{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T18:30:45Z","timestamp":1781375445368,"version":"3.54.1"},"reference-count":225,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0114900"],"award-info":[{"award-number":["2022ZD0114900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176006"],"award-info":[{"award-number":["62176006"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,4]]},"DOI":"10.1109\/tpami.2023.3330935","type":"journal-article","created":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T18:58:32Z","timestamp":1699469912000},"page":"2430-2449","source":"Crossref","is-referenced-by-count":88,"title":["Human Motion Generation: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-0259","authenticated-orcid":false,"given":"Wentao","family":"Zhu","sequence":"first","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0571-2659","authenticated-orcid":false,"given":"Xiaoxuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9030-4583","authenticated-orcid":false,"given":"Dongwoo","family":"Ro","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7170-277X","authenticated-orcid":false,"given":"Hai","family":"Ci","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8142-5470","authenticated-orcid":false,"given":"Jinlu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0065-8374","authenticated-orcid":false,"given":"Jiaxin","family":"Shi","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Company, Ltd., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1843-3180","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Arts, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Company, Ltd., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9888-6409","authenticated-orcid":false,"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/s0166-4115(97)80041-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/35086023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3371382.3378386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/robotics9040102"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3150507"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref14","article-title":"Human motion diffusion model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tevet"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref16","first-page":"14959","article-title":"HUMANISE: Language-conditioned human motion generation in 3D scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref18","first-page":"932","article-title":"A neural probabilistic language model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref19","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref20","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref24","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref28","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref30","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref31","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole"},{"key":"ref32","first-page":"31841","article-title":"GET3D: A generative model of high quality 3D textured shapes learned from images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/089892900562417"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1167\/2.5.2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandc.2012.04.006"},{"key":"ref46","volume-title":"Motion and Representation: The Language of Human Movement","author":"Sutil","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01113"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.045"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.177\/0278364920917446"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00051"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/s23052597"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14426"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102897"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3524497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2000.0897"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.002"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2035253"},{"key":"ref59","article-title":"Deep generative models on 3D representations: A survey","author":"Shi","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01273"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00059"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"ref65","article-title":"CMU graphics lab motion capture database","author":"Hodgins","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661273"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00781"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_12"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref73","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Radford"},{"key":"ref74","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref77","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref78","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"S\u00f8nderby"},{"key":"ref79","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref80","article-title":"What are diffusion models?","author":"Weng","year":"2021"},{"key":"ref81","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566606"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566607"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566605"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2006.00964.x"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459932"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_2"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548287"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref101","first-page":"18000","article-title":"Executing your commands via motion diffusion in latent space","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Xin"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref118","article-title":"Dancing to music","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref119","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"issue":"17","key":"ref121","first-page":"26","article-title":"GrooveNet: Real-time music-driven dance movement generation using artificial neural networks","volume":"8","author":"Alemi","year":"2017","journal-title":"Networks"},{"key":"ref122","first-page":"16","article-title":"Diversity of traditional dance expression in crete: Data collection, research questions, and method development","volume-title":"Proc. 1st Symp. ICTM Study Group Sound Movement Sci.","author":"Holzapfel"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547797"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548090"},{"key":"ref127","first-page":"9995","article-title":"You never stop dancing: Non-freezing dance generation via bank-constrained manifold projection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3163676"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58750-9_28"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_15"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475223"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450692"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00230"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14734"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3522618"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01203"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322961"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01981"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01983"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_15"},{"key":"ref165","first-page":"7356","article-title":"Contact-aware human motion forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref170","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3605-7_4"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856281"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/545261.545279"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409067"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925893"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"ref185","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_21"},{"key":"ref189","first-page":"501","article-title":"AIST dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Tsuchida"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1145\/2890493"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0380-4"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392410"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00539"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3271691"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508374"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.603"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref201","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01239"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00069"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00723"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01115"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073247"},{"key":"ref209","first-page":"83","article-title":"Fmdistance: A fast and effective distance function for motion capture data","volume-title":"Proc. Eurographics Conf.","author":"Onuma"},{"key":"ref210","article-title":"Fairmotion - Tools to load, process, and visualize motion capture data","author":"Gopinath","year":"2020"},{"key":"ref211","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.04.005"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"ref214","first-page":"35072","article-title":"Mutual information divergence: A unified metric for multimodal generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref215","volume-title":"The Rating of Chessplayers, Past and Present","author":"Elo","year":"1978"},{"key":"ref216","first-page":"15085","article-title":"Learning human motion representations: A unified perspective","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Zhu"},{"key":"ref217","article-title":"From isolated islands to pangea: Unifying semantic space for human action understanding","author":"Li","year":"2023"},{"key":"ref218","article-title":"ULIP-2: Towards scalable multimodal pre-training for 3D understanding","author":"Xue","year":"2023"},{"key":"ref219","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01382"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref224","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Szot"},{"key":"ref225","first-page":"80","article-title":"Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation","volume-title":"Proc. Conf. Robot Learn.","author":"Li"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10461350\/10313063.pdf?arnumber=10313063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:45:52Z","timestamp":1725903952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10313063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":225,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3330935","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":[[2024,4]]}}}