{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:12Z","timestamp":1776888432038,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650770","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Exploiting Visual Relation and Multi-Grained Knowledge for Multimodal Relation Extraction"],"prefix":"10.1109","author":[{"given":"Qianru","family":"Shen","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailun","family":"Lin","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.559"},{"key":"ref3","article-title":"Visualbert: a simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30675-4_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.677"},{"key":"ref13","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref15","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.26987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"ref18","first-page":"1855","article-title":"Different data, different modalities! reinforced data splitting for effective multimodal information extraction from social media posts","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Xu"},{"key":"ref19","article-title":"Chain-of-Thought Prompt Distillation for Multimodal Named Entity and Multimodal Relation Extraction","author":"Chen","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00677"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1506"},{"key":"ref27","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1203"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1279"},{"key":"ref30","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref32","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML\u201923)","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref36","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","author":"Huang","year":"2023"},{"key":"ref37","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","author":"Chuang","year":"2023"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650770.pdf?arnumber=10650770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:58:51Z","timestamp":1725947931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650770","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}