{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:53:13Z","timestamp":1784137993242,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232021A-08"],"award-info":[{"award-number":["2232021A-08"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Informatization Development Special Project of Shanghai Municipal Commission of Economy and Information Technology","award":["202002009"],"award-info":[{"award-number":["202002009"]}]},{"name":"National Natural Science Foundation of China","award":["61906035"],"award-info":[{"award-number":["61906035"]}]},{"name":"Shanghai Sailing Program","award":["19YF1402300"],"award-info":[{"award-number":["19YF1402300"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498475","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"1215-1223","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":101,"title":["MAF: A General Matching and Alignment Framework for Multimodal Named Entity Recognition"],"prefix":"10.1145","author":[{"given":"Bo","family":"Xu","sequence":"first","affiliation":[{"name":"Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhou","family":"Huang","sequence":"additional","affiliation":[{"name":"Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaofeng","family":"Sha","sequence":"additional","affiliation":[{"name":"Fudan University &amp; Shanghai Key Laboratory of Intelligence Processing, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongya","family":"Wang","sequence":"additional","affiliation":[{"name":"Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer Normalization. stat , Vol. 1050 (2016), 21."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Dawei Chen Zhixu Li Binbin Gu and Zhigang Chen. 2021. Multimodal Named Entity Recognition with Image Attributes and Image Knowledge. In Database Systems for Advanced Applications. 186--201.","DOI":"10.1007\/978-3-030-73197-7_12"},{"key":"e_1_3_2_2_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_5_1","volume-title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning. In International Conference on Learning Representations .","author":"Gunel Beliz","year":"2020","unstructured":"Beliz Gunel, Jingfei Du, Alexis Conneau, and Veselin Stoyanov. 2020. Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning. In International Conference on Learning Representations ."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_8_1","volume-title":"Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)."},{"key":"e_1_3_2_2_9_1","volume-title":"Proc. of the 18th Intl. Conf. on Machine Learning (ICML-2001)","author":"Pereira Fernando C. N.","year":"2001","unstructured":"Fernando C. N. Pereira John D. Lafferty, Andrew McCallum. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proc. of the 18th Intl. Conf. on Machine Learning (ICML-2001) . 282--289."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414930"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the 2011 conference on empirical methods in natural language processing. 1524--1534","author":"Ritter Alan","year":"2011","unstructured":"Alan Ritter, Sam Clark, Oren Etzioni, et al. 2011. Named entity recognition in tweets: an experimental study. In Proceedings of the 2011 conference on empirical methods in natural language processing. 1524--1534."},{"key":"e_1_3_2_2_16_1","volume-title":"Representing text chunks. arXiv preprint cs\/9907006","author":"Sang Erik F","year":"1999","unstructured":"Erik F Sang and Jorn Veenstra. 1999. Representing text chunks. arXiv preprint cs\/9907006 (1999)."},{"key":"e_1_3_2_2_17_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_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"e_1_3_2_2_20_1","volume-title":"Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance. In Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Zhang Dong","year":"2021","unstructured":"Dong Zhang, Suzhong Wei, Shoushan Li, Hanqian Wu, Qiaoming Zhu, and Guodong Zhou. 2021 b. Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 14347--14355."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_2_23_1","volume-title":"Contrastive learning of medical visual representations from paired images and text. arXiv preprint arXiv:2010.00747","author":"Zhang Yuhao","year":"2020","unstructured":"Yuhao Zhang, Hang Jiang, Yasuhide Miura, Christopher D Manning, and Curtis P Langlotz. 2020. Contrastive learning of medical visual representations from paired images and text. arXiv preprint arXiv:2010.00747 (2020)."}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498475","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:19Z","timestamp":1750188679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":23,"alternative-id":["10.1145\/3488560.3498475","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498475","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}