{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T11:08:17Z","timestamp":1779102497606,"version":"3.51.4"},"reference-count":92,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01493","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":2,"title":["SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting"],"prefix":"10.1109","author":[{"given":"Paschalis","family":"Giakoumoglou","sequence":"first","affiliation":[{"name":"Aristotle University of Thessaloniki,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitrios","family":"Karageorgiou","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, CERTH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Symeon","family":"Papadopoulos","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, CERTH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panagiotis C.","family":"Petrantonakis","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6","article-title":"Mistral AI","year":"2025","journal-title":"Mistral small 3.1: Multimodal language model"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2011.2129512"},{"key":"ref3","first-page":"4","article-title":"Anthropic","volume-title":"Claude 3.5 sonnet","year":"2024"},{"key":"ref4","first-page":"6","article-title":"Anthropic","volume-title":"Claude 3.7 sonnet","year":"2025"},{"key":"ref5","first-page":"6","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3337714"},{"key":"ref7","first-page":"2","author":"Bengio","journal-title":"Convolutional networks for images, speech, and time-series,1997"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2005.1530171"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990497"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2024.11.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.2001.0487"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.09.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111934"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1642"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2218597"},{"key":"ref17","first-page":"6","author":"Comanici","year":"2025","journal-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713194"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01974"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2702738"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.976235"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00292"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2446943"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref27","first-page":"5678","article-title":"Brushnet: Plug-and-play image inpainting with user guidance","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ju","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00438"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2462368"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4692-1_51"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01617-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00839"},{"key":"ref35","first-page":"4","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.03.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189545"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9050858"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00650"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903181"},{"key":"ref43","first-page":"5","author":"Manukyan","year":"2024","journal-title":"Hd-painter: High-resolution prompt-faithful text-guided image inpainting"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS61860.2024.10810690"},{"key":"ref45","first-page":"7","author":"Mareen","year":"2024","journal-title":"Tgif: A text-guided image forgery dataset for deepfake detection"},{"key":"ref46","first-page":"3","author":"Ma\u00f1as","year":"2024","journal-title":"Improving text-to-image consistency via automatic prompt optimization"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref49","first-page":"2","author":"Nichol","year":"2022","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref50","first-page":"4","article-title":"OpenAI","year":"2023","journal-title":"Chatgpt-3.5"},{"key":"ref51","first-page":"5","article-title":"OpenAI","year":"2023","journal-title":"Chatgpt-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroscience.2014.09.051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref54","first-page":"5","volume":"3","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref55","first-page":"88218831","article-title":"Zero-shot text-to-image generation","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref56","first-page":"2","author":"Ramesh","year":"2021","journal-title":"Zero-shot text-to-image generation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.17"},{"key":"ref60","first-page":"1","author":"Saharia","year":"2022","journal-title":"Photorealistic text-to-image diffusion models with deep language understanding"},{"key":"ref61","first-page":"6","author":"Schuhmann","year":"2022","journal-title":"Laion-5b: An open large-scale dataset for training next generation image-text models"},{"key":"ref62","first-page":"2","author":"Simonyan","year":"2015","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00323"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00388"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3678884.3681890"},{"key":"ref68","first-page":"6","author":"Team","year":"2025","journal-title":"Gemma 3 technical report"},{"key":"ref69","first-page":"3","author":"Theis","year":"2024","journal-title":"What makes an image realistic?"},{"key":"ref70","first-page":"49","article-title":"Comofod - new database for copy-move forgery detection","volume-title":"Proceedings ELMAR-2013","author":"Tralic","year":"2013"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53311-2_15"},{"key":"ref72","first-page":"2","author":"Vaswani","year":"2023","journal-title":"Attention is all you need"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3002101"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075039"},{"key":"ref77","first-page":"6","volume":"3","author":"Wu","year":"2023","journal-title":"Q-align: Teaching 1 mms for visual scoring via discrete text-defined levels"},{"key":"ref78","first-page":"343","article-title":"Defakehop: A light-weight high-performance deepfake detector","volume":"24","author":"Wu","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2008.4620591"},{"key":"ref80","first-page":"5","volume":"4","author":"Ye","year":"2024","journal-title":"Loki: A comprehensive synthetic data detection benchmark using large multimodal models"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref82","first-page":"5","author":"Yu","year":"2023","journal-title":"Inpaint-anything: Segment meets inpaint"},{"key":"ref83","first-page":"5","author":"Yu","year":"2023","journal-title":"Inpaint anything: Segment anything meets image inpainting"},{"key":"ref84","first-page":"1","author":"Zhang","year":"2024","journal-title":"Text-to-image diffusion models in generative ai: A survey"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4829-0"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01352"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3225194"},{"key":"ref89","first-page":"3","author":"Zhong","year":"2023","journal-title":"Rich and poor texture contrast: A simple yet effective approach for ai-generated image detection"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.05.015"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02620-0"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444234.pdf?arnumber=11444234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:11Z","timestamp":1777613351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01493","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}