{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:20:30Z","timestamp":1765808430383,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176115,62376120,61936012"],"award-info":[{"award-number":["62176115,62376120,61936012"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680995","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"1379-1388","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Focus & Gating: A Multimodal Approach for Unveiling Relations in Noisy Social Media"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7133-2195","authenticated-orcid":false,"given":"Liang","family":"He","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5731-9963","authenticated-orcid":false,"given":"Hongke","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7678-103X","authenticated-orcid":false,"given":"Zhen","family":"Wu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8193-8344","authenticated-orcid":false,"given":"Jianbing","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4139-7337","authenticated-orcid":false,"given":"Xinyu","family":"Dai","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9859-6898","authenticated-orcid":false,"given":"Jiajun","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_3_1","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond.","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"In-context Learning for Few-shot Multimodal Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Cai Chenran","year":"2023","unstructured":"Chenran Cai, Qianlong Wang, Bin Liang, Bing Qin, Min Yang, Kam-Fai Wong, and Ruifeng Xu. 2023. In-context Learning for Few-shot Multimodal Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6--10, 2023, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, 2969--2979. https:\/\/aclanthology.org\/2023.findings-emnlp.196"},{"key":"e_1_3_2_1_5_1","volume-title":"Chain-of-thought prompt distillation for multimodal named entity and multimodal relation extraction. arXiv preprint arXiv:2306.14122","author":"Chen Feng","year":"2023","unstructured":"Feng Chen and Yujian Feng. 2023. Chain-of-thought prompt distillation for multimodal named entity and multimodal relation extraction. arXiv preprint arXiv:2306.14122 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.03521"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_9_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612209"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611899"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.27"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12061390"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I13.26987"},{"key":"e_1_3_2_1_16_1","volume-title":"VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR, Vol. abs\/1908.03557 (2019). showeprint[arXiv]1908.03557 http:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V38I12.29280"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645603"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--21348-0_30"},{"key":"e_1_3_2_1_20_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 13--23. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/c74d97b01eae257e44aa9d5bade97baf-Abstract.html"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--981--99--8429--9_32"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"key":"e_1_3_2_1_25_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579051.3579073"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.BDR.2020.100159"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V36I3.20174"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12--17","author":"Xu Bo","year":"2022","unstructured":"Bo Xu, Shizhou Huang, Ming Du, Hongya Wang, Hui Song, Chaofeng Sha, and Yanghua Xiao. 2022. Different Data, Different Modalities! Reinforced Data Splitting for Effective Multimodal Information Extraction from Social Media Posts. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12--17, 2022, Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics, 1855--1864. https:\/\/aclanthology.org\/2022.coling-1.160"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I3.25445"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V35I16.17687"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680995","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:35Z","timestamp":1750295855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":37,"alternative-id":["10.1145\/3664647.3680995","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680995","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}