{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:50:09Z","timestamp":1785606609181,"version":"3.56.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["P0008740"],"award-info":[{"award-number":["P0008740"]}],"id":[{"id":"10.13039\/501100004377","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":[[2023,3,1]]},"DOI":"10.1109\/tpami.2022.3177813","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T19:39:27Z","timestamp":1653593967000},"page":"3522-3538","source":"Crossref","is-referenced-by-count":98,"title":["MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9905-8154","authenticated-orcid":false,"given":"Bruce X.B.","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4242-4840","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8667-2443","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7524-5999","authenticated-orcid":false,"given":"Sheng-hua","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science & Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1709-2637","authenticated-orcid":false,"given":"Keith C.C.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2011.6083628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"ref14","first-page":"1","article-title":"An introduction to sensor fusion","volume":"502","author":"Elmenreich","year":"2002","journal-title":"Vienna Univ. Technol., Austria"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2574712"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537340"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00059"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16430"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2012.2234129"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.110112.00192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.04.011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"ref38","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref40","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00558"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_22"},{"key":"ref47","first-page":"851","article-title":"Why cant i dance in the mall? learning to mitigate scene bias in action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"ref50","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Int. Conf. Mach. Learn.","author":"Ngiam"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.77"},{"key":"ref52","first-page":"1","article-title":"Human activity recognition with pose-driven attention to RGB","volume-title":"Proc. 29th Brit. Mach. Vis. Conf.","author":"Baradel"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref55","first-page":"1953","article-title":"Attention in convolutional LSTM for gesture recognition","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Zhang"},{"key":"ref56","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Xingjian"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.09.024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130379"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.98"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818328"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2017.8026285"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940281"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967577"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref73","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2785279"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2812099"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_13"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2017.8026283"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.115"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247822"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.333"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298860"},{"key":"ref87","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00241"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_39"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10036240\/09782511.pdf?arnumber=9782511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T19:45:21Z","timestamp":1736451921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9782511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":89,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3177813","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":[[2023,3,1]]}}}