{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:24:30Z","timestamp":1779359070556,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["#A18A2b0046"],"award-info":[{"award-number":["#A18A2b0046"]}],"id":[{"id":"10.13039\/501100001348","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":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3161735","type":"journal-article","created":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T19:33:54Z","timestamp":1648064034000},"page":"2181-2192","source":"Crossref","is-referenced-by-count":76,"title":["Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2345","authenticated-orcid":false,"given":"Hehe","family":"Fan","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Lei","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref10","article-title":"PointRNN: Point recurrent neural network for moving point cloud processing","author":"Fan","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref12","article-title":"Pstnet: Point spatio-temporal convolution on point cloud sequences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058688"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/c.22.99"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref18","first-page":"1262","article-title":"Unsupervised learning of view-invariant action representations","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00062"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00934"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00548"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.76"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref33","article-title":"Tranquil clouds: Neural networks for learning temporally coherent features in point clouds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Prantl"},{"key":"ref34","first-page":"5099","article-title":"PointNet : Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref35","first-page":"13688","article-title":"CaSPR: Learning canonical spatiotemporal point cloud representations","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rempe"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref41","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref45","article-title":"Lagrangian fluid simulation with continuous convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ummenhofer"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33275-3_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00059"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.050"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref56","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351040"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09740525.pdf?arnumber=9740525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:06:02Z","timestamp":1705536362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9740525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3161735","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":[[2023,2,1]]}}}