{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:47:51Z","timestamp":1730213271033,"version":"3.28.0"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"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":["62176010,61771026,U21A20515,62172416,62376271"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2022131"],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.01190","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"12523-12533","source":"Crossref","is-referenced-by-count":0,"title":["UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization"],"prefix":"10.1109","author":[{"given":"Shuaibo","family":"Li","sequence":"first","affiliation":[{"name":"Beijing University of Technology"}]},{"given":"Wei","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}]},{"given":"Jianwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,MAIS"}]},{"given":"Shibiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}]},{"given":"Benchong","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,MAIS"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"37","article-title":"Principal component analysis","volume":"2","author":"Abdi","year":"1987","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HORA55278.2022.9799858"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2909827.2930786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2825953"},{"journal-title":"arXiv preprint","article-title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt","year":"2023","author":"Cao","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713194"},{"key":"ref12","first-page":"21898","article-title":"Solq: Segmenting objects by learning queries","volume":"34","author":"Dong","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3180556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625374"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"journal-title":"arXiv preprint","article-title":"An image is worth 16\u00d716 words: Trans-formers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2202227"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2190402"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00786"},{"journal-title":"arXiv e-prints","article-title":"PAIR- Diffusion: A Comprehensive Multimodal Object-Level Image Editor","year":"2023","author":"Goel","key":"ref20"},{"key":"ref21","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01974"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_19"},{"first-page":"209","article-title":"Machine learning techniques for image manipulation detection: A review and analysis","volume-title":"The International Conference on Recent Innovations in Computing","author":"Iqbal","key":"ref28"},{"journal-title":"arXiv preprint","article-title":"Object-centric slot diffusion","year":"2023","author":"Jiang","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"journal-title":"arXiv preprint","article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref31"},{"article-title":"The point where reality meets fantasy: Mixed adversarial generators for image splice detection","volume-title":"Advances in Neural Information Processing Systems.","year":"2019","author":"Kniaz","key":"ref32"},{"issue":"2","key":"ref33","first-page":"2","article-title":"A pictures worth","volume":"6","author":"Krawetz","year":"2007","journal-title":"Hacker Factor Solutions"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01617-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00839"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3130168"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189545"},{"article-title":"Decoupled weight de-cay regularization","volume-title":"International Conference on Learning Representations","year":"2018","author":"Loshchilov","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.02.001"},{"journal-title":"arXiv preprint","article-title":"Conditional generative adversarial nets","year":"2014","author":"Mirza","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"journal-title":"arXiv preprint","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW50321.2020.9096940"},{"journal-title":"arXiv preprint","article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref50","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2883588"},{"key":"ref55","first-page":"18310","article-title":"Object-stitch: Object compositing with diffusion model","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Song","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/2056305120903408"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","first-page":"2364","article-title":"Ob-jectformer for image manipulation detection and localization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3439723"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532339"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00977"},{"volume-title":"Detectron2.","year":"2019","author":"Wu","key":"ref63"},{"journal-title":"arXiv preprint","article-title":"Slotdiffusion: Object-centric generative modeling with diffusion models","year":"2023","author":"Wu","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01763"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102825"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247607"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00116"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7007"},{"journal-title":"arXiv preprint","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref72"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2024,6,16]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10658324.pdf?arnumber=10658324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T05:37:49Z","timestamp":1726810669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":72,"URL":"http:\/\/dx.doi.org\/10.1109\/cvpr52733.2024.01190","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}
