{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:01Z","timestamp":1792786921759,"version":"4.5.0"},"reference-count":129,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62561002"],"award-info":[{"award-number":["62561002"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Ningxia Natural Science Foundation Project","award":["2025AAC020006"],"award-info":[{"award-number":["2025AAC020006"]}]},{"name":"Ningxia Leading Talent Cultivation Project for Science and Technology","award":["2025GKLRLX26"],"award-info":[{"award-number":["2025GKLRLX26"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3701328","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:52:16Z","timestamp":1781034736000},"page":"12776-12798","source":"Crossref","is-referenced-by-count":0,"title":["Single-Stage Instance Segmentation Survey: A \u201c1+2+3\u201d Technical Framework"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8145-712X","authenticated-orcid":false,"given":"Tao","family":"Zhou","sequence":"first","affiliation":[{"name":"North Minzu University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4926-6535","authenticated-orcid":false,"given":"Defang","family":"Chang","sequence":"additional","affiliation":[{"name":"North Minzu University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiling","family":"Lu","sequence":"additional","affiliation":[{"name":"Ningxia Medical University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8796-7416","authenticated-orcid":false,"given":"Wenwen","family":"Chai","sequence":"additional","affiliation":[{"name":"North Minzu University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6631-8939","authenticated-orcid":false,"given":"Ke","family":"Song","sequence":"additional","affiliation":[{"name":"North Minzu University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyu","family":"Shen","sequence":"additional","affiliation":[{"name":"North Minzu University","place":["Yinchuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3576857"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3571672"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552694"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111579"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3579469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085295"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00374"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3385980"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00399"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109165"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01629"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374073"},{"key":"ref28","article-title":"Depth-guided semi-supervised instance segmentation","author":"Chen","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01480"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104401"},{"issue":"3","key":"ref32","first-page":"1041","article-title":"A survey on instance segmentation: Recent advances and challenges","volume":"17","author":"Zhang","year":"2021","journal-title":"Int. J. Innov. Comput. Inf. Control"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-022-01407-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00592-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3456910"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01881"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref41","article-title":"CAST: Contrastive adaptation and distillation for semi-supervised instance segmentation","author":"Taghavi","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00273"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107215"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02274"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190782"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00307"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_35"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363054"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04981-0_24"},{"key":"ref51","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680960"},{"key":"ref53","first-page":"4053","article-title":"P2P: Transforming from point supervision to explicit visual prompt for object detection and segmentation","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Guo","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-26789-1"},{"key":"ref55","article-title":"PM-VIS: High-performance box-supervised video instance segmentation","author":"Yang","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246102"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00323"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.093"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00424"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01093"},{"key":"ref62","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00695"},{"key":"ref65","article-title":"Boosting box-supervised instance segmentation with pseudo depth","author":"Yu","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02363"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107724"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2969046"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIS49377.2020.9194856"},{"key":"ref76","article-title":"Learning spatial fusion for single-shot object detection","author":"Liu","year":"2019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01085"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102248"},{"key":"ref79","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref81","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00527"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3080324"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533399"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413048"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2024.108479"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647248"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10221951"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3180564"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3014297"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia49877.2020.9277350"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561693"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.112"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00097"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00626"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107194"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00722"},{"key":"ref107","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_17"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref111","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020058"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref114","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3474698"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00039"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11177-y"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3579214"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3436099"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02086"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3455551"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103717"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394850"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127830"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11555026.pdf?arnumber=11555026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:07:43Z","timestamp":1790262463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11555026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":129,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3701328","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":[[2026,10]]}}}