{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T05:16:45Z","timestamp":1778390205888,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3648143","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"4555-4564","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Contrastive Learning for Multimodal Classification of Crisis related Tweets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6686-2223","authenticated-orcid":false,"given":"Bishwas","family":"Mandal","sequence":"first","affiliation":[{"name":"Kansas State University, Manhattan, KS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7515-9433","authenticated-orcid":false,"given":"Sarthak","family":"Khanal","sequence":"additional","affiliation":[{"name":"Kansas State University, Manhattan, KS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6440-0914","authenticated-orcid":false,"given":"Doina","family":"Caragea","sequence":"additional","affiliation":[{"name":"Kansas State University, Manhattan, KS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01469"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_31"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3013558.3013571"},{"key":"e_1_3_2_2_6_1","volume-title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring. arxiv","author":"Berthelot David","year":"1911","unstructured":"David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel. 2020. ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring. arxiv: 1911.09785 [cs.LG]"},{"key":"e_1_3_2_2_7_1","volume-title":"COVID, and Military Multimodal Misinformation. arXiv preprint arXiv:2112.08594","author":"Biamby Giscard","year":"2021","unstructured":"Giscard Biamby, Grace Luo, Trevor Darrell, and Anna Rohrbach. 2021. Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation. arXiv preprint arXiv:2112.08594 (2021)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.repl4nlp-1.4"},{"key":"e_1_3_2_2_9_1","unstructured":"Minwoo Byeon Beomhee Park Haecheon Kim Sungjun Lee Woonhyuk Baek and Saehoon Kim. 2022. COYO-700M: Image-Text Pair Dataset. https:\/\/github.com\/kakaobrain\/coyo-dataset."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806236"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP50058.2020.00051"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811638"},{"key":"e_1_3_2_2_13_1","volume-title":"Le","author":"Cubuk Ekin D.","year":"2019","unstructured":"Ekin D. Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V. Le. 2019. RandAugment: Practical automated data augmentation with a reduced search space. arxiv: 1909.13719 [cs.CV]"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","unstructured":"Sergey Edunov Myle Ott Michael Auli and David Grangier. 2018. Understanding Back-Translation at Scale. https:\/\/doi.org\/10.48550\/ARXIV.1808.09381","DOI":"10.48550\/ARXIV.1808.09381"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-38"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.127"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301110"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.140"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3170897"},{"key":"e_1_3_2_2_21_1","volume-title":"Monitoring misinformation on Twitter during crisis events: a machine learning approach. Risk analysis","author":"Hunt Kyle","year":"2022","unstructured":"Kyle Hunt, Puneet Agarwal, and Jun Zhuang. 2022. Monitoring misinformation on Twitter during crisis events: a machine learning approach. Risk analysis, Vol. 42, 8 (2022), 1728--1748."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11069-020-04016-6"},{"key":"e_1_3_2_2_23_1","unstructured":"Chao Jia Yinfei Yang Ye Xia Yi-Ting Chen Zarana Parekh Hieu Pham Quoc V. Le Yunhsuan Sung Zhen Li and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. arxiv: 2102.05918 [cs.CV]"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2016.7425918"},{"key":"e_1_3_2_2_25_1","volume-title":"Lin (Eds.)","volume":"33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised Contrastive Learning. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 18661--18673. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/d89a66c7c80a29b1bdbab0f2a1a94af8-Paper.pdf"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/eScience51609.2021.00052"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7390-1"},{"key":"e_1_3_2_2_28_1","unstructured":"Yi Li Hualiang Wang Yiqun Duan and Xiaomeng Li. 2023. CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks. arxiv: 2304.05653 [cs.CV]"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09343-1"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02791-5"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Information Systems for Crisis Response and Management. https:\/\/api.semanticscholar.org\/CorpusID:78090471","author":"Mozannar Hussein","year":"2018","unstructured":"Hussein Mozannar, Yara Rizk, and Mariette Awad. 2018. Damage Identification in Social Media Posts using Multimodal Deep Learning. In International Conference on Information Systems for Crisis Response and Management. https:\/\/api.semanticscholar.org\/CorpusID:78090471"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2019.00040"},{"key":"e_1_3_2_2_33_1","volume-title":"Ng","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 2011. Multimodal Deep Learning. In ICML. 689--696. https:\/\/icml.cc\/2011\/papers\/399_icmlpaper.pdf"},{"key":"e_1_3_2_2_34_1","volume-title":"Analysis of social media data using multimodal deep learning for disaster response. arXiv preprint arXiv:2004.11838","author":"Ofli Ferda","year":"2020","unstructured":"Ferda Ofli, Firoj Alam, and Muhammad Imran. 2020. Analysis of social media data using multimodal deep learning for disaster response. arXiv preprint arXiv:2004.11838 (2020)."},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022","author":"Pranesh Raj","year":"2022","unstructured":"Raj Pranesh. 2022. Exploring Multimodal Features and Fusion Strategies for Analyzing Disaster Tweets. In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). Association for Computational Linguistics, Gyeongju, Republic of Korea, 62--68. https:\/\/aclanthology.org\/2022.wnut-1.6"},{"key":"e_1_3_2_2_36_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_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3294474"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04040-8"},{"key":"e_1_3_2_2_39_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arxiv","author":"Sanh Victor","year":"1910","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2020. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arxiv: 1910.01108 [cs.CL]"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671427"},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 2711--2723","author":"Sirbu Iustin","year":"2022","unstructured":"Iustin Sirbu, Tiberiu Sosea, Cornelia Caragea, Doina Caragea, and Traian Rebedea. 2022. Multimodal Semi-supervised Learning for Disaster Tweet Classification. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 2711--2723. https:\/\/aclanthology.org\/2022.coling-1.239"},{"key":"e_1_3_2_2_42_1","volume-title":"Weinberger (Eds.)","volume":"26","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. 2013. Zero-Shot Learning Through Cross-Modal Transfer. In Advances in Neural Information Processing Systems, C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Vol. 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2013\/file\/2d6cc4b2d139a53512fb8cbb3086ae2e-Paper.pdf"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","unstructured":"Kihyuk Sohn David Berthelot Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang and Colin Raffel. 2020. FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. https:\/\/doi.org\/10.48550\/ARXIV.2001.07685","DOI":"10.48550\/ARXIV.2001.07685"},{"key":"e_1_3_2_2_44_1","volume-title":"The 18th International Conference on Information Systems for Crisis Response and Management (ISCRAM","author":"Sosea Tiberiu","year":"2021","unstructured":"Tiberiu Sosea, Iustin Sirbu, Cornelia Caragea, Doina Caragea, and Traian Rebedea. 2021. Using the Image-Text Relationship to Improve Multimodal Disaster Tweet Classification. In The 18th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2021)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6201"},{"key":"e_1_3_2_2_46_1","volume-title":"Seon Ho Kim, and Cyrus Shahabi","author":"To Hien","year":"2017","unstructured":"Hien To, Sumeet Agrawal, Seon Ho Kim, and Cyrus Shahabi. 2017. On identifying disaster-related tweets: Matching-based or learning-based?. In 2017 IEEE third international conference on multimedia big data (BigMM). IEEE, 330--337."},{"key":"e_1_3_2_2_47_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9, 86 (2008), 2579--2605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_48_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.562"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.socscimed.2019.112552"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1901.11196"},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-646"},{"key":"e_1_3_2_2_55_1","volume-title":"ISCRAM 2020 Conference Proceedings--17th International Conference on Information Systems for Crisis Response and Management.","author":"Xukun Li","year":"2020","unstructured":"Li Xukun and Doina Caragea. 2020. Improving Disaster-related Tweet Classification with a Multimodal Approach. In ISCRAM 2020 Conference Proceedings--17th International Conference on Information Systems for Crisis Response and Management."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-016-1151-4"},{"key":"e_1_3_2_2_57_1","unstructured":"Boogeo Yoon Youhan Lee and Woonhyuk Baek. 2022. COYO-ALIGN. https:\/\/github.com\/kakaobrain\/coyo-align."},{"key":"e_1_3_2_2_58_1","unstructured":"Jianfei Yu and Jing Jiang. 2019. Adapting BERT for target-oriented multimodal sentiment classification. IJCAI."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1901.04889"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi10100636"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3648143","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3648143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:28:41Z","timestamp":1755822521000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3648143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":60,"alternative-id":["10.1145\/3589334.3648143","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3648143","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}