{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:42:53Z","timestamp":1787017373471,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Science and Technology Commission of Shanghai Municipality Grant","award":["21511100101, 22511105901,22DZ2229004"],"award-info":[{"award-number":["21511100101, 22511105901,22DZ2229004"]}]},{"DOI":"10.13039\/501100006374","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0111000\/2021ZD0111004"],"award-info":[{"award-number":["2021ZD0111000\/2021ZD0111004"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658115","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"638-646","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["A Sentimental Prompt Framework with Visual Text Encoder for Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2057-5271","authenticated-orcid":false,"given":"Shizhou","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2083-4307","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5169","authenticated-orcid":false,"given":"Changqun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5451-8984","authenticated-orcid":false,"given":"Jiabo","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4110-8989","authenticated-orcid":false,"given":"Xin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University & Shanghai Key Laboratory of Multidimensional lnformation Processing, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1239"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1345"},{"key":"e_1_3_2_1_5_1","volume-title":"Tel Aviv","author":"Jia Menglin","year":"2022","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, and Ser-Nam Lim. 2022. Visual prompt tuning. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIII. Springer, 709--727."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_8_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_17_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_18_1","volume-title":"Language Modelling with Pixels. In The Eleventh International Conference on Learning Representations, ICLR","author":"Rust Phillip","year":"2023","unstructured":"Phillip Rust, Jonas F. Lotz, Emanuele Bugliarello, Elizabeth Salesky, Miryam de Lhoneux, and Desmond Elliott. 2023. Language Modelling with Pixels. In The Eleventh International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the conference. Association for Computational Linguistics. Meeting","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the conference. Association for Computational Linguistics. Meeting, Vol. 2019. NIH Public Access, 6558."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00129-1_24"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.287"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30675-4_40"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISI.2017.8004895"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133142"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210093"},{"key":"e_1_3_2_1_26_1","first-page":"5105","article-title":"Multi-level attention map network for multimodal sentiment analysis","volume":"35","author":"Xue Xiaojun","year":"2022","unstructured":"Xiaojun Xue, Chunxia Zhang, Zhendong Niu, and Xindong Wu. 2022. Multi-level attention map network for multimodal sentiment analysis. IEEE Transactions on Knowledge and Data Engineering, Vol. 35, 5 (2022), 5105--5118.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517139"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178204"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"},{"key":"e_1_3_2_1_33_1","volume-title":"Multimodal sentiment analysis with image-text interaction network","author":"Zhu Tong","year":"2022","unstructured":"Tong Zhu, Leida Li, Jufeng Yang, Sicheng Zhao, Hantao Liu, and Jiansheng Qian. 2022. Multimodal sentiment analysis with image-text interaction network. IEEE Transactions on Multimedia (2022)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658115","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:52:20Z","timestamp":1755766340000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658115"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":33,"alternative-id":["10.1145\/3652583.3658115","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658115","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}