{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:50:03Z","timestamp":1744181403693,"version":"3.37.3"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/iccv48922.2021.00808","type":"proceedings-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T22:08:02Z","timestamp":1646086082000},"page":"8168-8177","source":"Crossref","is-referenced-by-count":19,"title":["Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection"],"prefix":"10.1109","author":[{"given":"Bingyao","family":"Yu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}]},{"given":"Wanhua","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}]}],"member":"263","reference":[{"article-title":"Deep video inpainting detection","year":"2021","author":"zhou","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7007"},{"article-title":"End-to-end video instance segmentation with transformers","year":"2020","author":"wang","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref31","article-title":"Tampered region localization of digital color images based on jpeg compression noise","author":"wang","year":"2010","journal-title":"IWDW"},{"key":"ref30","first-page":"108","article-title":"Axial-deeplab: Standalone axial-attention for panoptic segmentation","author":"wang","year":"2020","journal-title":"ECCV"},{"article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","year":"2020","author":"zheng","key":"ref37"},{"key":"ref36","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref34","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"2018","journal-title":"ICLRE"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref40","article-title":"A deep learning approach to patch-based image in-painting forensics","author":"zhu","year":"2018","journal-title":"SPIC"},{"article-title":"An image is worth 16x16 words:Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2202227"},{"key":"ref13","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","author":"frank","year":"2020","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1145\/2980179.2982398","article-title":"Temporally coherent completion of dynamic video","author":"huang","year":"2016","journal-title":"TOG"},{"key":"ref16","article-title":"Fighting fake news: Image splice detection via learned self-consistency","author":"huh","year":"2018","journal-title":"ECCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00839"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.39"},{"key":"ref4","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref27","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"ref29","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.09.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"article-title":"Pre-trained image processing transformer","year":"2020","author":"chen","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1576246.1531330"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.02.001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref24","article-title":"Context encoders:Feature learning by inpainting","author":"pathak","year":"2016","journal-title":"CVPR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2021,10,10]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9709627\/9709628\/09710661.pdf?arnumber=9710661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:33:57Z","timestamp":1658259237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9710661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv48922.2021.00808","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}