{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:09:23Z","timestamp":1775066963583,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210082","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Yuan","sequence":"first","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrong","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Li","sequence":"additional","affiliation":[{"name":"01.AI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Mo","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612526"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402242"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.381"},{"key":"ref7","article-title":"Multimodal question answering for unified information extraction","author":"Sun","year":"2023"},{"key":"ref8","article-title":"Ace 2005 multilingual training corpus","author":"Christopher","year":"2006","journal-title":"Linguistic Data Consortium, Philadelphia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_19"},{"key":"ref10","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.710"},{"key":"ref15","article-title":"Chain-of-thought prompt distillation for multi-modal named entity and multimodal relation extraction","author":"Chen","year":"2023"},{"key":"ref16","article-title":"Mm-bigbench: Evaluating multimodal models on multimodal content comprehension tasks","author":"Yang","year":"2023"},{"key":"ref17","first-page":"19 769","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210082.pdf?arnumber=11210082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:03:37Z","timestamp":1761890617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210082","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}