{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:18:19Z","timestamp":1783153099552,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792220","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"2707-2715","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0488-5741","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7857-9588","authenticated-orcid":false,"given":"Jingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-212X","authenticated-orcid":false,"given":"Decheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian Unviersity, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3448-2514","authenticated-orcid":false,"given":"Chunlei","family":"Peng","sequence":"additional","affiliation":[{"name":"Xidian Unviersity, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Spice: Semantic propositional image caption evaluation. In Computer Vision-ECCV 2016: 14th European Conference","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. Spice: Semantic propositional image caption evaluation. In Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V 14. Springer, 382-398."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_6_1","volume-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886","author":"Chu Xiangxiang","year":"2023","unstructured":"Xiangxiang Chu, Limeng Qiao, Xinyang Lin, Shuang Xu, Yang Yang, Yiming Hu, Fei Wei, Xinyu Zhang, Bo Zhang, Xiaolin Wei, et al., 2023. Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Boquan Zhou, Shichao Liu, and Ahmed E Hassan.","author":"Dong Ximing","year":"2024","unstructured":"Ximing Dong, Shaowei Wang, Dayi Lin, Gopi Krishnan Rajbahadur, Boquan Zhou, Shichao Liu, and Ahmed E Hassan. 2024. PromptExp: Multi-granularity Prompt Explanation of Large Language Models. arXiv preprint arXiv:2410.13073 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3246793"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658035"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"e_1_3_2_1_13_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00167"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_17_1","volume-title":"ICML 2025 Workshop on Reliable and Responsible Foundation Models. https:\/\/openreview.net\/forum?id=TsPUGxxEB4","author":"Pirogov Viacheslav","year":"2025","unstructured":"Viacheslav Pirogov. 2025. Visual Language Models as Zero-Shot Deepfake Detectors. In ICML 2025 Workshop on Reliable and Responsible Foundation Models. https:\/\/openreview.net\/forum?id=TsPUGxxEB4"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449978"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01823"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449809"},{"key":"e_1_3_2_1_23_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_25_1","volume-title":"HPT: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling. arXiv preprint arXiv:2408.14812","author":"Wang Yubin","year":"2024","unstructured":"Yubin Wang, Xinyang Jiang, De Cheng, Wenli Sun, Dongsheng Li, and Cairong Zhao. 2024. HPT: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling. arXiv preprint arXiv:2408.14812 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Wu Xun","year":"2023","unstructured":"Xun Wu, Shaohan Huang, and Furu Wei. 2023. Mole: Mixture of lora experts. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690238"},{"key":"e_1_3_2_1_28_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pAQzEY7M03","author":"Xu Zhipei","year":"2025","unstructured":"Zhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, and Jian Zhang. 2025. FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pAQzEY7M03"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110526"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2019.8806244"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887985"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095913"},{"key":"e_1_3_2_1_34_1","volume-title":"Common Sense Reasoning for Deep Fake Detection. arXiv preprint arXiv:2402.00126","author":"Zhang Yue","year":"2024","unstructured":"Yue Zhang, Ben Colman, Ali Shahriyari, and Gaurav Bharaj. 2024a. Common Sense Reasoning for Deep Fake Detection. arXiv preprint arXiv:2402.00126 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection. arXiv preprint arXiv:2409.09724","author":"Zhang Yaning","year":"2024","unstructured":"Yaning Zhang, Tianyi Wang, Zitong Yu, Zan Gao, Linlin Shen, and Shengyong Chen. 2024b. MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection. arXiv preprint arXiv:2409.09724 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning. arXiv preprint arXiv:2406.17770","author":"Zhao Xiangyu","year":"2024","unstructured":"Xiangyu Zhao, Xiangtai Li, Haodong Duan, Haian Huang, Yining Li, Kai Chen, and Hua Yang. 2024. MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning. arXiv preprint arXiv:2406.17770 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_39_1","volume-title":"Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models. CoRR","author":"Zhu Minjie","year":"2024","unstructured":"Minjie Zhu, Yichen Zhu, Xin Liu, Ning Liu, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Zhicai Ou, Feifei Feng, and Jian Tang. 2024. Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models. CoRR (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:45:53Z","timestamp":1783151153000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792220"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":40,"alternative-id":["10.1145\/3774904.3792220","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792220","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}