{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:16Z","timestamp":1774419676304,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889935","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["DiffMEL: A large-scale difficulty-graded dataset for Multimodal Entity Linking"],"prefix":"10.1109","author":[{"given":"Fang","family":"Wang","sequence":"first","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoying","family":"Bai","sequence":"additional","affiliation":[{"name":"Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Yan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Hu","sequence":"additional","affiliation":[{"name":"Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1186"},{"key":"ref2","first-page":"4285","article-title":"Building a multimodal entity linking dataset from tweets","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Adjali"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475400"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73197-7_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.328"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.178"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3233\/SW-222986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.152"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3233\/sw-180333"},{"issue":"3","key":"ref10","article-title":"The question answering systems: A survey","volume":"2","author":"Allam","year":"2012","journal-title":"International Journal of Research and Reviews in Information Sciences (IJRRIS)"},{"key":"ref11","first-page":"51","article-title":"Named entity recognition for question answering","volume-title":"Australasian Language Technology Association Workshop","author":"Moll\u00e1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref13","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref15","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref16","article-title":"Model merging in llms, mllms, and beyond: Methods, theories, applications and opportunities","author":"Yang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/math11081815"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1210"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6204"},{"key":"ref20","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref21","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref22","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref35","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889935.pdf?arnumber=10889935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:03Z","timestamp":1774416243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889935","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}