{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:09:58Z","timestamp":1765008598461,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002137"],"award-info":[{"award-number":["62002137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M711360"],"award-info":[{"award-number":["2022M711360"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771014","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Agent Framework for Fine-Grained Multimodal Named Entity Recognition through Check and Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5321-705X","authenticated-orcid":false,"given":"Heng-yang","family":"Lu","sequence":"first","affiliation":[{"name":"Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1089-8181","authenticated-orcid":false,"given":"Xintong","family":"Liu","sequence":"additional","affiliation":[{"name":"Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0316-0398","authenticated-orcid":false,"given":"Xingda","family":"Shang","sequence":"additional","affiliation":[{"name":"Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0750-4749","authenticated-orcid":false,"given":"Wei","family":"Fang","sequence":"additional","affiliation":[{"name":"Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-jun","family":"Wu","sequence":"additional","affiliation":[{"name":"Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.196"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Chenran Cai Qianlong Wang Bing Qin and Ruifeng Xu. 2024. A multi-task framework based on decomposition for multimodal named entity recognition. Neurocomputing 604 (2024) 128388. 10.1016\/j.neucom.2024.128388","DOI":"10.1016\/j.neucom.2024.128388"},{"key":"e_1_3_3_1_4_2","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Chakraborty Souradip","year":"2025","unstructured":"Souradip Chakraborty, Sujay Bhatt, Udari\u00a0Madhushani Sehwag, Soumya\u00a0Suvra Ghosal, Jiahao Qiu, Mengdi Wang, Dinesh Manocha, Furong Huang, Alec Koppel, and Sumitra Ganesh. 2025. Collab: Controlled Decoding using Mixture of Agents for LLM Alignment. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=7ohlQUbTpp"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.248"},{"key":"e_1_3_3_1_6_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_3_1_7_2","first-page":"53418","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Lei Bin","year":"2024","unstructured":"Bin Lei, Yi Zhang, Shan Zuo, Ali Payani, and Caiwen Ding. 2024. MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems. In Advances in Neural Information Processing Systems , Vol.\u00a037. Curran Associates, Inc., 53418\u201353437. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/5fcedec09977357f32e8e0ec8957073b-Paper-Conference.pdf"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681598"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240802"},{"key":"e_1_3_3_1_10_2","first-page":"7208","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Lu Feihong","year":"2024","unstructured":"Feihong Lu, Xiaocui Yang, Qian Li, Qingyun Sun, Ke Jiang, Cheng Ji, and Jianxin Li. 2024. Few-Shot Multimodal Named Entity Recognition Based on Multimodal Causal Intervention Graph. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ELRA and ICCL, 7208\u20137219. https:\/\/aclanthology.org\/2024.lrec-main.633\/"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.461"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V39I24.34711"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612322"},{"key":"e_1_3_3_1_14_2","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Wang Junlin","year":"2025","unstructured":"Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, and James Zou. 2025. Mixture-of-Agents Enhances Large Language Model Capabilities. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=h0ZfDIrj7T"},{"key":"e_1_3_3_1_15_2","first-page":"5776","volume-title":"Advances in Neural Information Processing Systems","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. In Advances in Neural Information Processing Systems , Vol.\u00a033. Curran Associates, Inc., 5776\u20135788. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.183"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755210"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.516"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Qi Zhang Jinlan Fu Xiaoyu Liu and Xuanjing Huang. 2018. Adaptive Co-attention Network for Named Entity Recognition in Tweets. Proceedings of the AAAI Conference on Artificial Intelligence 32 (2018). 10.1609\/aaai.v32i1.11962","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.101"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:07:47Z","timestamp":1765008467000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":20,"alternative-id":["10.1145\/3743093.3771014","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771014","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}