{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:38:04Z","timestamp":1774431484677,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62036005"],"award-info":[{"award-number":["62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK3490000006"],"award-info":[{"award-number":["WK3490000006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3361010","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:40:48Z","timestamp":1706812848000},"page":"4977-4992","source":"Crossref","is-referenced-by-count":13,"title":["Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6467-7112","authenticated-orcid":false,"given":"Kaidong","family":"Zhang","sequence":"first","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2495-3311","authenticated-orcid":false,"given":"Jialun","family":"Peng","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2806-4791","authenticated-orcid":false,"given":"Jingjing","family":"Fu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03000.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.141"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref19","article-title":"Decoupled spatial-temporal transformer for video inpainting","author":"Liu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_28"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3372454"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00560"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref31","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2437193"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_49"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/140954933"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982398"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00589"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015232"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"ref39","first-page":"1","article-title":"Learnable gated temporal shift module for deep video inpainting","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01618"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01420"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00281"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01431"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref50","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00211"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3013518"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_14"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref67","first-page":"1","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu"},{"key":"ref68","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref70","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_15"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_10"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref75","article-title":"The 2018 DAVIS challenge on video object segmentation","author":"Caelles","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref79","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10418551.pdf?arnumber=10418551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:55:10Z","timestamp":1719345310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":79,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3361010","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}