{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:41:43Z","timestamp":1771922503534,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859666","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Cross-Modal Attention Networks with Modality Disentanglement for Scene-Text VQA"],"prefix":"10.1109","author":[{"given":"Zeqin","family":"Fang","sequence":"first","affiliation":[{"name":"Wuhan University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongwei","family":"Xie","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref12","article-title":"Pythia-a platform for vision & language research","volume":"2018","author":"singh","year":"0","journal-title":"SysML Workshop NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.136"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref4","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"1563","article-title":"Icdar 2019 competition on scene text visual question answering","author":"biten","year":"0","journal-title":"2019 International Conference on Document Analysis and Recognition (ICDAR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859666.pdf?arnumber=9859666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:40Z","timestamp":1663619080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859666\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859666","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}