{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:51Z","timestamp":1775578671007,"version":"3.50.1"},"reference-count":112,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"State Key Laboratory of General Artificial Intelligence"},{"name":"School of Intelligence Science and Technology"},{"name":"Peking University, Beijing"},{"name":"Pazhou Laboratory"},{"name":"NSF China","award":["62276004"],"award-info":[{"award-number":["62276004"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFC3807600"],"award-info":[{"award-number":["2023YFC3807600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3453916","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T17:24:20Z","timestamp":1725384260000},"page":"11087-11103","source":"Crossref","is-referenced-by-count":5,"title":["Panoptic-PartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"first","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking Univeristy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7178-5358","authenticated-orcid":false,"given":"Shilin","family":"Xu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking Univeristy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-7231","authenticated-orcid":false,"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[{"name":"KAUST, Jeddah, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9770-7720","authenticated-orcid":false,"given":"Haobo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, Merced, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1428-8848","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8735-2516","authenticated-orcid":false,"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking Univeristy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1493-7569","authenticated-orcid":false,"given":"Zhouchen","family":"Lin","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, Peking Univeristy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, Merced, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.163"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064837"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00544"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00927"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5220\/0011616000003411"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00385"},{"key":"ref14","article-title":"Learning to fuse things and stuff","author":"Li","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00847"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6955"},{"key":"ref17","first-page":"20508","article-title":"Auto-panoptic: Cooperative multi-component architecture search for panoptic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref22","first-page":"5463","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref23","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01422"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00719"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00825"},{"key":"ref32","first-page":"28104","article-title":"Unsupervised part discovery from contrastive reconstruction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Choudhury"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00580"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.25"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00045"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240509"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00855"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211479"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.96"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"ref53","first-page":"9213","article-title":"Unsupervised part representation by flow capsules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sabour"},{"key":"ref54","article-title":"Unsupervised discovery of parts, structure, and dynamics","author":"Xu","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01465"},{"key":"ref58","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref59","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02034-6"},{"key":"ref61","first-page":"1","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref66","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref67","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref68","first-page":"21898","article-title":"SOLQ: Segmenting objects by learning queries","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_43"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref77","first-page":"993","article-title":"Densely connected multi-dilated convolutional networks for dense prediction tasks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Takahashi"},{"key":"ref78","first-page":"4514","article-title":"Pattern-structure diffusion for multi-task learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ling"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00152"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292995"},{"key":"ref84","first-page":"1","article-title":"TaskPrompter: Spatial-channel multi-task prompting for dense scene understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref89","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref92","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref93","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref94","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref95","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":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01445-z"},{"key":"ref97","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref105","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01333"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200416"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10663698.pdf?arnumber=10663698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:33:23Z","timestamp":1732667603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10663698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":112,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3453916","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":[[2024,12]]}}}