{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:36:30Z","timestamp":1784248590049,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62276196"],"award-info":[{"award-number":["No.62276196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei Key Laboratory of Big Data in Science and Technology (Wuhan Library of Chinese Academy of Science)","award":["No.20211h0437"],"award-info":[{"award-number":["No.20211h0437"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570485","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"958-966","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["Reducing the Bias of Visual Objects in Multimodal Named Entity Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9647-7203","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7924-8620","authenticated-orcid":false,"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology & Engineering Research Center of Digital Publishing Intelligent Service Technology, Ministry of Education, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7553-6916","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology & Engineering Research Center of Digital Publishing Intelligent Service Technology, Ministry of Education, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4303-9020","authenticated-orcid":false,"given":"Jianquan","family":"Liu","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Lei Jimmy","year":"2016","unstructured":"Lei Jimmy Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. CoRR, Vol. abs\/1607.06450 (2016)."},{"key":"e_1_3_2_1_2_1","volume-title":"Database Systems for Advanced Applications - 26th International Conference, DASFAA. 186--201.","author":"Chen Dawei","unstructured":"Dawei Chen, Zhixu Li, Binbin Gu, and Zhigang Chen. 2021a. Multimodal Named Entity Recognition with Image Attributes and Image Knowledge. In Database Systems for Advanced Applications - 26th International Conference, DASFAA. 186--201."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML. 1597--1607","author":"Chen Ting","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning, ICML. 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.483"},{"key":"e_1_3_2_1_5_1","volume-title":"Debiased Contrastive Learning. In Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, NeurIPS.","author":"Chuang Ching-Yao","year":"2020","unstructured":"Ching-Yao Chuang, Joshua Robinson, Yen-Chen Lin, Antonio Torralba, and Stefanie Jegelka. 2020. Debiased Contrastive Learning. In Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, NeurIPS."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. 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, NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_7_1","volume-title":"Bader","author":"Giorgi John M.","year":"2021","unstructured":"John M. Giorgi, Osvald Nitski, Bo Wang, and Gary D. Bader. 2021. DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP."},{"key":"e_1_3_2_1_8_1","volume-title":"Mask R-CNN. In 2017 IEEE International Conference on Computer Vision, ICCV. 2980--2988","author":"He Kaiming","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1 r, and Ross B. Girshick. 2017. Mask R-CNN. In 2017 IEEE International Conference on Computer Vision, ICCV. 2980--2988."},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 770--778","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 770--778."},{"key":"e_1_3_2_1_10_1","volume-title":"Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI. 13171--13179","author":"Kim Seonhoon","year":"2021","unstructured":"Seonhoon Kim, Seohyeong Jeong, Eunbyul Kim, Inho Kang, and Nojun Kwak. 2021. Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI. 13171--13179."},{"key":"e_1_3_2_1_11_1","volume-title":"The 2016 Conference of the North American","author":"Lample Guillaume","unstructured":"Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural Architectures for Named Entity Recognition. In The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT. 260--270."},{"key":"e_1_3_2_1_12_1","volume-title":"Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems, NeurIPS. 9694--9705","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven Chu-Hong Hoi. 2021b. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems, NeurIPS. 9694--9705."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL.","author":"Ma Xuezhe","unstructured":"Xuezhe Ma and Eduard H. Hovy. 2016. End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL."},{"key":"e_1_3_2_1_16_1","volume-title":"Self-Supervised Learning of Pretext-Invariant Representations. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 6706--6716","author":"Misra Ishan","unstructured":"Ishan Misra and Laurens van der Maaten. 2020. Self-Supervised Learning of Pretext-Invariant Representations. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 6706--6716."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML. 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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML. 8748--8763."},{"key":"e_1_3_2_1_19_1","volume-title":"Representing Text Chunks. In 9th Conference of the European Chapter of the Association for Computational Linguistics, EACL. 173--179","author":"Erik","unstructured":"Erik F. Tjong Kim Sang and Jorn Veenstra. 1999. Representing Text Chunks. In 9th Conference of the European Chapter of the Association for Computational Linguistics, EACL. 173--179."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL. 6558--6569","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 57th Conference of the Association for Computational Linguistics, ACL. 6558--6569."},{"key":"e_1_3_2_1_21_1","volume-title":"Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, NeurIPS. 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, NeurIPS. 5998--6008."},{"key":"e_1_3_2_1_22_1","volume-title":"CLEAR: Contrastive Learning for Sentence Representation. CoRR","author":"Wu Zhuofeng","year":"2020","unstructured":"Zhuofeng Wu, Sinong Wang, Jiatao Gu, Madian Khabsa, Fei Sun, and Hao Ma. 2020a. CLEAR: Contrastive Learning for Sentence Representation. CoRR, Vol. abs\/2012.15466."},{"key":"e_1_3_2_1_23_1","volume-title":"Multimodal Representation with Embedded Visual Guiding Objects for Named Entity Recognition in Social Media Posts. In The 28th ACM International Conference on Multimedia, MM. 1038--1046","author":"Wu Zhiwei","year":"2020","unstructured":"Zhiwei Wu, Changmeng Zheng, Yi Cai, Junying Chen, Ho-fung Leung, and Qing Li. 2020b. Multimodal Representation with Embedded Visual Guiding Objects for Named Entity Recognition in Social Media Posts. In The 28th ACM International Conference on Multimedia, MM. 1038--1046."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"e_1_3_2_1_26_1","volume-title":"Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI. 14347--14355","author":"Zhang Dong","year":"2021","unstructured":"Dong Zhang, Suzhong Wei, Shoushan Li, Hanqian Wu, Qiaoming Zhu, and Guodong Zhou. 2021. Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI. 14347--14355."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013398"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","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 Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570485","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":28,"alternative-id":["10.1145\/3539597.3570485","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570485","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}