{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:14:19Z","timestamp":1784301259797,"version":"3.55.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2705700"],"award-info":[{"award-number":["2023YFC2705700"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFB4500600"],"award-info":[{"award-number":["2022YFB4500600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2048"],"award-info":[{"award-number":["U23B2048"]}],"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":["62076186"],"award-info":[{"award-number":["62076186"]}],"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":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovative Research Group Project of Hubei Province","award":["2024AFA017"],"award-info":[{"award-number":["2024AFA017"]}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2024BAB046"],"award-info":[{"award-number":["2024BAB046"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3495831","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:40:23Z","timestamp":1731350423000},"page":"1431-1447","source":"Crossref","is-referenced-by-count":35,"title":["Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4180-1096","authenticated-orcid":false,"given":"Maoyuan","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-8820","authenticated-orcid":false,"given":"Juhua","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6682-2877","authenticated-orcid":false,"given":"Chenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-6647","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0328-423X","authenticated-orcid":false,"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing & Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611755"},{"key":"ref3","first-page":"1","article-title":"UPOCR: Towards unified pixel-level OCR interface","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984082"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26293-7_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01856"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3286657"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","first-page":"29914","article-title":"Segment anything in high quality","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref26","article-title":"Sam-med2d","author":"Cheng","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28514"},{"key":"ref28","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref29","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref30","first-page":"8815","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/72"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00134"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00731"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.192"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00167"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-021-00380-6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref48","article-title":"DocSegTr: An instance-level end-to-end document image segmentation transformer","author":"Biswas","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235826"},{"key":"ref54","first-page":"18893","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379828"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00184"},{"key":"ref63","first-page":"25971","article-title":"Segment anything in 3D with NeRFs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cen"},{"key":"ref64","article-title":"Part to whole: Collaborative prompting for surgical instrument segmentation","author":"Yue","year":"2023"},{"key":"ref65","article-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","author":"Wu","year":"2023"},{"key":"ref66","first-page":"1","article-title":"Personalize segment anything model with one shot","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref67","first-page":"1","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref70","first-page":"12786","article-title":"TokenLearner: Adaptive space-time tokenization for videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ryoo"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref75","first-page":"17721","article-title":"SOLOV2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30508-6_20"},{"key":"ref77","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref79","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref82","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref84","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref85","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref86","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10750316.pdf?arnumber=10750316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:03:28Z","timestamp":1738821808000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10750316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":86,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3495831","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":[[2025,3]]}}}