{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:57:48Z","timestamp":1780934268575,"version":"3.54.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113939","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:19:05Z","timestamp":1778084345000},"page":"113939","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Improving face forgery detection via hierarchical mixture of experts and fine-grained visual-text alignment"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8805-9792","authenticated-orcid":false,"given":"Chaowei","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bolin","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113939_b1","first-page":"1","article-title":"FakeCatcher: Detection of synthetic portrait videos using biological signals","author":"Ciftci","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113939_b2","doi-asserted-by":"crossref","unstructured":"Y. Luo, Y. Zhang, J. Yan, W. Liu, Generalizing face forgery detection with high-frequency features, in: IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 16317\u201316326.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"10.1016\/j.patcog.2026.113939_b3","doi-asserted-by":"crossref","unstructured":"J. Cao, C. Ma, T. Yao, S. Chen, S. Ding, X. Yang, End-to-end reconstruction-classification learning for face forgery detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 4113\u20134122.","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"10.1016\/j.patcog.2026.113939_b4","doi-asserted-by":"crossref","unstructured":"H. Dang, F. Liu, J. Stehouwer, X. Liu, A.K. Jain, On the detection of digital face manipulation, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 5781\u20135790.","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"10.1016\/j.patcog.2026.113939_b5","unstructured":"A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, I. Sutskever, Learning transferable visual models from natural language supervision, in: International Conference on Machine Learning, 2021, pp. 8748\u20138763."},{"key":"10.1016\/j.patcog.2026.113939_b6","article-title":"Moe-ffd: Mixture of experts for generalized and parameter-efficient face forgery detection","author":"Kong","year":"2025","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.patcog.2026.113939_b7","doi-asserted-by":"crossref","unstructured":"Y. Li, X. Yang, P. Sun, H. Qi, S. Lyu, Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"10.1016\/j.patcog.2026.113939_b8","series-title":"The deepfake detection challenge (dfdc) dataset","author":"Dolhansky","year":"2020"},{"key":"10.1016\/j.patcog.2026.113939_b9","series-title":"The deepfake detection challenge (dfdc) preview dataset","author":"Dolhansky","year":"2019"},{"key":"10.1016\/j.patcog.2026.113939_b10","doi-asserted-by":"crossref","unstructured":"X. Yang, Y. Li, S. Lyu, Exposing Deep Fakes Using Inconsistent Head Poses, in: IEEE International Conference on Acoustics, Speech and Signal Processing, 2019.","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"10.1016\/j.patcog.2026.113939_b11","doi-asserted-by":"crossref","unstructured":"D. Afchar, V. Nozick, J. Yamagishi, I. Echizen, Mesonet: a compact facial video forgery detection network, in: IEEE International Workshop on Information Forensics and Security, 2018, pp. 1\u20137.","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"10.1016\/j.patcog.2026.113939_b12","doi-asserted-by":"crossref","unstructured":"U. Ojha, Y. Li, Y.J. Lee, Towards Universal Fake Image Detectors that Generalize Across Generative Models, in: IEEE Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"10.1016\/j.patcog.2026.113939_b13","doi-asserted-by":"crossref","unstructured":"H. Liu, Z. Tan, C. Tan, Y. Wei, J. Wang, Y. Zhao, Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.01024"},{"key":"10.1016\/j.patcog.2026.113939_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113659","article-title":"Refining forgery-aware prompts for deepfake detection with pattern blended samples","volume":"179","author":"Feng","year":"2026","journal-title":"PR","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.patcog.2026.113939_b15","series-title":"Findings of the Association for Computational Linguistics","first-page":"1405","article-title":"K-adapter: infusing knowledge into pre-trained models with adapters","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113939_b16","article-title":"Dual-domain adaptation networks for realistic image super-resolution","author":"Fang","year":"2026","journal-title":"TMM"},{"key":"10.1016\/j.patcog.2026.113939_b17","article-title":"Learning prompt adapters for forgetting-free continual image super-resolution","author":"Fang","year":"2026","journal-title":"TIP"},{"issue":"2","key":"10.1016\/j.patcog.2026.113939_b18","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"CLIP-adapter: Better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"IJCV"},{"key":"10.1016\/j.patcog.2026.113939_b19","first-page":"4248","article-title":"Learning domain-aware detection head with prompt tuning","volume":"36","author":"Li","year":"2023","journal-title":"NIPS"},{"key":"10.1016\/j.patcog.2026.113939_b20","series-title":"Advances in Neural Information Processing Systems","article-title":"DA-ada: Learning domain-aware adapter for domain adaptive object detection","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.113939_b21","series-title":"Advances in Neural Information Processing Systems","isbn-type":"print","article-title":"Mixture-of-experts with expert choice routing","author":"Zhou","year":"2022","ISBN":"https:\/\/id.crossref.org\/isbn\/9781713871088"},{"key":"10.1016\/j.patcog.2026.113939_b22","series-title":"OpenMoE: An early effort on open mixture-of-experts language models","author":"Xue","year":"2024"},{"issue":"2","key":"10.1016\/j.patcog.2026.113939_b23","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","article-title":"Hierarchical mixtures of experts and the EM algorithm","volume":"6","author":"Jordan","year":"1994","journal-title":"Neural Comput."},{"key":"10.1016\/j.patcog.2026.113939_b24","series-title":"International Conference on Pattern Recognition","first-page":"7900","article-title":"Hierarchical routing mixture of experts","author":"Zhao","year":"2021"},{"key":"10.1016\/j.patcog.2026.113939_b25","series-title":"International Conference on Learning Representations","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"10.1016\/j.patcog.2026.113939_b26","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Forgery-aware adaptive transformer for generalizable synthetic image detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113939_b27","first-page":"4534","article-title":"DeepfakeBench: A comprehensive benchmark of deepfake detection","volume":"vol. 36","author":"Yan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113939_b28","doi-asserted-by":"crossref","unstructured":"A. Rossler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, M. Nie\u00dfner, Faceforensics++: Learning to detect manipulated facial images, in: IEEE International Conference on Computer Vision, 2019, pp. 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"10.1016\/j.patcog.2026.113939_b29","doi-asserted-by":"crossref","unstructured":"J. Thies, M. Zollhofer, M. Stamminger, C. Theobalt, M. Niessner, Face2Face: Real-Time Face Capture and Reenactment of RGB Videos, in: IEEE Conference on Computer Vision and Pattern Recognition, 2016.","DOI":"10.1109\/CVPR.2016.262"},{"issue":"4","key":"10.1016\/j.patcog.2026.113939_b30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3323035","article-title":"Deferred neural rendering: Image synthesis using neural textures","volume":"38","author":"Thies","year":"2019","journal-title":"TOG"},{"key":"10.1016\/j.patcog.2026.113939_b31","first-page":"6","article-title":"A method for stochastic optimization","volume":"vol. 5","author":"Kinga","year":"2015"},{"key":"10.1016\/j.patcog.2026.113939_b32","unstructured":"M. Tan, Q. Le, Efficientnet: Rethinking model scaling for convolutional neural networks, in: International Conference on Machine Learning, 2019, pp. 6105\u20136114."},{"key":"10.1016\/j.patcog.2026.113939_b33","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"CVPR"},{"key":"10.1016\/j.patcog.2026.113939_b34","doi-asserted-by":"crossref","unstructured":"Y. Qian, G. Yin, L. Sheng, Z. Chen, J. Shao, Thinking in frequency: Face forgery detection by mining frequency-aware clues, in: European Conference on Computer Vision, 2020, pp. 86\u2013103.","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"10.1016\/j.patcog.2026.113939_b35","doi-asserted-by":"crossref","unstructured":"L. Li, J. Bao, T. Zhang, H. Yang, D. Chen, F. Wen, B. Guo, Face x-ray for more general face forgery detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 5001\u20135010.","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"10.1016\/j.patcog.2026.113939_b36","doi-asserted-by":"crossref","unstructured":"H. Liu, X. Li, W. Zhou, Y. Chen, Y. He, H. Xue, W. Zhang, N. Yu, Spatial-phase shallow learning: rethinking face forgery detection in frequency domain, in: IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 772\u2013781.","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"10.1016\/j.patcog.2026.113939_b37","doi-asserted-by":"crossref","unstructured":"W. Zhuang, Q. Chu, Z. Tan, Q. Liu, H. Yuan, C. Miao, Z. Luo, N. Yu, UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection, in: European Conference on Computer Vision, 2022.","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"10.1016\/j.patcog.2026.113939_b38","doi-asserted-by":"crossref","unstructured":"B. Huang, Z. Wang, J. Yang, J. Ai, Q. Zou, Q. Wang, D. Ye, Implicit Identity Driven Deepfake Face Swapping Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2023, pp. 4490\u20134499.","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"10.1016\/j.patcog.2026.113939_b39","doi-asserted-by":"crossref","unstructured":"Z. Yan, Y. Zhang, Y. Fan, B. Wu, Ucf: Uncovering common features for generalizable deepfake detection, in: IEEE International Conference on Computer Vision, 2023, pp. 22412\u201322423.","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"10.1016\/j.patcog.2026.113939_b40","doi-asserted-by":"crossref","unstructured":"Z. Yan, Y. Luo, S. Lyu, Q. Liu, B. Wu, Transcending forgery specificity with latent space augmentation for generalizable deepfake detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"10.1016\/j.patcog.2026.113939_b41","doi-asserted-by":"crossref","first-page":"3814","DOI":"10.1109\/TIFS.2024.3372773","article-title":"Learning to discover forgery cues for face forgery detection","volume":"19","author":"Tian","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.patcog.2026.113939_b42","doi-asserted-by":"crossref","unstructured":"X. Cui, Y. Li, A. Luo, J. Zhou, J. Dong, Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2025, pp. 19207\u201319217.","DOI":"10.1109\/CVPR52734.2025.01789"},{"key":"10.1016\/j.patcog.2026.113939_b43","doi-asserted-by":"crossref","unstructured":"A. Haliassos, K. Vougioukas, S. Petridis, M. Pantic, Lips Don\u2019t Lie: A Generalisable and Robust Approach To Face Forgery Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 5039\u20135049.","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"10.1016\/j.patcog.2026.113939_b44","doi-asserted-by":"crossref","unstructured":"Y. Zheng, J. Bao, D. Chen, M. Zeng, F. Wen, Exploring Temporal Coherence for More General Video Face Forgery Detection, in: IEEE International Conference on Computer Vision, 2021, pp. 15044\u201315054.","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"10.1016\/j.patcog.2026.113939_b45","series-title":"European Conference on Computer Vision","first-page":"596","article-title":"Hierarchical contrastive inconsistency learning for deepfake video detection","author":"Gu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113939_b46","doi-asserted-by":"crossref","unstructured":"A. Haliassos, R. Mira, S. Petridis, M. Pantic, Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022.","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"10.1016\/j.patcog.2026.113939_b47","doi-asserted-by":"crossref","unstructured":"X. Dong, J. Bao, D. Chen, T. Zhang, W. Zhang, N. Yu, D. Chen, F. Wen, B. Guo, Protecting Celebrities From DeepFake With Identity Consistency Transformer, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 9468\u20139478.","DOI":"10.1109\/CVPR52688.2022.00925"},{"key":"10.1016\/j.patcog.2026.113939_b48","doi-asserted-by":"crossref","unstructured":"K. Shiohara, T. Yamasaki, Detecting Deepfakes with Self-Blended Images, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 18720\u201318729.","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"10.1016\/j.patcog.2026.113939_b49","doi-asserted-by":"crossref","unstructured":"N. Larue, N.-S. Vu, V. Struc, P. Peer, V. Christophides, SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes, in: IEEE International Conference on Computer Vision, 2022, pp. 20954\u201320964.","DOI":"10.1109\/ICCV51070.2023.01921"},{"key":"10.1016\/j.patcog.2026.113939_b50","doi-asserted-by":"crossref","unstructured":"Y. Xu, J. Liang, G. Jia, Z. Yang, Y. Zhang, R. He, TALL: Thumbnail Layout for Deepfake Video Detection, in: IEEE International Conference on Computer Vision, 2023, pp. 22658\u201322668.","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"10.1016\/j.patcog.2026.113939_b51","doi-asserted-by":"crossref","unstructured":"Z. Wang, J. Bao, W. Zhou, W. Wang, H. Li, AltFreezing for More General Video Face Forgery Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2023, pp. 4129\u20134138.","DOI":"10.1109\/CVPR52729.2023.00402"},{"key":"10.1016\/j.patcog.2026.113939_b52","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional Prompt Learning for Vision-Language Models, in: IEEE Conference on Computer Vision and Pattern Recognition, 2022.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.patcog.2026.113939_b53","doi-asserted-by":"crossref","unstructured":"L. Jiang, R. Li, W. Wu, C. Qian, C.C. Loy, DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"10.1016\/j.patcog.2026.113939_b54","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2016","journal-title":"IJCV"},{"key":"10.1016\/j.patcog.2026.113939_b55","doi-asserted-by":"crossref","unstructured":"H. Li, R. Zhang, H. Yao, X. Zhang, Y. Hao, X. Song, S. Peng, Y. Zhao, C. Zhao, Y. Wu, L. ling Li, SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2025, pp. 25465\u201325475.","DOI":"10.1109\/CVPR52734.2025.02371"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009040?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009040?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:00:26Z","timestamp":1780930826000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S0031320326009040"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113939","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving face forgery detection via hierarchical mixture of experts and fine-grained visual-text alignment","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113939","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113939"}}