{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:38:25Z","timestamp":1772807905906,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448507","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12647-12651","source":"Crossref","is-referenced-by-count":2,"title":["Relational Graph-Bridged Image-Text Interaction: A Novel Method for Multi-Modal Relation Extraction"],"prefix":"10.1109","author":[{"given":"Zihao","family":"Zheng","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}]},{"given":"Ruiji","family":"Fu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.50"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.190"},{"key":"ref3","first-page":"2370","article-title":"REBEL: Relation extraction by end-to-end language generation","volume-title":"EMNLP Findings","author":"Cabot"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.452"},{"key":"ref6","article-title":"A comprehensive survey on deep learning for relation extraction: Recent advances and new frontiers","author":"Xiaoyan","year":"2023"},{"key":"ref7","first-page":"3","article-title":"MNRE : A CHALLENGE MULTIMODAL DATASET FOR NEURAL RELATION","volume-title":"Icme","author":"Zheng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103264"},{"key":"ref11","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3345146"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"ref16","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"NeurIPS","volume":"34","author":"Nagrani"},{"key":"ref18","first-page":"7199","article-title":"Annotating the tweebank corpus on named entity recognition and building nlp models for social media analysis","volume-title":"LREC","author":"Jiang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref22","article-title":"Greaselm: Graph reasoning enhanced language models","volume-title":"ICLR","author":"Zhang"},{"key":"ref23","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498475"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.159"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1203"},{"key":"ref28","first-page":"2895","article-title":"Matching the blanks: Distributional similarity for relation learning","volume-title":"ACL","author":"Soares"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.5"},{"key":"ref30","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"NeurIPS","author":"Lu"},{"key":"ref31","author":"Sun","year":"2023","journal-title":"Multimodal question answering for unified information extraction"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29873"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612095"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448507.pdf?arnumber=10448507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:43:15Z","timestamp":1722660195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448507","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}