{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:20:47Z","timestamp":1783437647467,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20200463"],"award-info":[{"award-number":["BK20200463"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of China","award":["62076133 and 62006117"],"award-info":[{"award-number":["62076133 and 62006117"]}]},{"DOI":"10.13039\/501100018541","name":"Natural Science Foundation of Jiangsu Province for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["BK20200018"],"award-info":[{"award-number":["BK20200018"]}],"id":[{"id":"10.13039\/501100018541","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612322","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"3934-3943","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Fine-Grained Multimodal Named Entity Recognition and Grounding with a Generative Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1827-1867","authenticated-orcid":false,"given":"Jieming","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3034-7998","authenticated-orcid":false,"given":"Ziyan","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8380-0609","authenticated-orcid":false,"given":"Jianfei","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7160-9620","authenticated-orcid":false,"given":"Li","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0621-1058","authenticated-orcid":false,"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4319"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 1036--1044","author":"Chen Long","year":"2021","unstructured":"Long Chen,Wenbo Ma, Jun Xiao, Hanwang Zhang, and Shih-Fu Chang. 2021. Refnms: Breaking proposal bottlenecks in two-stage referring expression grounding. In Proceedings of the AAAI Conference on Artificial Intelligence. 1036--1044."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.11"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_2_6_1","volume-title":"Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction. In Findings of the Association for Computational Linguistics: NAACL","author":"Chen Xiang","year":"2022","unstructured":"Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2022. Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction. In Findings of the Association for Computational Linguistics: NAACL 2022."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of NAACL. 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 NAACL. 4171--4186."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.248"},{"key":"e_1_3_2_2_11_1","volume-title":"Unsupervised named-entity extraction from the web: An experimental study. Artificial intelligence 165, 1","author":"Etzioni Oren","year":"2005","unstructured":"Oren Etzioni, Michael Cafarella, Doug Downey, Ana-Maria Popescu, Tal Shaked, Stephen Soderland, Daniel S Weld, and Alexander Yates. 2005. Unsupervised named-entity extraction from the web: An experimental study. Artificial intelligence 165, 1 (2005), 91--134."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219885"},{"key":"e_1_3_2_2_13_1","volume-title":"Measuring nominal scale agreement among many raters. Psychological bulletin 76, 5","author":"Fleiss Joseph L","year":"1971","unstructured":"Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin 76, 5 (1971), 378."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT). 188--196","author":"Gerguis Michel Naim","year":"2016","unstructured":"Michel Naim Gerguis, Cherif Salama, and M Watheq El-Kharashi. 2016. ASU: An Experimental Study on Applying Deep Learning in Twitter Named Entity Recognition.. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT). 188--196."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Kevin Gimpel Nathan Schneider Brendan O'Connor Dipanjan Das Daniel Mills Jacob Eisenstein Michael Heilman Dani Yogatama Jeffrey Flanigan and Noah A Smith. 2010. Part-of-speech tagging for twitter: Annotation features and experiments. Technical Report. Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science.","DOI":"10.21236\/ADA547371"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25971"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548427"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531753"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.519"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT).","author":"Limsopatham Nut","year":"2016","unstructured":"Nut Limsopatham and Nigel Collier. 2016. Bidirectional LSTM for Named Entity Recognition in Twitter Messages. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4421"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"26","author":"Ling Xiao","year":"2012","unstructured":"Xiao Ling and Daniel Weld. 2012. Fine-grained entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 26. 94--100."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.217"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.395"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of ACL.","author":"Ma Xuezhe","year":"2016","unstructured":"Xuezhe Ma and Eduard Hovy. 2016. End-to-end Sequence Labeling via Bidirectional LSTM-CNNs-CRF. In Proceedings of ACL."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1186"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1078"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/1596374.1596399"},{"key":"e_1_3_2_2_36_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_2_37_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","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 28 (2015)."},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of EMNLP. 1524--1534","author":"Ritter Alan","year":"2011","unstructured":"Alan Ritter, Sam Clark, Mausam, and Oren Etzioni. 2011. Named Entity Recognition in Tweets: An Experimental Study. In Proceedings of EMNLP. 1524--1534."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114101"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of 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 ACL. 6558--6569."},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of NAACL. 3176--3189","author":"Gui Min","year":"2022","unstructured":"XinyuWang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, TaoWang, Zhongqiang Huang, and Kewei Tu. 2022. ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition. In Proceedings of NAACL. 3176--3189."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_12"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413650"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498475"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.451"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.726"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548228"},{"key":"e_1_3_2_2_59_1","volume-title":"Boosting entity-aware image captioning with multi-modal knowledge graph. arXiv preprint arXiv:2107.11970","author":"Zhao Wentian","year":"2021","unstructured":"Wentian Zhao, Yao Hu, Heda Wang, Xinxiao Wu, and Jiebo Luo. 2021. Boosting entity-aware image captioning with multi-modal knowledge graph. arXiv preprint arXiv:2107.11970 (2021)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013398"},{"key":"e_1_3_2_2_62_1","first-page":"1","article-title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","volume":"01","author":"Zhu Xiangru","year":"2022","unstructured":"Xiangru Zhu, Zhixu Li, Xiaodan Wang, Xueyao Jiang, Penglei Sun, Xuwu Wang, Yanghua Xiao, and Nicholas Jing Yuan. 2022. Multi-Modal Knowledge Graph Construction and Application: A Survey. IEEE Transactions on Knowledge & Data Engineering 01 (2022), 1--20.","journal-title":"IEEE Transactions on Knowledge & Data Engineering"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612322","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:42Z","timestamp":1755820662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":62,"alternative-id":["10.1145\/3581783.3612322","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612322","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}