{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:10:18Z","timestamp":1764144618788,"version":"3.46.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82405005),"],"award-info":[{"award-number":["82405005),"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10489-025-06979-0","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T07:34:29Z","timestamp":1762500869000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D$$^2$$M: Decomposition-diffusion model for enhanced multimodal sentiment analysis"],"prefix":"10.1007","volume":"55","author":[{"given":"Liansong","family":"Zong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhe","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongfeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"issue":"2","key":"6979_CR1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P (2018) Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6979_CR2","doi-asserted-by":"publisher","first-page":"102132","DOI":"10.1016\/j.inffus.2023.102132","volume":"103","author":"J Wang","year":"2024","unstructured":"Wang J, Yang Y, Jiang Y, Ma M, Xie Z, Li T (2024) Cross-modal incongruity aligning and collaborating for multi-modal sarcasm detection. Inf Fusion 103:102132","journal-title":"Inf Fusion"},{"key":"6979_CR3","doi-asserted-by":"crossref","unstructured":"Zhang Y, Chen M, Shen J, Wang C (2022) Tailor versatile multi-modal learning for multi-label emotion recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 9100\u20139108","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"6979_CR4","doi-asserted-by":"publisher","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. MM \u201920, pp 1122\u20131131. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3394171.3413678","DOI":"10.1145\/3394171.3413678"},{"key":"6979_CR5","doi-asserted-by":"crossref","unstructured":"Yang D, Huang S, Kuang H, Du Y, Zhang L (2022) Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM international conference on multimedia, pp 1642\u20131651","DOI":"10.1145\/3503161.3547754"},{"key":"6979_CR6","doi-asserted-by":"publisher","first-page":"111848","DOI":"10.1016\/j.knosys.2024.111848","volume":"295","author":"J Wang","year":"2024","unstructured":"Wang J, Yang Y, Liu K, Xie Z, Zhang F, Li T (2024) Citenet: cross-modal incongruity perception network for multimodal sentiment prediction. Knowl-Based Syst 295:111848","journal-title":"Knowl-Based Syst"},{"key":"6979_CR7","doi-asserted-by":"crossref","unstructured":"You Q, Luo J, Jin H, Yang J (2015) Joint visual-textual sentiment analysis with deep neural networks. In: ACM MM, pp 1071\u20131074","DOI":"10.1145\/2733373.2806284"},{"key":"6979_CR8","doi-asserted-by":"crossref","unstructured":"You Q, Luo J, Jin H, Yang J (2016) Cross-modality consistent regression for joint visual-textual sentiment analysis of social multimedia. In: ACM MM, pp 13\u201322","DOI":"10.1145\/2835776.2835779"},{"key":"6979_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108107","volume":"240","author":"Y Du","year":"2022","unstructured":"Du Y, Liu Y, Peng Z, Jin X (2022) Gated attention fusion network for multimodal sentiment classification. Knowl Based Syst 240:108107","journal-title":"Knowl Based Syst"},{"key":"6979_CR10","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/TASLP.2022.3221017","volume":"31","author":"J Wang","year":"2022","unstructured":"Wang J, Yang Y, Liu K, Zhu Z, Liu X (2022) M3s: scene graph driven multi-granularity multi-task learning for multi-modal ner. IEEE\/ACM Trans Audio Speech Lang Process 31:111\u2013120","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"6979_CR11","doi-asserted-by":"crossref","unstructured":"Wei Y, Yuan S, Yang R, Shen L, Li Z, Wang L, Chen M (2023) Tackling modality heterogeneity with multi-view calibration network for multimodal sentiment detection. In: ACL, pp 5240\u20135252","DOI":"10.18653\/v1\/2023.acl-long.287"},{"key":"6979_CR12","doi-asserted-by":"publisher","unstructured":"Zhu T, Li L, Yang J, Zhao S, Xiao X (2022) Multimodal emotion classification with multi-level semantic reasoning network. IEEE Trans Multim. Early Access. https:\/\/doi.org\/10.1109\/TMM.2022.3214989","DOI":"10.1109\/TMM.2022.3214989"},{"key":"6979_CR13","doi-asserted-by":"crossref","unstructured":"Dey RK, Das AK (2022) A simple strategy for handling \u2018not\u2019can improve the performance of sentiment analysis. In: International conference on computational intelligence in pattern recognition, pp 255\u2013267. Springer","DOI":"10.1007\/978-981-19-3089-8_25"},{"key":"6979_CR14","doi-asserted-by":"publisher","first-page":"118290","DOI":"10.1016\/j.eswa.2022.118290","volume":"209","author":"R Catelli","year":"2022","unstructured":"Catelli R, Fujita H, De Pietro G, Esposito M (2022) Deceptive reviews and sentiment polarity: effective link by exploiting Bert. Expert Syst Appl 209:118290","journal-title":"Expert Syst Appl"},{"key":"6979_CR15","doi-asserted-by":"publisher","first-page":"110125","DOI":"10.1016\/j.knosys.2022.110125","volume":"260","author":"B Huang","year":"2023","unstructured":"Huang B, Zhang J, Ju J, Guo R, Fujita H, Liu J (2023) Crf-gcn: an effective syntactic dependency model for aspect-level sentiment analysis. Knowl-Based Syst 260:110125","journal-title":"Knowl-Based Syst"},{"key":"6979_CR16","doi-asserted-by":"crossref","unstructured":"Dey RK, Das AK (2024) Neighbour adjusted dispersive flies optimization based deep hybrid sentiment analysis framework. Multimedia Tools Appl 1\u201324","DOI":"10.1007\/s11042-023-17953-8"},{"key":"6979_CR17","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":"6979_CR18","doi-asserted-by":"crossref","unstructured":"Li Z, Xu B, Zhu C, Zhao T (2022) CLMLF: a contrastive learning and multi-layer fusion method for multimodal sentiment detection. In: Findings of NAACL, pp 2282\u20132294","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"6979_CR19","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":"6979_CR20","doi-asserted-by":"crossref","unstructured":"Wu Y, Lin Z, Zhao Y, Qin B, Zhu L-N (2021) A text-centered shared-private framework via cross-modal prediction for multimodal sentiment analysis. In: Findings of the association for computational linguistics: ACL-IJCNLP 2021, pp 4730\u20134738","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"6979_CR21","unstructured":"Kim H, Mnih A (2018) Disentangling by factorising. In: International conference on machine learning, pp 2649\u20132658. PMLR"},{"key":"6979_CR22","unstructured":"Dai W, Li X, Hu P, Wang Z, Qi J, Peng J, Zhou Y (2024) Mind: improving multimodal sentiment analysis via multimodal information disentanglement. arXiv:2401.11818"},{"key":"6979_CR23","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho J, Salimans T, Gritsenko A, Chan W, Norouzi M, Fleet DJ (2022) Video diffusion models. Adv Neural Inf Process Syst 35:8633\u20138646","journal-title":"Adv Neural Inf Process Syst"},{"key":"6979_CR24","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yang H, Fu J, Fu D (2022) Learning spatiotemporal frequency-transformer for compressed video super-resolution. In: European conference on computer vision, pp 257\u2013273. Springer","DOI":"10.1007\/978-3-031-19797-0_15"},{"key":"6979_CR25","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar B, Elad M, Ermon S, Song J (2022) Denoising diffusion restoration models. Adv Neural Inf Process Syst 35:23593\u201323606","journal-title":"Adv Neural Inf Process Syst"},{"key":"6979_CR26","doi-asserted-by":"crossref","unstructured":"Saharia C, Chan W, Chang H, Lee C, Ho J, Salimans T, Fleet D, Norouzi M (2022) Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 conference proceedings, pp 1\u201310","DOI":"10.1145\/3528233.3530757"},{"key":"6979_CR27","doi-asserted-by":"crossref","unstructured":"B\u00f6hme M, Pham V-T, Roychoudhury A (2016) Coverage-based greybox fuzzing as Markov chain. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, pp 1032\u20131043","DOI":"10.1145\/2976749.2978428"},{"issue":"8","key":"6979_CR28","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":"6979_CR29","doi-asserted-by":"publisher","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","volume":"7","author":"W Guo","year":"2019","unstructured":"Guo W, Wang J, Wang S (2019) Deep multimodal representation learning: a survey. IEEE Access 7:63373\u201363394","journal-title":"IEEE Access"},{"key":"6979_CR30","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems, vol 30"},{"key":"6979_CR31","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6979_CR32","unstructured":"Kiela D, Bhooshan S, Firooz H, Perez E, Testuggine D (2019) Supervised multimodal bitransformers for classifying images and text. arXiv:1909.02950"},{"key":"6979_CR33","unstructured":"Li LH, Yatskar M, Yin D, Hsieh C-J, Chang K-W (2019) Visualbert: a simple and performant baseline for vision and language. arXiv:1908.03557"},{"key":"6979_CR34","unstructured":"Zellinger W, Grubinger T, Lughofer E, Natschl\u00e4ger T, Saminger-Platz S (2017) Central moment discrepancy (CMD) for domain-invariant representation learning. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=SkB-_mcel"},{"key":"6979_CR35","unstructured":"Hjelm RD, Fedorov A, Lavoie-Marchildon S, Grewal K, Bachman P, Trischler A, Bengio Y (2018) Learning deep representations by mutual information estimation and maximization. arXiv:1808.06670"},{"key":"6979_CR36","unstructured":"Bertoin D, Rachelson E (2022) Disentanglement by cyclic reconstruction. IEEE Trans Neural Netw Learn Syst"},{"issue":"59","key":"6979_CR37","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, March M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(59):1\u201335","journal-title":"J Mach Learn Res"},{"issue":"6","key":"6979_CR38","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"},{"key":"6979_CR39","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":"6979_CR40","doi-asserted-by":"crossref","unstructured":"Hasan MK, Rahman W, Zadeh A, Zhong J, Tanveer MI, Morency L-P et al (2019) Ur-funny: a multimodal language dataset for understanding humor. arXiv:1904.06618","DOI":"10.18653\/v1\/D19-1211"},{"key":"6979_CR41","unstructured":"Quan W, Feng Y, Zhou M, Zhao Y, Wang T, Yan D-M (2024) Tcan: text-oriented cross attention network for multimodal sentiment analysis. arXiv:2404.04545"},{"issue":"3","key":"6979_CR42","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1177\/00030651221107681","volume":"70","author":"NM Szajnberg","year":"2022","unstructured":"Szajnberg NM (2022) What the face reveals: basic and applied studies of spontaneous expression using the facial action coding system (facs). J Am Psychoanal Assoc 70(3):591\u2013595. https:\/\/doi.org\/10.1177\/00030651221107681","journal-title":"J Am Psychoanal Assoc"},{"issue":"1","key":"6979_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3284750","volume":"15","author":"Y Peng","year":"2019","unstructured":"Peng Y, Qi J (2019) Cm-gans: cross-modal generative adversarial networks for common representation learning. ACM Trans Multimedia Comput Commun Appl (TOMM) 15(1):1\u201324","journal-title":"ACM Trans Multimedia Comput Commun Appl (TOMM)"},{"key":"6979_CR44","doi-asserted-by":"crossref","unstructured":"Liu Z, Shen Y, Lakshminarasimhan VB, Liang PP, Zadeh A, Morency L-P (2018) Efficient low-rank multimodal fusion with modality-specific factors. arXiv:1806.00064","DOI":"10.18653\/v1\/P18-1209"},{"key":"6979_CR45","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":"6979_CR46","doi-asserted-by":"crossref","unstructured":"Han W, Chen H, Gelbukh A, Zadeh A, Morency L-p, Poria S (2021) Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. In: Proceedings of the 2021 international conference on multimodal interaction, pp 6\u201315","DOI":"10.1145\/3462244.3479919"},{"key":"6979_CR47","doi-asserted-by":"crossref","unstructured":"Zong D, Ding C, Li B, Li J, Zheng K, Zhou Q (2023) Acformer: an aligned and compact transformer for multimodal sentiment analysis. In: Proceedings of the 31st ACM international conference on multimedia, pp 833\u2013842","DOI":"10.1145\/3581783.3611974"},{"issue":"21","key":"6979_CR48","doi-asserted-by":"publisher","first-page":"4175","DOI":"10.3390\/electronics13214175","volume":"13","author":"M Ji","year":"2024","unstructured":"Ji M, Wei N, Zhou J, Wang X (2024) Ss-trans (single-stream transformer for multimodal sentiment analysis and emotion recognition): the emotion whisperer\u2014a single-stream transformer for multimodal sentiment analysis. Electronics 13(21):4175","journal-title":"Electronics"},{"key":"6979_CR49","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Rese 9(11)"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06979-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06979-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06979-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:05:41Z","timestamp":1764144341000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06979-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":49,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["6979"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06979-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"12 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"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 competing interests to declare relevant to this article\u2019s content.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"1080"}}