{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:26:48Z","timestamp":1765499208926,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62302503"],"award-info":[{"award-number":["No.62302503"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NUDT Youth Independent Innovation Science Fund Project","award":["Grant No.ZK23-15"],"award-info":[{"award-number":["Grant No.ZK23-15"]}]},{"name":"Open Research Fund from State Key Laboratory of High Performance Computing of China","award":["Grant No.202401-09"],"award-info":[{"award-number":["Grant No.202401-09"]}]},{"name":"10th Youth Talent Support Program of the China Association for Science and Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761053","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"960-969","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Multimodal Entity Linking via Distillation and Multimodal Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1654-8615","authenticated-orcid":false,"given":"Jintao","family":"Huang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5790-8026","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7805-9471","authenticated-orcid":false,"given":"Shasha","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6647-8862","authenticated-orcid":false,"given":"Yuanxi","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2763-0577","authenticated-orcid":false,"given":"Ruochun","family":"Jin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_31"},{"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 et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25544"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_2_1_7_1","volume-title":"Named entity disambiguation for noisy text. arXiv preprint arXiv:1706.09147","author":"Eshel Yotam","year":"2017","unstructured":"Yotam Eshel, Noam Cohen, Kira Radinsky, Shaul Markovitch, Ikuya Yamada, and Omer Levy. 2017. Named entity disambiguation for noisy text. arXiv preprint arXiv:1706.09147 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017232"},{"key":"e_1_3_2_1_10_1","volume-title":"Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_11_1","volume-title":"mplug-docowl2: High-resolution compressing for ocr-free multi-page document understanding. arXiv preprint arXiv:2409.03420","author":"Hu Anwen","year":"2024","unstructured":"Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan, Ji Zhang, Qin Jin, Fei Huang, and Jingren Zhou. 2024b. mplug-docowl2: High-resolution compressing for ocr-free multi-page document understanding. arXiv preprint arXiv:2409.03420 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Teacher-student architecture for knowledge distillation: A survey. arXiv preprint arXiv:2308.04268","author":"Hu Chengming","year":"2023","unstructured":"Chengming Hu, Xuan Li, Dan Liu, Haolun Wu, Xi Chen, Ju Wang, and Xue Liu. 2023. Teacher-student architecture for knowledge distillation: A survey. arXiv preprint arXiv:2308.04268 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Multi-level Matching Network for Multimodal Entity Linking. arXiv preprint arXiv:2412.10440","author":"Hu Zhiwei","year":"2024","unstructured":"Zhiwei Hu, V\u00edctor Guti\u00e9rrez-Basulto, Ru Li, and Jeff Z Pan. 2024a. Multi-level Matching Network for Multimodal Entity Linking. arXiv preprint arXiv:2412.10440 (2024)."},{"key":"e_1_3_2_1_14_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR, 5583-5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International conference on machine learning. PMLR, 5583-5594."},{"key":"e_1_3_2_1_16_1","volume-title":"Improving entity linking by modeling latent relations between mentions. arXiv preprint arXiv:1804.10637","author":"Le Phong","year":"2018","unstructured":"Phong Le and Ivan Titov. 2018. Improving entity linking by modeling latent relations between mentions. arXiv preprint arXiv:1804.10637 (2018)."},{"key":"e_1_3_2_1_17_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"key":"e_1_3_2_1_18_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, Vol. 364 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.450"},{"key":"e_1_3_2_1_20_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599439"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1186"},{"key":"e_1_3_2_1_23_1","volume-title":"When does label smoothing help? Advances in neural information processing systems","author":"M\u00fcller Rafael","year":"2019","unstructured":"Rafael M\u00fcller, Simon Kornblith, and Geoffrey E Hinton. 2019. When does label smoothing help? Advances in neural information processing systems, Vol. 32 (2019)."},{"volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12173-12182","author":"Pang Guansong","key":"e_1_3_2_1_24_1","unstructured":"Guansong Pang, Cheng Yan, Chunhua Shen, Anton van den Hengel, and Xiao Bai. 2020. Self-trained deep ordinal regression for end-to-end video anomaly detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12173-12182."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_3_2_1_26_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_28_1","volume-title":"A mathematical theory of communication. The Bell system technical journal","author":"Shannon Claude E","year":"1948","unstructured":"Claude E Shannon. 1948. A mathematical theory of communication. The Bell system technical journal, Vol. 27, 3 (1948), 379-423."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024","author":"Shi Senbao","year":"2024","unstructured":"Senbao Shi, Zhenran Xu, Baotian Hu, and Min Zhang. 2024. Generative Multimodal Entity Linking. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 7654-7665. https:\/\/aclanthology.org\/2024.lrec-main.676\/"},{"key":"e_1_3_2_1_30_1","volume-title":"DWE: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking. arXiv preprint arXiv:2404.04818","author":"Song Shezheng","year":"2024","unstructured":"Shezheng Song, Shasha Li, Shan Zhao, Xiaopeng Li, Chengyu Wang, Jie Yu, Jun Ma, Tianwei Yan, Bin Ji, and Xiaoguang Mao. 2024a. DWE: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking. arXiv preprint arXiv:2404.04818 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29867"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.91"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.46"},{"key":"e_1_3_2_1_34_1","unstructured":"Qwen Team. 2025. Qwen2.5-VL. https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/211359"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531867"},{"key":"e_1_3_2_1_37_1","volume-title":"WikiDiverse: a multimodal entity linking dataset with diversified contextual topics and entity types. arXiv preprint arXiv:2204.06347","author":"Wang Xuwu","year":"2022","unstructured":"Xuwu Wang, Junfeng Tian, Min Gui, Zhixu Li, Rui Wang, Ming Yan, Lihan Chen, and Yanghua Xiao. 2022a. WikiDiverse: a multimodal entity linking dataset with diversified contextual topics and entity types. arXiv preprint arXiv:2204.06347 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Scalable zero-shot entity linking with dense entity retrieval. arXiv preprint arXiv:1911.03814","author":"Wu Ledell","year":"2019","unstructured":"Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2019a. Scalable zero-shot entity linking with dense entity retrieval. arXiv preprint arXiv:1911.03814 (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"Scalable zero-shot entity linking with dense entity retrieval. arXiv preprint arXiv:1911.03814","author":"Wu Ledell","year":"2019","unstructured":"Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2019b. Scalable zero-shot entity linking with dense entity retrieval. arXiv preprint arXiv:1911.03814 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612575"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73197-7_35"},{"key":"e_1_3_2_1_43_1","volume-title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. arXiv preprint arXiv:2406.01934","author":"Zhang Zefeng","year":"2024","unstructured":"Zefeng Zhang, Jiawei Sheng, Chuang Zhang, Yunzhi Liang, Wenyuan Zhang, Siqi Wang, and Tingwen Liu. 2024. Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. arXiv preprint arXiv:2406.01934 (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00114"},{"key":"e_1_3_2_1_45_1","volume-title":"Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective. arXiv preprint arXiv:2102.00650","author":"Zhou Helong","year":"2021","unstructured":"Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, and Qian Zhang. 2021. Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective. arXiv preprint arXiv:2102.00650 (2021)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.55524\/ijircst.2024.12.3.17"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:22:33Z","timestamp":1765498953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":46,"alternative-id":["10.1145\/3746252.3761053","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761053","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}