{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:54:24Z","timestamp":1775325264844,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB3104703"],"award-info":[{"award-number":["2022YFB3104703"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32341012"],"award-info":[{"award-number":["32341012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172103"],"award-info":[{"award-number":["62172103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3525526","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T19:23:13Z","timestamp":1735932193000},"page":"2723-2738","source":"Crossref","is-referenced-by-count":17,"title":["Instruction-Guided Scene Text Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3114-2188","authenticated-orcid":false,"given":"Yongkun","family":"Du","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-6889","authenticated-orcid":false,"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7743-8260","authenticated-orcid":false,"given":"Yuchen","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0650-9564","authenticated-orcid":false,"given":"Caiyan","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_20"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3545453"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/189"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref21","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref22","article-title":"TextMonkey: An OCR-free large multimodal model for understanding document","author":"Liu","year":"2024"},{"key":"ref23","article-title":"PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system","author":"Li","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01880-0"},{"key":"ref34","first-page":"2664","article-title":"Bidirectional scene text recognition with a single decoder","volume-title":"Proc. Eur. Conf. Artif. Intell.","author":"Bleeker"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_26"},{"key":"ref36","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46308-2_29"},{"key":"ref38","article-title":"Instruction-Following speech recognition","author":"Lai","year":"2023"},{"key":"ref39","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref42","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Deshmukh"},{"key":"ref43","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref44","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023"},{"key":"ref45","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/197"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref59","article-title":"Benchmarking Chinese text recognition: Datasets, baselines, and an empirical study","author":"Chen","year":"2021"},{"key":"ref60","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref62","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01097"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20062"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00448"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_27"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_19"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547784"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01790"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110244"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28402"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"ref84","article-title":"Grounding DINO 1.5: Advance the \u201cedge","author":"Ren","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10820836.pdf?arnumber=10820836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:41:59Z","timestamp":1741372919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10820836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":84,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3525526","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}