{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:00:45Z","timestamp":1781586045611,"version":"3.54.5"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"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":["62176106"],"award-info":[{"award-number":["62176106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176106"],"award-info":[{"award-number":["62176106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176106"],"award-info":[{"award-number":["62176106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Scientific Research Project of the School of Emergency Management of Jiangsu University","award":["KY-A-01"],"award-info":[{"award-number":["KY-A-01"]}]},{"name":"Special Scientific Research Project of the School of Emergency Management of Jiangsu University","award":["KY-A-01"],"award-info":[{"award-number":["KY-A-01"]}]},{"name":"Special Scientific Research Project of the School of Emergency Management of Jiangsu University","award":["KY-A-01"],"award-info":[{"award-number":["KY-A-01"]}]},{"name":"Project of Faculty of Agricultural Engineering of Jiangsu University","award":["NGXB20240101"],"award-info":[{"award-number":["NGXB20240101"]}]},{"name":"Project of Faculty of Agricultural Engineering of Jiangsu University","award":["NGXB20240101"],"award-info":[{"award-number":["NGXB20240101"]}]},{"name":"Project of Faculty of Agricultural Engineering of Jiangsu University","award":["NGXB20240101"],"award-info":[{"award-number":["NGXB20240101"]}]},{"name":"Key Project of National Nature Science Foundation of China","award":["U1836220"],"award-info":[{"award-number":["U1836220"]}]},{"name":"Key Project of National Nature Science Foundation of China","award":["U1836220"],"award-info":[{"award-number":["U1836220"]}]},{"name":"Key Project of National Nature Science Foundation of China","award":["U1836220"],"award-info":[{"award-number":["U1836220"]}]},{"name":"Jiangsu Key Research and Development Plan Industry Foresight and Key Core Technology","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]},{"name":"Jiangsu Key Research and Development Plan Industry Foresight and Key Core Technology","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]},{"name":"Jiangsu Key Research and Development Plan Industry Foresight and Key Core Technology","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11760-025-04212-6","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T07:03:18Z","timestamp":1748415798000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Advanced Modality Contribution-based Fusion for Multi-modal Multi-label Emotion Recognition"],"prefix":"10.1007","volume":"19","author":[{"given":"Jia","family":"Nie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"4212_CR1","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, D., Shen, J.: Inter-modality and intra-sample alignment for multi-modal emotion recognition. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8301\u20138305 (2024). IEEE","DOI":"10.1109\/ICASSP48485.2024.10446571"},{"issue":"5","key":"4212_CR2","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1109\/TCSVT.2023.3312858","volume":"34","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Li, M., Lin, S., Xu, H., Xiao, G.: Transformer-based multimodal emotional perception for dynamic facial expression recognition in the wild. IEEE Transactions on Circuits and Systems for Video Technology 34(5), 3192\u20133203 (2023)","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"4212_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Mao, Q., Zhang, J., Huang, X., Zheng, W.: Towards a robust group-level emotion recognition via uncertainty-aware learning. IEEE Transactions on Affective Computing (2025)","DOI":"10.1109\/TAFFC.2025.3547994"},{"key":"4212_CR4","doi-asserted-by":"crossref","unstructured":"Guo, W., Zhu, Q., Mao, Q.: Joint multi-scale contextual and noise suppression for group emotion recognition. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025). IEEE","DOI":"10.1109\/ICASSP49660.2025.10888975"},{"key":"4212_CR5","doi-asserted-by":"crossref","unstructured":"Wang, P., Zeng, S., Chen, J., Fan, L., Chen, M., Wu, Y., He, X.: Leveraging label information for multimodal emotion recognition. arXiv preprint arXiv:2309.02106 (2023)","DOI":"10.21437\/Interspeech.2023-1732"},{"key":"4212_CR6","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., Cambria, E., Morency, L.-P.: 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 (2018)"},{"key":"4212_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102218","volume":"105","author":"A Geetha","year":"2024","unstructured":"Geetha, A., Mala, T., Priyanka, D., Uma, E.: Multimodal emotion recognition with deep learning: advancements, challenges, and future directions. Information Fusion 105, 102218 (2024)","journal-title":"Information Fusion"},{"issue":"5","key":"4212_CR8","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1007\/s11760-021-02079-x","volume":"16","author":"P Sreevidya","year":"2022","unstructured":"Sreevidya, P., Veni, S., Ramana Murthy, O.: Elder emotion classification through multimodal fusion of intermediate layers and cross-modal transfer learning. Signal, image and video processing 16(5), 1281\u20131288 (2022)","journal-title":"Signal, image and video processing"},{"issue":"1","key":"4212_CR9","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11760-023-02707-8","volume":"18","author":"SS Hosseini","year":"2024","unstructured":"Hosseini, S.S., Yamaghani, M.R., Poorzaker Arabani, S.: Multimodal modelling of human emotion using sound, image and text fusion. Signal, Image and Video Processing 18(1), 71\u201379 (2024)","journal-title":"Signal, Image and Video Processing"},{"key":"4212_CR10","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.-P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"4212_CR11","doi-asserted-by":"crossref","unstructured":"Yang, J., Wang, Y., Yi, R., Zhu, Y., Rehman, A., Zadeh, A., Poria, S., Morency, L.-P.: 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 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"4212_CR12","doi-asserted-by":"crossref","unstructured":"Lv, C.-C., Zhang, X., Zhang, H.-B.: Visual audio and textual triplet fusion network for multi-modal sentiment analysis. Signal, Image and Video Processing, 1\u20139 (2024)","DOI":"10.1007\/s11760-024-03563-w"},{"key":"4212_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, M., Shen, J., Wang, C.: Tailor versatile multi-modal learning for multi-label emotion recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 9100\u20139108 (2022)","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"4212_CR14","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, R., Wang, Z., Hu, D.: Enhancing multimodal cooperation via sample-level modality valuation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 27338\u201327347 (2024)","DOI":"10.1109\/CVPR52733.2024.02581"},{"key":"4212_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, D., Ju, X., Li, J., Li, S., Zhu, Q., Zhou, G.: Multi-modal multi-label emotion detection with modality and label dependence. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3584\u20133593 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.291"},{"key":"4212_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, D., Ju, X., Zhang, W., Li, J., Li, S., Zhu, Q., Zhou, G.: Multi-modal multi-label emotion recognition with heterogeneous hierarchical message passing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 14338\u201314346 (2021)","DOI":"10.1609\/aaai.v35i16.17686"},{"key":"4212_CR17","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"4212_CR18","doi-asserted-by":"crossref","unstructured":"Ge, S., Jiang, Z., Cheng, Z., Wang, C., Yin, Y., Gu, Q.: Learning robust multi-modal representation for multi-label emotion recognition via adversarial masking and perturbation. In: Proceedings of the ACM Web Conference 2023, pp. 1510\u20131518 (2023)","DOI":"10.1145\/3543507.3583258"},{"key":"4212_CR19","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1016\/j.patcog.2004.03.009","volume":"37","author":"MR Boutell","year":"2004","unstructured":"Boutell, M.R., Luo, J., Shen, X., Brown, C.M.: Learning multi-label scene classification. Pattern Recognit. 37, 1757\u20131771 (2004)","journal-title":"Pattern Recognit."},{"key":"4212_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","volume":"3","author":"G Tsoumakas","year":"2007","unstructured":"Tsoumakas, G., Katakis, I.M.: Multi-label classification: An overview. Int. J. Data Warehous. Min. 3, 1\u201313 (2007)","journal-title":"Int. J. Data Warehous. Min."},{"key":"4212_CR21","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s10994-011-5256-5","volume":"85","author":"J Read","year":"2011","unstructured":"Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. Machine learning 85, 333\u2013359 (2011)","journal-title":"Machine learning"},{"key":"4212_CR22","unstructured":"Yang, P., Sun, X., Li, W., Ma, S., Wu, W., Wang, H.: SGM: sequence generation model for multi-label classification. In: International Conference on Computational Linguistics, pp. 3915\u20133926 (2018)"},{"key":"4212_CR23","doi-asserted-by":"crossref","unstructured":"Chen, Z.-M., Wei, X.-S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"4212_CR24","unstructured":"Hu, P., Li, X., Zhou, Y.: Shape: An unified approach to evaluate the contribution and cooperation of individual modalities. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 4032\u20134059 (2023)"},{"key":"4212_CR25","doi-asserted-by":"crossref","unstructured":"Parcalabescu, L., Frank, A.: MM-SHAP: A performance-agnostic metric for measuring multimodal contributions in vision and language models & tasks. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4032\u20134059 (2023)","DOI":"10.18653\/v1\/2023.acl-long.223"},{"key":"4212_CR26","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"4212_CR27","doi-asserted-by":"crossref","unstructured":"Shapley, L.S.: A value for n-person games. Contribution to the Theory of Games 2 (1953)","DOI":"10.1515\/9781400881970-018"},{"key":"4212_CR28","first-page":"4765","volume":"30","author":"M Scott","year":"2017","unstructured":"Scott, M., Su-In, L., et al.: A unified approach to interpreting model predictions. Advances in neural information processing systems 30, 4765\u20134774 (2017)","journal-title":"Advances in neural information processing systems"},{"key":"4212_CR29","unstructured":"Kenton, J.D.M.-W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol. 1, p. 2 (2019). Minneapolis, Minnesota"},{"issue":"4","key":"4212_CR30","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1511\/2001.28.344","volume":"89","author":"R Plutchik","year":"2001","unstructured":"Plutchik, R.: The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. American scientist 89(4), 344\u2013350 (2001)","journal-title":"American scientist"},{"key":"4212_CR31","doi-asserted-by":"crossref","unstructured":"Tsai, Y.-H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.-P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol. 2019, p. 6558 (2019). NIH Public Access","DOI":"10.18653\/v1\/P19-1656"},{"key":"4212_CR32","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: Misa: Modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"4212_CR33","unstructured":"Kingma, D.P.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04212-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04212-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04212-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T07:12:59Z","timestamp":1749625979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04212-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":33,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["4212"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04212-6","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"15 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No competing interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"626"}}