{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:41Z","timestamp":1740132881411,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA27030600"],"award-info":[{"award-number":["XDA27030600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2024.3486104","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:34:01Z","timestamp":1729791241000},"page":"6-10","source":"Crossref","is-referenced-by-count":0,"title":["DSTA: Reinforcing Vision-Language Understanding for Scene-Text VQA With Dual-Stream Training Approach"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0401-7216","authenticated-orcid":false,"given":"Yingtao","family":"Tan","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5049-8092","authenticated-orcid":false,"given":"Yingying","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3017632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01401"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859603"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547977"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611753"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26357"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref18","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref19","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref21","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref22","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3396705"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547942"},{"issue":"140","key":"ref26","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"article-title":"Exploring the limits of language modeling","year":"2016","author":"Jozefowicz","key":"ref27"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3178899"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.278"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475606"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16476"},{"article-title":"Tag: Boosting text-VQA via text-aware visual question-answer generation","year":"2022","author":"Wang","key":"ref34"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref35"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10734181.pdf?arnumber=10734181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T06:17:57Z","timestamp":1734416277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3486104","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}