{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:23:14Z","timestamp":1782314594336,"version":"3.54.5"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102500"],"award-info":[{"award-number":["2018AAA0102500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3414935","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:49:28Z","timestamp":1718905768000},"page":"3907-3920","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-5770","authenticated-orcid":false,"given":"Xuehao","family":"Gao","sequence":"first","affiliation":[{"name":"Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8687-4427","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-6857","authenticated-orcid":false,"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-0596","authenticated-orcid":false,"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3508-1851","authenticated-orcid":false,"given":"Guo-Jun","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00624"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.045"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038362"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref6","first-page":"792","article-title":"Learning spatio-temporal structure from RGB-D videos for human activity detection and anticipation","volume-title":"Proc. ICML","author":"Koppula"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3032079"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2988287"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01483-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01306"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01305"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16321"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061073"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108708"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635968"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00958"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_15"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547956"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160401"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0168-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089380"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547811"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01102"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00634"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00655"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3139918"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3230249"},{"key":"ref38","first-page":"51","article-title":"Contrastive self-supervised learning for skeleton action recognition","volume-title":"Proc. NeurIPS Workshop","author":"Gao"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3252172"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127040"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"ref48","first-page":"14959","article-title":"HUMANISE: Language-conditioned human motion generation in 3D scenes","volume-title":"Proc. NeurIPS","volume":"35","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010742"},{"key":"ref54","first-page":"1","article-title":"Skeleton-graph: Long-term 3D motion prediction from 2D observations using deep spatio-temporal graph CNNs","volume-title":"Proc. ICCVW","author":"Mohamed"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27919"},{"key":"ref56","first-page":"1","article-title":"Stochastic multi-person 3D motion forecasting","volume-title":"Proc. ICLR","author":"Xu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160538"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3579359"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342324"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296446"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"ref63","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. ICML","author":"Sohl-Dickstein"},{"key":"ref64","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. NeurIPS","author":"Song"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref66","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref67","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186752"},{"key":"ref69","article-title":"Swap attention in spatiotemporal diffusions for text-to-video generation","author":"Wang","year":"2023","journal-title":"arXiv:2305.10874"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3352002"},{"key":"ref72","first-page":"1","article-title":"Human motion diffusion model","volume-title":"Proc. ICLR","author":"Tevet"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3238411"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"ref75","first-page":"7356","article-title":"Contact-aware human motion forecasting","volume-title":"Proc. NeurIPS","author":"Mao"},{"key":"ref76","first-page":"6036","article-title":"Multi-person 3D motion prediction with multi-range transformers","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"ref78","first-page":"589","article-title":"Staged contact-aware global human motion forecasting","volume-title":"Proc. BMVC","author":"Scofano"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01443"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10566611.pdf?arnumber=10566611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T04:33:27Z","timestamp":1719549207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10566611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3414935","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}