{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T04:26:01Z","timestamp":1744086361548,"version":"3.40.3"},"reference-count":42,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521756","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T20:19:21Z","timestamp":1743797961000},"page":"1652-1664","source":"Crossref","is-referenced-by-count":0,"title":["Cps-STS: Bridging the Gap Between Content and Position for Coarse-Point-Supervised Scene Text Spotter"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2727-4744","authenticated-orcid":false,"given":"Weida","family":"Chen","sequence":"first","affiliation":[{"name":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1917-9031","authenticated-orcid":false,"given":"Linfei","family":"Wang","sequence":"additional","affiliation":[{"name":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2462-6174","authenticated-orcid":false,"given":"Huafeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3180-0484","authenticated-orcid":false,"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-5273","authenticated-orcid":false,"given":"Dapeng","family":"Tao","sequence":"additional","affiliation":[{"name":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3107681"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092187"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01654-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222286"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"issue":"7","key":"ref9","first-page":"11899","article-title":"Text perceptron: Towards end-to-end arbitrary-shaped text spotting","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Qiao","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548266"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_15"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/34.24792"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"Pix2seq: A language modeling framework for object detection","year":"2021","author":"Chen","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548266"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171108"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146779"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129651"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01461"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_30"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16348"},{"article-title":"DEER: Detection-agnostic end-to-end recognizer for scene text spotting","year":"2022","author":"Kim","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547787"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10949660.pdf?arnumber=10949660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:19Z","timestamp":1744062979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521756","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}