{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T01:17:37Z","timestamp":1787707057683,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060778","type":"print"},{"value":"9783032060785","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06078-5_30","type":"book-chapter","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T18:50:29Z","timestamp":1759171829000},"page":"526-541","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AMST: Alternating Multimodal Skip Training"],"prefix":"10.1007","author":[{"given":"Hugo Manuel Alves Henriques","family":"e Silva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Selpi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: Iemocap: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"issue":"4","key":"30_CR2","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: CREMA-D: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014). https:\/\/doi.org\/10.1109\/TAFFC.2014.2336244","journal-title":"IEEE Trans. Affect. Comput."},{"key":"30_CR3","doi-asserted-by":"publisher","unstructured":"Fan, Y., Xu, W., Wang, H., Wang, J., Guo, S.: PMR: prototypical modal rebalance for multimodal learning. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20029\u201320038 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01918","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Hasan, M.K., et al.: Ur-funny: a multimodal language dataset for understanding humor. arXiv preprint arXiv:1904.06618 (2019)","DOI":"10.18653\/v1\/D19-1211"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR6","doi-asserted-by":"publisher","unstructured":"Li, H., Li, X., Hu, P., Lei, Y., Li, C., Zhou, Y.: Boosting multi-modal model performance with adaptive gradient modulation. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22157\u201322167 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.02030","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Lin, X., et al.: Suppress and rebalance: towards generalized multi-modal face anti-spoofing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 211\u2013221 (2024)","DOI":"10.1109\/CVPR52733.2024.00028"},{"key":"30_CR8","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"30_CR9","doi-asserted-by":"publisher","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference,Proceedings of the Python in Science Conference (2014). https:\/\/doi.org\/10.25080\/majora-7b98e3ed-003","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"30_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-319-27674-8_2","volume-title":"MultiMedia Modeling","author":"T Niu","year":"2016","unstructured":"Niu, T., Zhu, S., Pang, L., Saddik, A.: Sentiment analysis on multi-view social data. In: Tian, Q., Sebe, N., Qi, G.-J., Huet, B., Hong, R., Liu, X. (eds.) MMM 2016. LNCS, vol. 9517, pp. 15\u201327. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-27674-8_2"},{"key":"30_CR11","doi-asserted-by":"publisher","unstructured":"Peng, X., Wei, Y., Deng, A., Wang, D., Hu, D.: Balanced multimodal learning via on-the-fly gradient modulation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8228\u20138237. IEEE Computer Society, Los Alamitos (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00806","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"30_CR12","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1109\/LSP.2021.3101421","volume":"28","author":"Y Sun","year":"2021","unstructured":"Sun, Y., Mai, S., Hu, H.: Learning to balance the learning rates between various modalities via adaptive tracking factor. IEEE Signal Process. Lett. 28, 1650\u20131654 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3101421","journal-title":"IEEE Signal Process. Lett."},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"30_CR14","doi-asserted-by":"publisher","unstructured":"Wang, W., Tran, D., Feiszli, M.: What makes training multi-modal classification networks hard? In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12692\u201312702 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01271","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"30_CR15","unstructured":"Wu, N., Jastrzebski, S., Cho, K., Geras, K.J.: Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 24043\u201324055. PMLR (2022)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W.: Multisentinet: a deep semantic network for multimodal sentiment analysis. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 2399\u20132402 (2017)","DOI":"10.1145\/3132847.3133142"},{"key":"30_CR17","doi-asserted-by":"publisher","unstructured":"Yao, Y., Mihalcea, R.: Modality-specific learning rates for effective multimodal additive late-fusion. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, pp. 1824\u20131834. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.143","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"30_CR18","doi-asserted-by":"publisher","unstructured":"Zhang, X., Yoon, J., Bansal, M., Yao, H.: Multimodal representation learning by alternating unimodal adaptation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 27446\u201327456. IEEE Computer Society, Los Alamitos (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02592","DOI":"10.1109\/CVPR52733.2024.02592"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06078-5_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:18:54Z","timestamp":1787703534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06078-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"ISBN":["9783032060778","9783032060785"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06078-5_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,30]]},"assertion":[{"value":"30 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}