{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T02:54:39Z","timestamp":1777085679592,"version":"3.51.4"},"reference-count":39,"publisher":"Tsinghua University Press","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222602,62302167,62176224,62106075,61972157"],"award-info":[{"award-number":["62222602,62302167,62176224,62106075,61972157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["23ZR1420400"],"award-info":[{"award-number":["23ZR1420400"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing, China","doi-asserted-by":"publisher","award":["CSTB2023NSCQ-JQX0007,CSTB2023NSCQ-MSX0137"],"award-info":[{"award-number":["CSTB2023NSCQ-JQX0007,CSTB2023NSCQ-MSX0137"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.26599\/cvm.2025.9450388","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T13:31:55Z","timestamp":1747315915000},"page":"497-511","source":"Crossref","is-referenced-by-count":8,"title":["Point Mask Transformer for Outdoor Point Cloud Semantic Segmentation"],"prefix":"10.26599","volume":"11","author":[{"given":"Xiangqian","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China,200062"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02413"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00459"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref6","article-title":"Cylinder3D: An effective 3D framework for driving-scene LiDAR semantic segmentation","author":"Zhou","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3453485"},{"key":"ref8","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems","author":"Cheng","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00735"},{"key":"ref17","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref19","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems","author":"Zhang","year":"2021"},{"key":"ref20","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems","author":"Xie","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00259"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00829"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","article-title":"AMVNet: Assertion-based multi-view fusion network for LiDAR semantic segmentation","author":"Liong","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11072531\/11005707.pdf?arnumber=11005707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:01Z","timestamp":1755910321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11005707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450388","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}