{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:43:23Z","timestamp":1740102203356,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003213","name":"Beijing Municipal Education Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003213","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011160","name":"State Key Laboratory of Virtual Reality Technology and Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011160","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222631","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"515-519","source":"Crossref","is-referenced-by-count":0,"title":["Tell Your Story: Text-Driven Face Video Synthesis with High Diversity via Adversarial Learning"],"prefix":"10.1109","author":[{"given":"Xia","family":"Hou","sequence":"first","affiliation":[{"name":"Beijing Information Science and Technology University,Computer School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Information Science and Technology University,Computer School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenfeng","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing Information Science and Technology University,Computer School"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506487"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref5","first-page":"852","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras","year":"2021","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803830"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00243"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref16"},{"key":"ref17","first-page":"8748","volume-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref20","first-page":"27196","article-title":"Ufc-bert: Unifying multi-modal controls for conditional image synthesis","volume":"34","author":"Zhang","year":"2021","journal-title":"NIPS"},{"article-title":"Towards accurate generative models of video: A new metric & challenges","year":"2018","author":"Unterthiner","key":"ref21"},{"article-title":"Assessing generative models via precision and recall","year":"2018","author":"Sajjadi","key":"ref22"},{"key":"ref23","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NIPS"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222631.pdf?arnumber=10222631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T21:00:50Z","timestamp":1710363650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222631","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}