructured":"Siagh A, Laallam FZ, Kazar O, Salem H (2023) An improved sentiment classification model based on data quality and word embeddings. J Supercomput 1\u201324","DOI":"10.1007\/s11227-023-05099-1"},{"key":"6729_CR5","doi-asserted-by":"crossref","unstructured":"Hadikhah Mozhdehi M, Eftekhari Moghadam A (2023) Textual emotion detection utilizing a transfer learning approach. J Supercomput 1\u201315","DOI":"10.1007\/s11227-023-05168-5"},{"key":"6729_CR6","doi-asserted-by":"crossref","unstructured":"Qorich M, El Ouazzani R (2023) Text sentiment classification of amazon reviews using word embeddings and convolutional neural networks. J Supercomput 1\u201326","DOI":"10.1007\/s11227-023-05094-6"},{"key":"6729_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.tcs.2018.04.029","volume":"752","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Song D, Zhang P, Wang P, Li J, Li X, Wang B (2018) A quantum-inspired multimodal sentiment analysis framework. Theoret Comput Sci 752:21\u201340","journal-title":"Theoret Comput Sci"},{"key":"6729_CR8","doi-asserted-by":"crossref","unstructured":"Zadeh A, Chen M, Poria S, Cambria E, Morency L-P (2017) Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp 1103\u20131114","DOI":"10.18653\/v1\/D17-1115"},{"key":"6729_CR9","doi-asserted-by":"crossref","unstructured":"Hazarika D, Zimmermann R, Poria S (2020) Misa: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp 1122\u20131131","DOI":"10.1145\/3394171.3413678"},{"key":"6729_CR10","doi-asserted-by":"crossref","unstructured":"Tsai Y-HH, Bai S, Liang PP, Kolter JZ, Morency L-P, Salakhutdinov R (2019) Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp 6558\u20136569","DOI":"10.18653\/v1\/P19-1656"},{"key":"6729_CR11","doi-asserted-by":"crossref","unstructured":"Tang J, Li K, Jin X, Cichocki A, Zhao Q, Kong W (2021) Ctfn: Hierarchical learning for multimodal sentiment analysis using coupled-translation fusion network. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 5301\u20135311","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"6729_CR12","unstructured":"Tang J, Li K, Hou M, Jin X, Kong W, Ding Y, Zhao Q Mmt: multi-way multi-modal transformer for multimodal learning"},{"key":"6729_CR13","doi-asserted-by":"crossref","unstructured":"Hu J, Liu Y, Zhao J, Jin Q (2021) Mmgcn: multimodal fusion via deep graph convolution network for emotion recognition in conversation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 5666\u20135675","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"6729_CR14","doi-asserted-by":"crossref","unstructured":"Chen M, Wang S, Liang PP, Baltru\u0161aitis T, Zadeh A, Morency L-P (2017) Multimodal sentiment analysis with word-level fusion and reinforcement learning. In: Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp 163\u2013171","DOI":"10.1145\/3136755.3136801"},{"key":"6729_CR15","doi-asserted-by":"crossref","unstructured":"Sun Z, Sarma P, Sethares W, Liang Y (2020) Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 8992\u20138999","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"6729_CR16","doi-asserted-by":"crossref","unstructured":"Guo J, Tang J, Dai W, Ding Y, Kong W (2022) Dynamically adjust word representations using unaligned multimodal information. In: Proceedings of the 30th ACM International Conference on Multimedia, pp 3394\u20133402","DOI":"10.1145\/3503161.3548137"},{"key":"6729_CR17","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"6729_CR18","doi-asserted-by":"crossref","unstructured":"Williams J, Kleinegesse S, Comanescu R, Radu O (2018) Recognizing emotions in video using multimodal DNN feature fusion. In: Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML), pp 11\u201319","DOI":"10.18653\/v1\/W18-3302"},{"key":"6729_CR19","doi-asserted-by":"crossref","unstructured":"Zadeh AB, Liang PP, Poria S, Cambria E, Morency L-P (2018) Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 2236\u20132246","DOI":"10.18653\/v1\/P18-1208"},{"key":"6729_CR20","doi-asserted-by":"crossref","unstructured":"Morency L-P, Mihalcea R, Doshi P (2011) Towards multimodal sentiment analysis: harvesting opinions from the web. In: Proceedings of the 13th International Conference on Multimodal Interfaces, pp 169\u2013176","DOI":"10.1145\/2070481.2070509"},{"key":"6729_CR21","doi-asserted-by":"crossref","unstructured":"Liang PP, Liu Z, Zadeh AB, Morency L-P (2018) Multimodal language analysis with recurrent multistage fusion. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 150\u2013161","DOI":"10.18653\/v1\/D18-1014"},{"key":"6729_CR22","unstructured":"Tsai Y-HH, Liang PP, Zadeh A, Morency L-P, Salakhutdinov R (2019) Learning factorized multimodal representations. In: International Conference on Representation Learning"},{"key":"6729_CR23","unstructured":"Zadeh A, Mao C, Shi K, Zhang Y, Liang PP, Poria S, Morency L-P (2019) Factorized multimodal transformer for multimodal sequential learning. arXiv preprint arXiv:1911.09826"},{"issue":"7","key":"6729_CR24","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.1109\/TPAMI.2020.2973634","volume":"43","author":"X Jia","year":"2020","unstructured":"Jia X, Jing X-Y, Zhu X, Chen S, Du B, Cai Z, He Z, Yue D (2020) Semi-supervised multi-view deep discriminant representation learning. IEEE Trans Pattern Anal Mach Intell 43(7):2496\u20132509","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6729_CR25","doi-asserted-by":"crossref","unstructured":"Yu W, Xu H, Yuan Z, Wu J (2021) Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 35, pp 10790\u201310797","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"6729_CR26","doi-asserted-by":"crossref","unstructured":"Yang J, Wang Y, Yi R, Zhu Y, Rehman A, Zadeh A, Poria S, Morency L-P (2021) Mtag: modal-temporal attention graph for unaligned human multimodal language sequences. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 1009\u20131021","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"6729_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2022.03.076","volume":"600","author":"Z Cai","year":"2022","unstructured":"Cai Z, Zhang T, Jing X-Y, Shao L (2022) Unequal adaptive visual recognition by learning from multi-modal data. Inf Sci 600:1\u201321","journal-title":"Inf Sci"},{"key":"6729_CR28","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Poria S, Chhaya N, Gelbukh A (2019) Dialoguegcn: a graph convolutional neural network for emotion recognition in conversation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp 154\u2013164","DOI":"10.18653\/v1\/D19-1015"},{"issue":"8","key":"6729_CR29","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"6729_CR30","unstructured":"Chen M, Wei Z, Huang Z, Ding B, Li Y (2020) Simple and deep graph convolutional networks. In: International Conference on Machine Learning. PMLR, pp 1725\u20131735"},{"key":"6729_CR31","doi-asserted-by":"crossref","unstructured":"Li G, Muller M, Thabet A, Ghanem B (2019) Deepgcns: can GCNS go as deep as CNNS? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9267\u20139276","DOI":"10.1109\/ICCV.2019.00936"},{"key":"6729_CR32","doi-asserted-by":"crossref","unstructured":"Skianis K, Malliaros F, Vazirgiannis M (2018) Fusing document, collection and label graph-based representations with word embeddings for text classification. In: Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12), pp 49\u201358","DOI":"10.18653\/v1\/W18-1707"},{"key":"6729_CR33","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907"},{"key":"6729_CR34","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805[SPACE]arXiv:1810.04805"},{"issue":"6","key":"6729_CR35","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L-P (2016) Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages. IEEE Intell Syst 31(6):82\u201388","journal-title":"IEEE Intell Syst"},{"issue":"5","key":"6729_CR36","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan J, Liberman M (2008) Speaker identification on the scotus corpus. J Acoust Soc Am 123(5):3878","journal-title":"J Acoust Soc Am"},{"key":"6729_CR37","doi-asserted-by":"crossref","unstructured":"Degottex G, Kane J, Drugman T, Raitio T, Scherer S (2014) Covarep\u00e2\u20ac\u201da collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 960\u2013964. IEEE","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"6729_CR38","doi-asserted-by":"crossref","unstructured":"Liu Z, Shen Y, Lakshminarasimhan VB, Liang PP, Zadeh AB, Morency L-P (2018) Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 2247\u20132256","DOI":"10.18653\/v1\/P18-1209"},{"key":"6729_CR39","doi-asserted-by":"crossref","unstructured":"Rahman W, Hasan MK, Lee S, Zadeh AB, Mao C, Morency L-P, Hoque E (2020) Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 2359\u20132369","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"6729_CR40","doi-asserted-by":"crossref","unstructured":"Han W, Chen H, Poria S (2021) Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp 9180\u20139192","DOI":"10.18653\/v1\/2021.emnlp-main.723"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06729-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06729-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06729-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T15:04:19Z","timestamp":1734707059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06729-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6729"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06729-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,20]]},"assertion":[{"value":"15 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"319"}}