{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:12:31Z","timestamp":1759331551160,"version":"build-2065373602"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2031"],"award-info":[{"award-number":["U23B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Postdoctoral Scientific Research Program Foundation","award":["2023B703"],"award-info":[{"award-number":["2023B703"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3586122","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:51:36Z","timestamp":1751637096000},"page":"6568-6580","source":"Crossref","is-referenced-by-count":0,"title":["Synthesizing Multi-Person and Rare Pose Images for Human Pose Estimation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7450-0462","authenticated-orcid":false,"given":"Liuqing","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Anhui University and the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]},{"given":"Zichen","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2452-3023","authenticated-orcid":false,"given":"Peng","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2689-317X","authenticated-orcid":false,"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00598"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026354"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488741"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/frvir.2020.00001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-022-01831-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"article-title":"Yolov4: Optimal speed and accuracy of object detection","year":"2020","author":"Bochkovskiy","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref16","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","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3326649"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3277758"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref20","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Qin","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3345180"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104134"},{"key":"ref23","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref24","first-page":"405","article-title":"Pose guided person image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ma","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01830"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref33","article-title":"Magicdrive: Street view generation with diverse 3D geometry control","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Gao","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00349"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547930"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3253048"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3330106"},{"article-title":"Improved regularization of convolutional neural networks with cutout","year":"2017","author":"DeVries","key":"ref38"},{"article-title":"Gridmask data augmentation","year":"2020","author":"Chen","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207578"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355461"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3591156.3591162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00399"},{"key":"ref44","article-title":"Unpaired pose guided human image generation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Chen","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00294"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01273"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103715"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547896"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00391"},{"key":"ref54","article-title":"VisorGPT: Learning visual prior via generative pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xie","year":"2023"},{"article-title":"Visual semantic role labeling","year":"2015","author":"Gupta","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_6"},{"article-title":"Rtmpose: Real-time multi-person pose estimation based on mmpose","year":"2023","author":"Jiang","key":"ref61"},{"key":"ref62","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xu","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00077"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_36"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582011"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11071880.pdf?arnumber=11071880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:09:52Z","timestamp":1759237792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3586122","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}