{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T21:31:35Z","timestamp":1781472695696,"version":"3.54.1"},"reference-count":62,"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\/iccv51701.2025.01895","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20379-20389","source":"Crossref","is-referenced-by-count":1,"title":["Bridging the Gap Between Ideal and Real-World Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios"],"prefix":"10.1109","author":[{"given":"Chunxiao","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Normal University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiling","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boming","family":"Miao","sequence":"additional","affiliation":[{"name":"Beijing Normal University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Central University of Finance and Economics,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","volume-title":"Introducing the next generation of claude","year":"2024"},{"issue":"2","key":"ref3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356122"},{"key":"ref5","volume-title":"Real-time deepfake detection in the real-world","author":"Cavia","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref8","article-title":"DRCT: diffusion reconstruction contrastive training towards universal detection of diffusion generated images","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Chen","year":"2024"},{"key":"ref9","article-title":"A single simple patch is all you need for ai-generated image detection","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"ref13","first-page":"6","article-title":"Fourier spectrum discrepancies in deep network generated images","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Dzanic","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8685-5_9"},{"key":"ref15","first-page":"13","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Frank","year":"2020"},{"key":"ref16","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","volume-title":"grok-2","year":"2025"},{"key":"ref18","article-title":"Wildfake: A large-scale challenging dataset for ai-generated images detection","author":"Hong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","volume-title":"hunyuan-vision","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897820"},{"key":"ref21","article-title":"Evolution of detection performance throughout the online lifespan of synthetic images","author":"Karageorgiou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Progressive growing of gans for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref25","article-title":"Harnessing the power of large vision language models for synthetic image detection","author":"Keita","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658035"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_23"},{"key":"ref28","volume-title":"Flux","year":"2024"},{"key":"ref29","article-title":"Improving synthetic image detection towards generalization: An image transformation perspective","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Fakebench: Uncover the achilles\u2019 heels of fake images with large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"ref34","article-title":"Seeing is not always believing: benchmarking human and model perception of ai-generated images","author":"Lu","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897310"},{"key":"ref36","article-title":"Midjourney","year":"2024","journal-title":"Midjourney"},{"key":"ref37","volume-title":"moonshot-preview-vision","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3748"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref42","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00872"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref46","volume-title":"Shadows don\u2019t lie and lines can\u2019t bend generative models don\u2019t know projective geometry\u2026for now. CoRR, abs\/2311.17138","author":"Sarkar","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616588"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32772"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref52","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","first-page":"8692","article-title":"Efros","volume-title":"Cnn-generated images are surprisingly easy to spot\u2026 for now. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR","author":"Wang","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"ref56","article-title":"A sanity check for ai-generated image detection","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Yi: Open foundation models by 01. ai","author":"Young","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3233\/faia250925"},{"key":"ref61","volume-title":"Patchcraft: Exploring texture patch for efficient ai-generated image detection","author":"Zhong","year":"2024"},{"key":"ref62","article-title":"Genimage: A million-scale benchmark for detecting ai-generated image","author":"Zhu","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"}],"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\/11446079.pdf?arnumber=11446079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:40:06Z","timestamp":1777531206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01895","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}