{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T11:06:52Z","timestamp":1759230412138},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"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\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,8]]},"DOI":"10.1109\/cscwd61410.2024.10580454","type":"proceedings-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T17:21:49Z","timestamp":1720632109000},"page":"2491-2496","source":"Crossref","is-referenced-by-count":1,"title":["Watch and Read! A Visual Relation-Aware and Textual Evidence Enhanced Model 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","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30675-4_40"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref8","first-page":"2830","article-title":"Categorizing and inferring the relationship between the text and image of twitter posts","volume-title":"ACL","author":"Alakananda"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.677"},{"article-title":"Visualbert: a simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref12"},{"key":"ref13","first-page":"16254","article-title":"On analyzing the role of image for visual-enhanced relation extraction","author":"Li","year":"2023","journal-title":"Student Abstract of AAAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"ref15","first-page":"1855","article-title":"Different data, different modalities! reinforced data splitting for effective multimodal information extraction from social media posts","volume-title":"ICCL","author":"Xu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1506"},{"key":"ref24","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language Understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1203"},{"key":"ref26","first-page":"2895","article-title":"Matching the blanks: distributional similarity for relation learning","volume-title":"ACL","author":"Soares"},{"article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"NIPS","author":"Lu","key":"ref27"},{"article-title":"Graph attention networks","volume-title":"ICLR","author":"Veli\u010dkovi\u0107","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"article-title":"Clipcap: clip prefix for image captioning","year":"2021","author":"Mokady","key":"ref31"}],"event":{"name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2024,5,8]]},"location":"Tianjin, China","end":{"date-parts":[[2024,5,10]]}},"container-title":["2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10579968\/10579982\/10580454.pdf?arnumber=10580454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:03:47Z","timestamp":1721279027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10580454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,8]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cscwd61410.2024.10580454","relation":{},"subject":[],"published":{"date-parts":[[2024,5,8]]}}}