{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:43Z","timestamp":1777865383525,"version":"3.51.4"},"reference-count":72,"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\/iccv51701.2025.01760","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18937-18947","source":"Crossref","is-referenced-by-count":1,"title":["LEGION: Learning to Ground and Explain for Synthetic Image Detection"],"prefix":"10.1109","author":[{"given":"Hengrui","family":"Kang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwei","family":"Wen","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Wen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyan","family":"Ye","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijia","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilin","family":"Feng","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baichuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Conghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356122"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref5","article-title":"Mj-bench: Is your multimodal reward model really a good judge for text-toimage generation?","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02208-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330866"},{"key":"ref9","first-page":"27","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01974"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"ref12","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Asap: Interpretable analysis and summarization of ai-generated image patterns at scale","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3141262"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02685"},{"key":"ref17","article-title":"Ffaa: Multimodal large language model based explainable open-world face forgery analysis assistant","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00996"},{"key":"ref24","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref25","article-title":"Forgerygpt: Multimodal large language model for explainable image forgery detection and localization","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Fakebench: Uncover the achilles\u2019 heels of fake images with large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00332"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref32","first-page":"4","article-title":"Synthetic photography detection: A visual guidance for identifying synthetic images created by ai","author":"Mathys","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00283"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2019.5.MWSF-532"},{"key":"ref35","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref36","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref38","article-title":"Sdxl: Improving latent diffusion mod-els for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref41","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.304"},{"key":"ref43","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"International conference on machine learning","author":"Sundararajan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref49","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Jetformer: An autoregressive generative model of raw images and text","author":"Tschannen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00240"},{"key":"ref52","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00703"},{"key":"ref55","article-title":"Spot the fake: Large multimodal model-based synthetic image detection with artifact explanation","author":"Wen","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref56","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","volume-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref58","article-title":"Fakeshield: Explainable image forgery detection and localization via multi-modal large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xu"},{"key":"ref59","article-title":"A sanity check for aigenerated image detection","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Yan"},{"key":"ref60","article-title":"Gpt-imgeval: A comprehensive benchmark for diagnosing gpt4o in image generation","author":"Yan","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Idea2img: Iterative self-refinement with gpt-4v (ision) for automatic image design and generation","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Loki: A comprehensive synthetic data detection benchmark using large multimodal models","author":"Ye","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"The Twelfth International Conference on Learning Representations","author":"You"},{"key":"ref64","article-title":"Interactive data synthesis for systematic vision adaptation via 11 ms -aigcs collaboration","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_23"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00697"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"ref70","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3398"}],"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\/11445122.pdf?arnumber=11445122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:19Z","timestamp":1777530199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01760","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}