{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T19:03:15Z","timestamp":1781377395029,"version":"3.54.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610262","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9418-9425","source":"Crossref","is-referenced-by-count":21,"title":["Mask4Former: Mask Transformer for 4D Panoptic Segmentation"],"prefix":"10.1109","author":[{"given":"Kadir","family":"Yilmaz","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Computer Vision Group,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Schult","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Computer Vision Group,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexey","family":"Nekrasov","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Computer Vision Group,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Computer Vision Group,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"4D-Former: Multimodal 4D Panoptic Segmentation","volume-title":"Conference on Robot Learning","author":"Athar"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00548"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","article-title":"Mask2former for video instance segmentation","author":"Cheng","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"Cheng","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00319"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01289"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_34"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref25","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236568"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140439"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01119"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24670-1_3"},{"key":"ref33","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref35","article-title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","volume-title":"International Conference on Learning Representations","author":"Shen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref40","article-title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","author":"Tancik","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02055"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00981"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610262.pdf?arnumber=10610262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:19:51Z","timestamp":1723267191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610262","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}