{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:15:39Z","timestamp":1777655739959,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0103501"],"award-info":[{"award-number":["2020AAA0103501"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475256","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T22:11:38Z","timestamp":1634595098000},"page":"3737-3745","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Combining Attention with Flow for Person Image Synthesis"],"prefix":"10.1145","author":[{"given":"Yurui","family":"Ren","sequence":"first","affiliation":[{"name":"Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubo","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas H.","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent America, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_2_2_2_1","volume-title":"Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096","author":"Brock Andrew","year":"2018"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00923"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_2_7_1","volume-title":"Generative adversarial networks. arXiv preprint arXiv:1406.2661","author":"Goodfellow Ian J","year":"2014"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01057"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00381"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01065"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294810"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"e_1_3_2_2_22_1","volume-title":"Joon Son Chung, and Andrew Zisserman","author":"Nagrani Arsha","year":"2017"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"e_1_3_2_2_25_1","volume-title":"Improved techniques for training gans. arXiv preprint arXiv:1606.03498","author":"Salimans Tim","year":"2016"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"e_1_3_2_2_27_1","volume-title":"Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation. arXiv preprint arXiv:2102.02972","author":"Tang Jilin","year":"2021"},{"key":"e_1_3_2_2_28_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454738"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454556"},{"key":"e_1_3_2_2_33_1","volume-title":"DwNet: Dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139","author":"Zablotskaia Polina","year":"2019"},{"key":"e_1_3_2_2_34_1","volume-title":"International conference on machine learning. PMLR, 7354--7363","author":"Zhang Han","year":"2019"},{"key":"e_1_3_2_2_35_1","volume-title":"PISE: Person Image Synthesis and Editing with Decoupled GAN. arXiv preprint arXiv:2103.04023","author":"Zhang Jinsong","year":"2021"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01130"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00245"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475256","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:17Z","timestamp":1750193297000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":39,"alternative-id":["10.1145\/3474085.3475256","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475256","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}