{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:47:48Z","timestamp":1770331668354,"version":"3.49.0"},"reference-count":40,"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\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L221013"],"award-info":[{"award-number":["L221013"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2070"],"award-info":[{"award-number":["U20B2070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3398538","type":"journal-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T17:45:28Z","timestamp":1715190328000},"page":"1494-1498","source":"Crossref","is-referenced-by-count":10,"title":["Style-A-Video: Agile Diffusion for Arbitrary Text-Based Video Style Transfer"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-6584","authenticated-orcid":false,"given":"Nisha","family":"Huang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6433-2678","authenticated-orcid":false,"given":"Yuxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","article-title":"CreativeSynth: Creative blending and synthesis of visual arts based on multimodal diffusion","author":"Huang","year":"2024"},{"key":"ref4","first-page":"1","article-title":"Region-aware diffusion for zero-shot text-driven image editing","volume-title":"Proc. Comput. Vis. Media Conf.","author":"Huang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref6","article-title":"Imagen video: High dedfinition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3342645"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3165758"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3098230"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2805809"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3259164"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0320-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6905"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_37"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3230084"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/687"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3605548"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00821","article-title":"Video-P2p: Video editing with cross-attention control","author":"Liu","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548282"},{"key":"ref26","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref33","article-title":"Videocrafter: A toolkit for text-to-video generation and editing","author":"Zhang","year":"2023"},{"key":"ref34","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023"},{"key":"ref35","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"ref40","first-page":"1083","article-title":"Blind video temporal consistency via deep video prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lei","year":"2020"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10522878.pdf?arnumber=10522878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T09:37:48Z","timestamp":1731922668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3398538","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}