{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:50:32Z","timestamp":1774893032056,"version":"3.50.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EFRI-1137172"],"award-info":[{"award-number":["EFRI-1137172"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIP-1343402"],"award-info":[{"award-number":["IIP-1343402"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1400802"],"award-info":[{"award-number":["IIS-1400802"]}],"id":[{"id":"10.13039\/100000001","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":[[2022,3,1]]},"DOI":"10.1109\/tpami.2020.3018491","type":"journal-article","created":{"date-parts":[[2020,8,21]],"date-time":"2020-08-21T20:17:38Z","timestamp":1598041058000},"page":"1638-1652","source":"Crossref","is-referenced-by-count":14,"title":["Unambiguous Text Localization, Retrieval, and Recognition for Cluttered Scenes"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6617-9582","authenticated-orcid":false,"given":"Xuejian","family":"Rong","sequence":"first","affiliation":[]},{"given":"Chucai","family":"Yi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4458-360X","authenticated-orcid":false,"given":"Yingli","family":"Tian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477575"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2013.2261083"},{"key":"ref3","article-title":"Cognitive neuroscience of visual object recognition","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/139"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00920"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref19","first-page":"2054","article-title":"ESIR: End-to-end scene text recognition via iterative image rectification","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Lu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00924"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2930176"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_33"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890248"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref36","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref38","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref41","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"ref43","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","volume-title":"Proc. 21st Int. Conf. Pattern Recognit.","author":"Wang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16865-4_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.07.009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref49","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Karpathy"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.12"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540072"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.213"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref63","first-page":"589","article-title":"Towards context-aware interaction recognition","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Zhuang"},{"key":"ref64","article-title":"Care about you: Towards large-scale human-centric visual relationship detection","author":"Zhuang","year":"2017"},{"key":"ref65","first-page":"852","article-title":"Visual relationship detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1023"},{"key":"ref68","first-page":"926","article-title":"Reasoning with neural tensor networks for knowledge base completion","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Socher"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref73","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-006-0014-0"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0237-z"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref89","article-title":"ICDAR 2015 text reading in the wild competition","author":"Zhou","year":"2015"},{"key":"ref90","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref91","article-title":"ICDAR 2017 Robust Reading Competition Website","year":"2017"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.581"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477645"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2016.7868622"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.180"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9703108\/9173716-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9703108\/09173716.pdf?arnumber=9173716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:44:28Z","timestamp":1704840268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9173716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":98,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3018491","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":[[2022,3,1]]}}}