{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T12:50:47Z","timestamp":1784292647639,"version":"3.55.0"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Deployment Program of the Chinese Academy of Sciences, China","award":["KGFZD-145-25-39"],"award-info":[{"award-number":["KGFZD-145-25-39"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272438"],"award-info":[{"award-number":["62272438"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L25700"],"award-info":[{"award-number":["L25700"]}],"id":[{"id":"10.13039\/501100004826","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":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3667694","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:57:38Z","timestamp":1771966658000},"page":"8000-8017","source":"Crossref","is-referenced-by-count":1,"title":["SAPNet++: Evolving Point-Prompted Instance Segmentation With Semantic and Spatial Awareness"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5708-7157","authenticated-orcid":false,"given":"Zhaoyang","family":"Wei","sequence":"first","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1636-463X","authenticated-orcid":false,"given":"Xumeng","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2997-1068","authenticated-orcid":false,"given":"Xuehui","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7084-9101","authenticated-orcid":false,"given":"Xue","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University (SJTU), Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3954-2387","authenticated-orcid":false,"given":"Guorong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-5152","authenticated-orcid":false,"given":"Zhenjun","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0454-3929","authenticated-orcid":false,"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science (UCAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref2","first-page":"17721","article-title":"SOLOV2: Dynamic and fast instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145407"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"ref11","first-page":"401","article-title":"H2RBox: Horizontal box annotation is all you need for oriented object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref12","first-page":"59137","article-title":"H2RBox-v2: Incorporating symmetry for boosting horizontal box supervised oriented object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00059"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_19"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00424"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_71"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363054"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00344"},{"key":"ref22","first-page":"6586","article-title":"Weakly supervised instance segmentation using the bounding box tightness prior","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Hsu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206511"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00147"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190782"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01583"},{"key":"ref32","first-page":"73016","article-title":"PointOBB-v2: Towards simpler, faster, and stronger single point supervised oriented object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02486-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01588"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01796"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00339"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01870"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00320"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109298"},{"key":"ref41","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":"ref42","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","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref48","article-title":"Fast segment anything","author":"Zhao","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref52","article-title":"Accuracy of segment-anything model (SAM) in medical image segmentation tasks","author":"He","year":"2023"},{"key":"ref53","article-title":"Segment anything model (SAM) enhanced pseudo labels for weakly supervised semantic segmentation","author":"Chen","year":"2023"},{"key":"ref54","article-title":"Segment anything is a good pseudo-label generator for weakly supervised semantic segmentation","author":"Jiang","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32347"},{"key":"ref56","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Krahenbuhl","year":"2011"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref58","article-title":"Gated CRF loss for weakly supervised semantic image segmentation","author":"Obukhov","year":"2019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref60","first-page":"29901","article-title":"Learnable tree filter for structure-preserving feature transform","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1956-0078686-7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083269"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01640"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1302"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref73","article-title":"iFormer: Integrating ConvNet and transformer for mobile application","author":"Zheng","year":"2025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00077"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02547-8"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02441-3"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02363"},{"key":"ref81","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lin","year":"2014"},{"key":"ref82","first-page":"303","article-title":"The Pascal visual object classes (VOC) challenge","volume-title":"Int. J. Comput. Vis.","volume":"88","author":"Everingham","year":"2010"},{"key":"ref83","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Zamir","year":"2019"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"ref85","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref88","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref90","first-page":"16797","article-title":"Comprehensive attention self-distillation for weakly-supervised object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Huang","year":"2020"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_18"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_18"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00434"},{"key":"ref94","article-title":"AsyInst: Asymmetric affinity with depthgrad and color for box-supervised instance segmentation","author":"Yang","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11408932.pdf?arnumber=11408932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:11Z","timestamp":1780948331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":94,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3667694","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":[[2026,7]]}}}