{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:31:40Z","timestamp":1784043100884,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755137","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"1327-1336","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7923-9329","authenticated-orcid":false,"given":"Jialei","family":"Cui","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6358-1904","authenticated-orcid":false,"given":"Jianwei","family":"Du","sequence":"additional","affiliation":[{"name":"Southeast University, Nangjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3652-7272","authenticated-orcid":false,"given":"Yanzhe","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9475-0280","authenticated-orcid":false,"given":"Lei","family":"Gao","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0306-6691","authenticated-orcid":false,"given":"Hui","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China and Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6484-1552","authenticated-orcid":false,"given":"Chenfu","family":"Bao","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. DeepFakes. www.github.com\/deepfakes\/faceswap. Accessed: 2021-04--24."},{"key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. DFD. https:\/\/ai.googleblog.com\/2019\/09\/contributing-data-to-deepfakedetection.html. Accessed 2021-04--24."},{"key":"e_1_3_2_2_3_1","unstructured":"[n. d.]. FaceSwap. www.github.com\/MarekKowalski\/FaceSwap. Accessed 2021-04--24."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00180"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"e_1_3_2_2_9_1","unstructured":"Liang Chen Yong Zhang Yibing Song Jue Wang and Lingqiao Liu. [n. d.]. OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training. ([n. d.])."},{"key":"e_1_3_2_2_10_1","volume-title":"DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis. arXiv preprint arXiv:2403.18471","author":"Chen Zhongxi","year":"2024","unstructured":"Zhongxi Chen, Ke Sun, Ziyin Zhou, Xianming Lin, Xiaoshuai Sun, Liujuan Cao, and Rongrong Ji. 2024. DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis. arXiv preprint arXiv:2403.18471 (2024)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Jikang Cheng Zhiyuan Yan Ying Zhang Yuhao Luo ZhongyuanWang and Chen Li. 2024. Can We Leave Deepfake Data Behind in Training Deepfake Detector?. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/079017-0691"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.195"},{"key":"e_1_3_2_2_13_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_2_14_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 7890--7899","author":"Durall Ricard","year":"2020","unstructured":"Ricard Durall, Margret Keuper, and Janis Keuper. 2020. Watch your upconvolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 7890--7899."},{"key":"e_1_3_2_2_15_1","volume-title":"International conference on machine learning. PMLR, 3247--3258","author":"Frank Joel","year":"2020","unstructured":"Joel Frank, Thorsten Eisenhofer, Lea Sch\u00f6nherr, Asja Fischer, Dorothea Kolossa, and Thorsten Holz. 2020. Leveraging frequency analysis for deep fake image recognition. In International conference on machine learning. PMLR, 3247--3258."},{"key":"e_1_3_2_2_16_1","volume-title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","author":"Gao Peng","year":"2021","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yanwen Zhang, Hongsheng Li, and Yu Qiao. 2021. CLIP-Adapter: Better Vision-Language Models with Feature Adapters. Cornell University - arXiv,Cornell University - arXiv (Oct 2021)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8100263"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00500"},{"key":"e_1_3_2_2_19_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658035"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"e_1_3_2_2_24_1","volume-title":"Exposing deepfake videos by detecting face warping artif acts. arXiv preprint arXiv:1811.00656","author":"Y Li.","year":"2018","unstructured":"Y Li. 2018. Exposing deepfake videos by detecting face warping artif acts. arXiv preprint arXiv:1811.00656 (2018)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/wifs.2018.8630787"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"e_1_3_2_2_28_1","volume-title":"Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection. arXiv preprint arXiv:2409.02664","author":"Lin Kaiqing","year":"2024","unstructured":"Kaiqing Lin, Yuzhen Lin, Weixiang Li, Taiping Yao, and Bin Li. 2024. Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection. arXiv preprint arXiv:2409.02664 (2024)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3522091"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00011"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Utkarsh Ojha Yuheng Li and Yong Jae Lee. 2023. Towards Universal Fake Image Detectors that Generalize Across Generative Models. In CVPR.","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_2_37_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"e_1_3_2_2_40_1","volume-title":"Towards general visual-linguistic face forgery detection. arXiv preprint arXiv:2307.16545","author":"Sun Ke","year":"2023","unstructured":"Ke Sun, Shen Chen, Taiping Yao, Haozhe Yang, Xiaoshuai Sun, Shouhong Ding, and Rongrong Ji. 2023. Towards general visual-linguistic face forgery detection. arXiv preprint arXiv:2307.16545 (2023)."},{"key":"e_1_3_2_2_41_1","volume-title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection. arXiv preprint arXiv:2408.09647","author":"Tan Chuangchuang","year":"2024","unstructured":"Chuangchuang Tan, Renshuai Tao, Huan Liu, Guanghua Gu, Baoyuan Wu, Yao Zhao, and Yunchao Wei. 2024. C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection. arXiv preprint arXiv:2408.09647 (2024)."},{"key":"e_1_3_2_2_42_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_2_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00780"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"e_1_3_2_2_49_1","unstructured":"Zhiyuan Yan Taiping Yao Shen Chen Yandan Zhao Xinghe Fu Junwei Zhu Donghao Luo Li Yuan ChengjieWang Shouhong Ding et al. 2024. DF40: Toward Next-Generation Deepfake Detection. arXiv preprint arXiv:2406.13495 (2024)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"e_1_3_2_2_51_1","volume-title":"Levine (Eds.)","volume":"36","author":"Yan Zhiyuan","year":"2023","unstructured":"Zhiyuan Yan, Yong Zhang, Xinhang Yuan, Siwei Lyu, and Baoyuan Wu. 2023. DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection. In Advances in Neural Information Processing Systems, A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 4534--4565. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/0e735e4b4f07de483cbe250130992726-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683164"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00572"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:02:17Z","timestamp":1765310537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755137","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755137","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}