{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:35:58Z","timestamp":1778373358686,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62406319"],"award-info":[{"award-number":["No.62406319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Laboratory of Science and Technology on Blind Signal Processing","award":["No.23007522"],"award-info":[{"award-number":["No.23007522"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754868","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"121-130","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6941-7305","authenticated-orcid":false,"given":"Xinkui","family":"Lin","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2963-0914","authenticated-orcid":false,"given":"Yongxiu","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-3907","authenticated-orcid":false,"given":"Minghao","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9521-1416","authenticated-orcid":false,"given":"Shilong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0258-7840","authenticated-orcid":false,"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7924-0158","authenticated-orcid":false,"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6464-3203","authenticated-orcid":false,"given":"Yubin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.142"},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_3_1","unstructured":"Yue Cao Yangzhou Liu Zhe Chen Guangchen Shi Wenhai Wang Danhuai Zhao and Tong Lu. 2024. MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding. arXiv:2410.11829 [cs.CV] https:\/\/arxiv.org\/abs\/2410.11829"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3345146"},{"key":"e_1_3_2_1_6_1","first-page":"2292","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems -","volume":"2","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: lightspeed computation of optimal transport. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2 (Lake Tahoe, Nevada) (NIPS'13). Curran Associates Inc., Red Hook, NY, USA, 2292-2300."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC'04)","author":"Doddington George","year":"2004","unstructured":"George Doddington, Alexis Mitchell, Mark Przybocki, Lance Ramshaw, Stephanie Strassel, and Ralph Weischedel. 2004. The Automatic Content Extraction (ACE) Program - Tasks, Data, and Evaluation. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC'04), Maria Teresa Lino, Maria Francisca Xavier, F\u00e1tima Ferreira, Rute Costa, and Raquel Silva (Eds.). European Language Resources Association (ELRA), Lisbon, Portugal. https:\/\/aclanthology.org\/L04-1011\/"},{"key":"e_1_3_2_1_9_1","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. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_10_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Schelten et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1649"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612209"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680995"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611899"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.27"},{"key":"e_1_3_2_1_16_1","volume-title":"Yu","author":"Hu Xuming","year":"2023","unstructured":"Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, and Philip S. Yu. 2023c. Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379571"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.76"},{"key":"e_1_3_2_1_20_1","unstructured":"Jinyuan Li Ziyan Li Han Li Jianfei Yu Rui Xia Di Sun and Gang Pan. 2024a. Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation. arXiv:2406.07268 [cs.MM] https:\/\/arxiv.org\/abs\/2406.07268"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Lei Li Xiang Chen Shuofei Qiao Feiyu Xiong Huajun Chen and Ningyu Zhang. 2023a. On analyzing the role of image for visual-enhanced relation extraction (student abstract). In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'23\/IAAI'23\/EAAI'23). AAAI Press Article 1918 2 pages. doi:10.1609\/aaai.v37i13.26987","DOI":"10.1609\/aaai.v37i13.26987"},{"key":"e_1_3_2_1_22_1","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. arXiv:1908.03557 [cs.CV] https:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.572"},{"key":"e_1_3_2_1_24_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024b. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3666122.3667638"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645603"},{"key":"e_1_3_2_1_27_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. arXiv:1711.05101 [cs.LG] https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681367"},{"key":"e_1_3_2_1_29_1","unstructured":"Sina Moradi. 2025. A Survey on Algorithmic Developments in Optimal Transport Problem with Applications. arXiv:2501.06247 [cs.DS] https:\/\/arxiv.org\/abs\/2501.06247"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"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 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_32_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Yang Fan Kai Dang Mengfei Du Xuancheng Ren Rui Men Dayiheng Liu Chang Zhou Jingren Zhou and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv:2409.12191 [cs.CV] https:\/\/arxiv.org\/abs\/2409.12191"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.823"},{"key":"e_1_3_2_1_34_1","unstructured":"Lihe Yang Bingyi Kang Zilong Huang Zhen Zhao Xiaogang Xu Jiashi Feng and Hengshuang Zhao. 2024b. Depth Anything V2. arXiv:2406.09414 [cs.CV] https:\/\/arxiv.org\/abs\/2406.09414"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679883"},{"key":"e_1_3_2_1_36_1","volume-title":"Emergence of Segmentation with Minimalistic White-Box Transformers. In Conference on Parsimony and Learning (Proceedings of Machine Learning Research","volume":"93","author":"Yu Yaodong","year":"2024","unstructured":"Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu, Druv Pai, Sam Buchanan, and Yi Ma. 2024. Emergence of Segmentation with Minimalistic White-Box Transformers. In Conference on Parsimony and Learning (Proceedings of Machine Learning Research, Vol. 234), Yuejie Chi, Gintare Karolina Dziugaite, Qing Qu, Atlas Wang Wang, and Zhihui Zhu (Eds.). PMLR, 72-93. https:\/\/proceedings.mlr.press\/v234\/yu24a.html"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681219"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103264"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.376"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448507"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:38:48Z","timestamp":1765309128000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3754868","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754868","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}