{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:57:38Z","timestamp":1781852258535,"version":"3.54.5"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2018AAA0101900"],"award-info":[{"award-number":["2018AAA0101900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3198011","type":"journal-article","created":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T19:28:16Z","timestamp":1660159696000},"page":"5649-5661","source":"Crossref","is-referenced-by-count":15,"title":["GeometryMotion-Transformer: An End-to-End Framework for 3D Action Recognition"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5183-8538","authenticated-orcid":false,"given":"Jiaheng","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1956-3367","authenticated-orcid":false,"given":"Jinyang","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877936"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref52","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","first-page":"2140","article-title":"Purely attention based local feature integration for video classification","volume":"44","author":"long","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref54","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3147032"},{"key":"ref19","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00062"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193290"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3105820"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3009499"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074240"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007331"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2963592"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00513"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00059"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref6","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"5099","article-title":"PointNet: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"qi","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.76"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.108"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref36","first-page":"1254","article-title":"Unsupervised learning of view-invariant action representations","author":"li","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2533389"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446289"},{"key":"ref2","article-title":"PSTNet: Point spatio-temporal convolution on point cloud sequences","author":"fan","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101847"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.050"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0893-6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_52"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09854132.pdf?arnumber=9854132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:09:16Z","timestamp":1701115756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9854132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3198011","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}