{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:42:04Z","timestamp":1770468124450,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819786190","type":"print"},{"value":"9789819786206","type":"electronic"}],"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_37","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"541-554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Cross-Modal Alignment in Multimodal Sentiment Analysis via Prompt Learning"],"prefix":"10.1007","author":[{"given":"Xiaofan","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-0907","authenticated-orcid":false,"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0519-7434","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9220-7501","authenticated-orcid":false,"given":"Chenyu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cai, H., Wan, X.: Multi-modal sarcasm detection in Twitter with hierarchical fusion model. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2506\u20132515. Association for Computational Linguistics, Florence, Italy (Jul 2019)","DOI":"10.18653\/v1\/P19-1239"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Huang, Y.: Sentiment analysis of microblog comments based on multi-feature fusion. In: Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence. ACAI \u201921, Association for Computing Machinery, New York, NY, USA (2022)","DOI":"10.1145\/3508546.3508636"},{"key":"37_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019)"},{"key":"37_CR4","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"issue":"10","key":"37_CR5","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.3390\/e25101421","volume":"25","author":"Q Guo","year":"2023","unstructured":"Guo, Q., Liao, Y., Li, Z., Liang, S.: Multi-modal representation via contrastive learning with attention bottleneck fusion and attentive statistics features. Entropy 25(10), 1421 (2023)","journal-title":"Entropy"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Hu, G., Lin, T.E., Zhao, Y., Lu, G., Wu, Y., Li, Y.: UniMSE: towards unified multimodal sentiment analysis and emotion recognition. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7837\u20137851. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022)","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Huang, F., Zhang, X., Zhao, Z., Xu, J., Li, Z.: Image-text sentiment analysis via deep multimodal attentive fusion. Know.-Based Syst. 167(C), 26\u201337 (Mar 2019)","DOI":"10.1016\/j.knosys.2019.01.019"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Huang, L., Ma, D., Li, S., Zhang, X., Wang, H.: Text level graph neural network for text classification. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) 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. 3444\u20133450. Association for Computational Linguistics, Hong Kong, China (Nov 2019)","DOI":"10.18653\/v1\/D19-1345"},{"key":"37_CR10","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1109\/ACCESS.2020.3048088","volume":"9","author":"Z Ke","year":"2021","unstructured":"Ke, Z., Sheng, J., Li, Z., Silamu, W., Guo, Q.: Knowledge-guided sentiment analysis via learning from natural language explanations. IEEE Access 9, 3570\u20133578 (2021)","journal-title":"IEEE Access"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H.A., Maaz, M., Khan, S.H., Khan, F.S.: Maple: multi-modal prompt learning. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19113\u201319122 (2022)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746\u20131751. Association for Computational Linguistics, Doha, Qatar (Oct 2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Li, Z., Sheng, J., Slamu, W.: Low-resource text classification via cross-lingual language model fine-tuning. In: China National Conference on Chinese Computational Linguistics, pp. 231\u2013246. Springer (2020)","DOI":"10.1007\/978-3-030-63031-7_17"},{"key":"37_CR14","doi-asserted-by":"publisher","first-page":"148489","DOI":"10.1109\/ACCESS.2020.3015854","volume":"8","author":"Z Li","year":"2020","unstructured":"Li, Z., Li, X., Sheng, J., Slamu, W.: Agglutifit: efficient low-resource agglutinative language model fine-tuning. IEEE Access 8, 148489\u2013148499 (2020)","journal-title":"IEEE Access"},{"key":"37_CR15","unstructured":"Li, Z., Mak, M.w., Lee, H.y., Meng, H.: Parameter-efficient fine-tuning of speaker-aware dynamic prompts for speaker verification"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Mak, M.W., Meng, H.M.L.: Dual parameter-efficient fine-tuning for speaker representation via speaker prompt tuning and adapters. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10751\u201310755. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447795"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., Xu, B., Zhu, C., Zhao, T.: CLMLF: a contrastive learning and multi-layer fusion method for multimodal sentiment detection. In: Carpuat, M., de Marneffe, M.C., Meza Ruiz, I.V. (eds.) Findings of the Association for Computational Linguistics: NAACL 2022, pp. 2282\u20132294. Association for Computational Linguistics, Seattle, United States (Jul 2022)","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Schifanella, R., de\u00a0Juan, P., Tetreault, J., Cao, L.: Detecting sarcasm in multimodal social platforms. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 1136\u20131145. MM \u201916, Association for Computing Machinery, New York, NY, USA (2016)","DOI":"10.1145\/2964284.2964321"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Xin, Y., Du, J., Wang, Q., Yan, K., Ding, S.: Mmap: multi-modal alignment prompt for cross-domain multi-task learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38(14), pp. 16076\u201316084 (Mar 2024)","DOI":"10.1609\/aaai.v38i14.29540"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Xu, N.: Analyzing multimodal public sentiment based on hierarchical semantic attentional network. In: 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), pp. 152\u2013154 (2017)","DOI":"10.1109\/ISI.2017.8004895"},{"key":"37_CR21","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. CIKM \u201917, Association for Computing Machinery, New York, NY, USA (2017)","DOI":"10.1145\/3132847.3133142"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W., Chen, G.: A co-memory network for multimodal sentiment analysis. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 929\u2013932. SIGIR \u201918, Association for Computing Machinery, New York, NY, USA (2018)","DOI":"10.1145\/3209978.3210093"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Xu, N., Zeng, Z., Mao, W.: Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3777\u20133786. Association for Computational Linguistics, Online (Jul 2020)","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"37_CR24","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","volume":"23","author":"X Yang","year":"2021","unstructured":"Yang, X., Feng, S., Wang, D., Zhang, Y.: Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans. Multimedia 23, 4014\u20134026 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Zhang, Y., Wang, D.: Multimodal sentiment detection based on multi-channel graph neural networks. 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. 328\u2013339. Association for Computational Linguistics, Online (Aug 2021)","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, J.: Adapting bert for target-oriented multimodal sentiment classification. In: International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/751"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhang, D.: Few-shot multi-modal sentiment analysis with prompt-based vision-aware language modeling. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhang, D., Li, S.: Unified multi-modal pre-training for few-shot sentiment analysis with prompt-based learning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 189\u2013198. MM \u201922, Association for Computing Machinery, New York, NY, USA (2022)","DOI":"10.1145\/3503161.3548306"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, P., Shi, W., Tian, J., Qi, Z., Li, B., Hao, H., Xu, B.: Attention-based bidirectional long short-term memory networks for relation classification. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 207\u2013212. Association for Computational Linguistics, Berlin, Germany (Aug 2016)","DOI":"10.18653\/v1\/P16-2034"}],"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_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:17:56Z","timestamp":1736885876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}