{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:03:59Z","timestamp":1766138639163,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3382948","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T19:09:52Z","timestamp":1711652992000},"page":"7896-7911","source":"Crossref","is-referenced-by-count":4,"title":["Self-Calibration Flow Guided Denoising Diffusion Model for Human Pose Transfer"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3961-890X","authenticated-orcid":false,"given":"Yu","family":"Xue","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5185-1492","authenticated-orcid":false,"given":"Lai-Man","family":"Po","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9559-1055","authenticated-orcid":false,"given":"Wing-Yin","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1710-4408","authenticated-orcid":false,"given":"Haoxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Magic Light Inc., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2944-3501","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"406","article-title":"Pose guided person image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ma"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611989"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3282139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12040857"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00787"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072171"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3047095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3286841"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3059706"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3157146"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1511.08458"},{"key":"ref22","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref23","article-title":"HumanDiffusion: A coarse-to-fine alignment diffusion framework for controllable text-driven person image generation","author":"Zhang","year":"2022","journal-title":"arXiv:2211.06235"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref27","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref28","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Austin"},{"key":"ref29","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref30","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref31","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01767"},{"key":"ref34","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref35","article-title":"BBDM: Image-to-image translation with Brownian bridge diffusion models","author":"Li","year":"2022","journal-title":"arXiv:2205.07680"},{"key":"ref36","article-title":"The Swiss army knife for image-to-image translation: Multi-task diffusion models","author":"Wolleb","year":"2022","journal-title":"arXiv:2204.02641"},{"key":"ref37","article-title":"On the design fundamentals of diffusion models: A survey","author":"Chang","year":"2023","journal-title":"arXiv:2306.04542"},{"article-title":"Vaes meet diffusion models: Efficient and high-fidelity generation","volume-title":"Proc. Workshop Deep Generative Models Downstream Appl.","author":"Pandey","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref40","article-title":"UNIT-DDPM: UNpaired image translation with denoising diffusion probabilistic models","author":"Sasaki","year":"2021","journal-title":"arXiv:2104.05358"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3131738"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01317"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00110"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00027"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408360"},{"key":"ref50","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02081"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"ref61","article-title":"DwNet: Dense warp-based network for pose-guided human video generation","author":"Zablotskaia","year":"2019","journal-title":"arXiv:1910.09139"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10483084.pdf?arnumber=10483084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:38:28Z","timestamp":1736368708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10483084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":61,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3382948","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}