{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:48:22Z","timestamp":1774014502075,"version":"3.50.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502308"],"award-info":[{"award-number":["62502308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["25ZR1402266"],"award-info":[{"award-number":["25ZR1402266"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","award":["A2536"],"award-info":[{"award-number":["A2536"]}],"id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.jvcir.2026.104733","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:45:38Z","timestamp":1769499938000},"page":"104733","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SFNet: Hierarchical perception and adaptive test-time training for AI-generated military image detection"],"prefix":"10.1016","volume":"116","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6091-4687","authenticated-orcid":false,"given":"Minyang","family":"Li","sequence":"first","affiliation":[]},{"given":"Wenpeng","family":"Mu","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3101-8865","authenticated-orcid":false,"given":"Shengyan","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8750-7036","authenticated-orcid":false,"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104733_b1","series-title":"Hierarchical text-conditional image generation with clip latents","first-page":"3","author":"Ramesh","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104733_b2","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.jvcir.2026.104733_b3","first-page":"719","article-title":"Exposing the deception: Uncovering more forgery clues for deepfake detection","volume":"vol. 38","author":"Ba","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104733_b4","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 4490\u20134499.","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"10.1016\/j.jvcir.2026.104733_b5","doi-asserted-by":"crossref","unstructured":"H. Liu, X. Li, W. Zhou, H. Fang, P. Bestagini, W. Zhang, Y. Chen, S. Tubaro, N. Yu, Y. He, et al., BifPro: a bidirectional facial-data protection framework against deepfake, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 7075\u20137084.","DOI":"10.1145\/3581783.3613752"},{"key":"10.1016\/j.jvcir.2026.104733_b6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/OJSP.2023.3337714","article-title":"Synthbuster: Towards detection of diffusion model generated images","volume":"5","author":"Bammey","year":"2023","journal-title":"IEEE Open J. Signal Process."},{"key":"10.1016\/j.jvcir.2026.104733_b7","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2904","article-title":"Eyes tell all: Irregular pupil shapes reveal gan-generated faces","author":"Guo","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104733_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104396","article-title":"Generalization enhancement strategy based on ensemble learning for open domain image manipulation detection","volume":"107","author":"Cheng","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104733_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2021.103239","article-title":"Dynamic texture analysis for detecting fake faces in video sequences","volume":"79","author":"Bonomi","year":"2021","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104733_b10","doi-asserted-by":"crossref","unstructured":"K. Chandrasegaran, N.-T. Tran, N.-M. Cheung, A closer look at fourier spectrum discrepancies for cnn-generated images detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7200\u20137209.","DOI":"10.1109\/CVPR46437.2021.00712"},{"key":"10.1016\/j.jvcir.2026.104733_b11","series-title":"International Conference on Machine Learning","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","author":"Frank","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104733_b12","doi-asserted-by":"crossref","unstructured":"C. Dong, A. Kumar, E. Liu, Think twice before detecting gan-generated fake images from their spectral domain imprints, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7865\u20137874.","DOI":"10.1109\/CVPR52688.2022.00771"},{"key":"10.1016\/j.jvcir.2026.104733_b13","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1109\/TIFS.2022.3233774","article-title":"F 2 trans: High-frequency fine-grained transformer for face forgery detection","volume":"18","author":"Miao","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.jvcir.2026.104733_b14","first-page":"5052","article-title":"Frequency-aware deepfake detection: Improving generalizability through frequency space domain learning","volume":"vol. 38","author":"Tan","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104733_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104075","article-title":"Copy move forgery detection and localisation robust to rotation using block based discrete cosine transform and eigenvalues","volume":"99","author":"Shehin","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104733_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104263","article-title":"DeepFake detection method based on multi-scale interactive dual-stream network","volume":"104","author":"Cheng","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104733_b17","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104733_b18","series-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104733_b19","series-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104733_b20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104733_b21","doi-asserted-by":"crossref","unstructured":"S. Gu, D. Chen, J. Bao, F. Wen, B. Zhang, D. Chen, L. Yuan, B. Guo, Vector quantized diffusion model for text-to-image synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10696\u201310706.","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"10.1016\/j.jvcir.2026.104733_b22","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104733_b23","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"13466","article-title":"Frequency masking for universal deepfake detection","author":"Doloriel","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104733_b24","series-title":"European Conference on Computer Vision","first-page":"86","article-title":"Thinking in frequency: Face forgery detection by mining frequency-aware clues","author":"Qian","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104733_b25","series-title":"Towards the detection of diffusion model deepfakes","author":"Ricker","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104733_b26","doi-asserted-by":"crossref","unstructured":"Z. Wang, J. Bao, W. Zhou, W. Wang, H. Hu, H. Chen, H. Li, Dire for diffusion-generated image detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 22445\u201322455.","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"10.1016\/j.jvcir.2026.104733_b27","doi-asserted-by":"crossref","unstructured":"C. Tan, Y. Zhao, S. Wei, G. Gu, Y. Wei, Learning on gradients: Generalized artifacts representation for gan-generated images detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 12105\u201312114.","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"10.1016\/j.jvcir.2026.104733_b28","doi-asserted-by":"crossref","unstructured":"C. Tan, Y. Zhao, S. Wei, G. Gu, P. Liu, Y. Wei, Rethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28130\u201328139.","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"10.1016\/j.jvcir.2026.104733_b29","series-title":"Rich and poor texture contrast: A simple yet effective approach for ai-generated image detection","author":"Zhong","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104733_b30","doi-asserted-by":"crossref","unstructured":"U. Ojha, Y. Li, Y.J. Lee, Towards universal fake image detectors that generalize across generative models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 24480\u201324489.","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"10.1016\/j.jvcir.2026.104733_b31","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104733_b32","first-page":"14541","article-title":"Fast vision transformers with hilo attention","volume":"35","author":"Pan","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104733_b33","doi-asserted-by":"crossref","unstructured":"Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, Q. Hu, ECA-Net: Efficient channel attention for deep convolutional neural networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11534\u201311542.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"10.1016\/j.jvcir.2026.104733_b34","series-title":"International Conference on Machine Learning","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","author":"Sun","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104733_b35","series-title":"Dall\u00b7 e mini","author":"Dayma","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104733_b36","series-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104733_b37","series-title":"Midjourney","author":"Midjourney","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104733_b38","series-title":"Stable diffusion flux","author":"AI","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104733_b39","series-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104733_b40","doi-asserted-by":"crossref","unstructured":"J.-Y. Zhu, T. Park, P. Isola, A.A. Efros, Unpaired image-to-image translation using cycle-consistent adversarial networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"10.1016\/j.jvcir.2026.104733_b41","doi-asserted-by":"crossref","unstructured":"S.-Y. Wang, O. Wang, R. Zhang, A. Owens, A.A. Efros, CNN-generated images are surprisingly easy to spot... for now, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8695\u20138704.","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"10.1016\/j.jvcir.2026.104733_b42","series-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104733_b43","series-title":"2022 IEEE International Conference on Image Processing","first-page":"3465","article-title":"Fusing global and local features for generalized ai-synthesized image detection","author":"Ju","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104733_b44","article-title":"Genimage: A million-scale benchmark for detecting ai-generated image","volume":"36","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104733_b45","doi-asserted-by":"crossref","unstructured":"Z. Liu, X. Qi, P.H. Torr, Global texture enhancement for fake face detection in the wild, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8060\u20138069.","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"10.1016\/j.jvcir.2026.104733_b46","doi-asserted-by":"crossref","unstructured":"S.A. Khan, D.-T. Dang-Nguyen, Clipping the deception: Adapting vision-language models for universal deepfake detection, in: Proceedings of the 2024 International Conference on Multimedia Retrieval, 2024, pp. 1006\u20131015.","DOI":"10.1145\/3652583.3658035"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000283?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000283?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T11:21:10Z","timestamp":1774005670000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":46,"alternative-id":["S1047320326000283"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104733","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SFNet: Hierarchical perception and adaptive test-time training for AI-generated military image detection","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104733","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104733"}}