{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:46:05Z","timestamp":1778010365154,"version":"3.51.4"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031976346","type":"print"},{"value":"9783031976353","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-97635-3_25","type":"book-chapter","created":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T07:41:55Z","timestamp":1751701315000},"page":"207-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Sentiment Analysis Through Multimodal Fusion: A BERT-DINOv2 Approach"],"prefix":"10.1007","author":[{"given":"Taoxu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meisi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xucheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunal","family":"Chaturvedi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukesh","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Anaissi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Braytee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,6]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Bejan, I.: Memosys at semeval-2020 task 8: multimodal emotion analysis in memes. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp. 1172\u20131178 (2020)","DOI":"10.18653\/v1\/2020.semeval-1.155"},{"key":"25_CR2","doi-asserted-by":"publisher","unstructured":"Borth, D., Ji, R., Chen, T., Breuel, T., Chang, S.: Large-scale visual sentiment ontology and detectors using adjective noun pairs, pp. 223\u2013232 (2013). https:\/\/doi.org\/10.1145\/2502081.2502282","DOI":"10.1145\/2502081.2502282"},{"key":"25_CR3","doi-asserted-by":"publisher","unstructured":"Braytee, A., Yang, A.S.C., Anaissi, A., Chaturvedi, K., Prasad, M.: A novel dual-pipeline based attention mechanism for multimodal social sentiment analysis. In: Companion Proceedings of the ACM on Web Conference 2024, WWW \u201924, p. 18161822. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3589335.3651967","DOI":"10.1145\/3589335.3651967"},{"key":"25_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-3-319-25207-0_14","volume-title":"Natural Language Processing and Chinese Computing","author":"G Cai","year":"2015","unstructured":"Cai, G., Xia, B.: Convolutional neural networks for multimedia sentiment analysis. In: Li, J., Ji, H., Zhao, D., Feng, Y. (eds.) NLPCC -2015. LNCS (LNAI), vol. 9362, pp. 159\u2013167. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-25207-0_14"},{"key":"25_CR5","unstructured":"Das, S.D., Mandal, S.: Team neuro at semeval-2020 task 8: multi-modal fine grain emotion classification of memes using multitask learning. arXiv preprint arXiv:2005.10915 (2020)"},{"key":"25_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"25_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2021)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Guo, Y., Huang, J., Dong, Y., Xu, M.: Guoym at semeval-2020 task 8: ensemble-based classification of visuo-lingual metaphor in memes. In: Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp. 1120\u20131125 (2020)","DOI":"10.18653\/v1\/2020.semeval-1.148"},{"key":"25_CR9","doi-asserted-by":"publisher","unstructured":"Huang, F., Zhang, X., Zhao, Z., Xu, J., Li, Z.: Image-text sentiment analysis via deep multimodal attentive fusion. Knowl.-Based Syst. 167 (2019). https:\/\/doi.org\/10.1016\/j.knosys.2019.01.019","DOI":"10.1016\/j.knosys.2019.01.019"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Keswani, V., Singh, S., Agarwal, S., Modi, A.: Iitk at semeval-2020 task 8: unimodal and bimodal sentiment analysis of internet memes. arXiv preprint arXiv:2007.10822 (2020)","DOI":"10.18653\/v1\/2020.semeval-1.150"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Lee, S., Lai, B., Ryan, F., Boote, B., Rehg, J.M.: Modeling multimodal social interactions: new challenges and baselines with densely aligned representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14585\u201314595 (2024)","DOI":"10.1109\/CVPR52733.2024.01382"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Niu, T., Zhu, S., Pang, L., El-Saddik, A.: Sentiment analysis on multi-view social data. In: MultiMedia Modeling, p. 1527 (2016)","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"25_CR13","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Sharma, C., et al.: Task report: memotion analysis 1.0 @SemEval 2020: the visuo-lingual metaphor! In: Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval-2020). Association for Computational Linguistics, Barcelona (2020)","DOI":"10.18653\/v1\/2020.semeval-1.99"},{"key":"25_CR15","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 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Vo, N., et al.: Composing text and image for image retrieval-an empirical odyssey. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"25_CR17","doi-asserted-by":"publisher","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).https:\/\/doi.org\/10.1109\/ISI.2017.8004895","DOI":"10.1109\/ISI.2017.8004895"},{"key":"25_CR18","doi-asserted-by":"publisher","unstructured":"Xu, N., Mao, W.: Multisentinet: a deep semantic network for multimodal sentiment analysis, pp. 2399\u20132402 (2017). https:\/\/doi.org\/10.1145\/3132847.3133142","DOI":"10.1145\/3132847.3133142"},{"key":"25_CR19","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). https:\/\/api.semanticscholar.org\/CorpusID:199465957","DOI":"10.24963\/ijcai.2019\/751"},{"key":"25_CR20","doi-asserted-by":"publisher","unstructured":"Yu, Y., Lin, H., Meng, J., Zhao, Z.: Visual and textual sentiment analysis of a microblog using deep convolutional neural networks. Algorithms 9, 41 (2016). https:\/\/doi.org\/10.3390\/a9020041","DOI":"10.3390\/a9020041"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97635-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T07:42:01Z","timestamp":1751701321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97635-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031976346","9783031976353"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97635-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","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":"7 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}