{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:32:52Z","timestamp":1742913172722,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8620-6_11","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"158-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ConD2: Contrastive Decomposition Distilling for Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Xi","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenti","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: Covarep\u2019a collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 960\u2013964 (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"11_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding (2018). arXiv:1810.04805"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Du, J., Jin, J., Zhuang, J., Zhang, C.: Hierarchical graph contrastive learning of local and global presentation for multimodal sentiment analysis. Sci. Rep. 14(1), 5335 (2024)","DOI":"10.1038\/s41598-024-54872-6"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis (2021). arXiv:2109.00412","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"11_CR5","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":"11_CR6","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Cui, Z.: Decoupled multimodal distilling for emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6631\u20136640 (2023)","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Weng, W., Liu, C.: Tscl-fhfn: two-stage contrastive learning and feature hierarchical fusion network for multimodal sentiment analysis. Neural Computing and Applications, pp. 1\u201315 (2024)","DOI":"10.1007\/s00521-024-09634-w"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Liang, T., Lin, G., Feng, L., Zhang, Y., Lv, F.: Attention is not enough: mitigating the distribution discrepancy in asynchronous multimodal sequence fusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8148\u20138156 (2021)","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Lu, Q., Sun, X., Gao, Z., Long, Y., Feng, J., Zhang, H.: Coordinated-joint translation fusion framework with sentiment-interactive graph convolutional networks for multimodal sentiment analysis. Inf. Process. Manag. 61(1), 103538 (2024)","DOI":"10.1016\/j.ipm.2023.103538"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Luo, Z., Hsieh, J.T., Jiang, L., Niebles, J.C., Fei-Fei, L.: Graph distillation for action detection with privileged modalities. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 166\u2013183 (2018)","DOI":"10.1007\/978-3-030-01264-9_11"},{"key":"11_CR12","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.procs.2017.01.157","volume":"104","author":"S Petrovica","year":"2017","unstructured":"Petrovica, S., Anohina-Naumeca, A., Ekenel, H.K.: Emotion recognition in affective tutoring systems: collection of ground-truth data. Proc. Comput. Sci. 104, 437\u2013444 (2017)","journal-title":"Proc. Comput. Sci."},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M.K., Lee, S., Zadeh, A., Mao, C., Morency, L.P., Hoque, E.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the conference. Association for Computational Linguistics. Meeting, vol.\u00a02020, p.\u00a02359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"11_CR14","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.\u00a02019, p.\u00a06558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"11_CR15","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., Salakhutdinov, R.: Learning factorized multimodal representations (2018). arXiv:1806.06176"},{"key":"11_CR16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.P.: Words can shift: dynamically adjusting word representations using nonverbal behaviors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Williams, J., Kleinegesse, S., Comanescu, R., Radu, O.: 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 (2018)","DOI":"10.18653\/v1\/W18-3302"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lin, Z., Zhao, Y., Qin, B., Zhu, L.N.: 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 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"11_CR20","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2021.09.041","volume":"467","author":"B Yang","year":"2022","unstructured":"Yang, B., Shao, B., Wu, L., Lin, X.: Multimodal sentiment analysis with unidirectional modality translation. Neurocomputing 467, 130\u2013137 (2022)","journal-title":"Neurocomputing"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Yang, J., Yu, Y., Niu, D., Guo, W., Xu, Y.: Confede: Contrastive feature decomposition for multimodal sentiment analysis. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7617\u20137630 (2023)","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Yi, G., Fan, C., Zhu, K., Lv, Z., Liang, S., Wen, Z., Pei, G., Li, T., Tao, J.: Vlp2msa: expanding vision-language pre-training to multimodal sentiment analysis. Knowl.-Based Syst. 283, 111136 (2024)","DOI":"10.1016\/j.knosys.2023.111136"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Meng, F., Zhu, Y., Ma, Y., Wu, J., Zou, J., Yang, K.: Ch-sims: A chinese multimodal sentiment analysis dataset with fine-grained annotation of modality. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp. 3718\u20133727 (2020)","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z., Wu, J.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI conference on artificial intelligence, vol.\u00a035, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhao, M., Qi, S.a., Sun, F., Wang, B., Guo, W., Wang, X., Yang, L., Niu, D.: Conki: Contrastive knowledge injection for multimodal sentiment analysis (2023). arXiv:2306.15796","DOI":"10.18653\/v1\/2023.findings-acl.860"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis (2017). arXiv:1707.07250","DOI":"10.18653\/v1\/D17-1115"},{"key":"11_CR28","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos (2016). arXiv:1606.06259"},{"key":"11_CR29","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":"11_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Yan, W., Mai, S., Hu, H.: Disentanglement translation network for multimodal sentiment analysis. Inf. Fusion 102, 102031 (2024)","DOI":"10.1016\/j.inffus.2023.102031"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., Peng, Y.: Better and faster: knowledge transfer from multiple self-supervised learning tasks via graph distillation for video classification (2018). arXiv:1804.10069","DOI":"10.24963\/ijcai.2018\/158"},{"key":"11_CR32","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.\u00a036, pp. 9100\u20139108 (2022)","DOI":"10.1609\/aaai.v36i8.20895"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8620-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:16:25Z","timestamp":1736885785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}