{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:36:41Z","timestamp":1784137001122,"version":"3.55.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T00:00:00Z","timestamp":1735948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T00:00:00Z","timestamp":1735948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11263-024-02339-6","type":"journal-article","created":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T06:39:07Z","timestamp":1735972747000},"page":"3278-3295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Robust Sequential DeepFake Detection"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0090-9604","authenticated-orcid":false,"given":"Rui","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,4]]},"reference":[{"key":"2339_CR1","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., & Le, Q. V. (2019). Attention augmented convolutional networks. In CVPR (pp. 3286\u20133295).","DOI":"10.1109\/ICCV.2019.00338"},{"key":"2339_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In ECCV (pp. 213\u2013229).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2339_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., Shen, L., Shao, R., Deng, X., & Nie, L. (2024). Lion: Empowering multimodal large language model with dual-level visual knowledge. In CVPR (pp. 26540\u201326550).","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"2339_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In CVPR (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2339_CR5","unstructured":"Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019). The deepfake detection challenge (DFDC) preview dataset. arXiv preprint arXiv:1910.08854"},{"key":"2339_CR6","unstructured":"Durall, R., Keuper, M., Pfreundt, F. J., & Keuper, J. (2019). Unmasking deepfakes with simple features. arXiv preprint arXiv:1911.00686"},{"key":"2339_CR7","first-page":"3022","volume":"33","author":"T Dzanic","year":"2020","unstructured":"Dzanic, T., Shah, K., & Witherden, F. (2020). Fourier spectrum discrepancies in deep network generated images. NeurIPS, 33, 3022\u20133032.","journal-title":"NeurIPS"},{"key":"2339_CR8","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., & Li, H. (2021). Fast convergence of DETR with spatially modulated co-attention. In CVPR (pp. 3621\u20133630).","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"2339_CR9","doi-asserted-by":"crossref","unstructured":"Gu, S., Bao, J., Chen, D., & Wen, F. (2020). GIQA: Generated image quality assessment. In ECCV (pp. 369\u2013385).","DOI":"10.1007\/978-3-030-58621-8_22"},{"key":"2339_CR10","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., & Pantic, M. (2021). Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. In CVPR (pp. 5039\u20135049).","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"2339_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2339_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Gan, B., Chen, S., Zhou, Y., Yin, G., Song, L., Sheng, L., Shao, J., & Liu, Z. (2021). ForgeryNet: A versatile benchmark for comprehensive forgery analysis. In CVPR (pp. 4360\u20134369).","DOI":"10.1109\/CVPR46437.2021.00434"},{"key":"2339_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, L., Li, R., Wu, W., Qian, C., & Loy, C. C. (2020). Deeperforensics-1.0: A large-scale dataset for real-world face forgery detection. In CVPR (pp. 2889\u20132898).","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"2339_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., Pan, X., Loy, C. C., & Liu, Z. (2021). Talk-to-edit: Fine-grained facial editing via dialog. In ICCV (pp. 13799\u201313808).","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"2339_CR15","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of GANs for improved quality, stability, and variation. In ICLR."},{"key":"2339_CR16","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In CVPR (pp. 4401\u20134410).","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2339_CR17","doi-asserted-by":"crossref","unstructured":"Kim, H., Choi, Y., Kim, J., Yoo, S., & Uh, Y. (2021). Exploiting spatial dimensions of latent in GAN for real-time image editing. In CVPR (pp. 852\u2013861).","DOI":"10.1109\/CVPR46437.2021.00091"},{"key":"2339_CR18","doi-asserted-by":"crossref","unstructured":"Lee, C. H., Liu, Z., Wu, L., & Luo, P. (2020). Maskgan: Towards diverse and interactive facial image manipulation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"2339_CR19","doi-asserted-by":"crossref","unstructured":"Lee, W., Kim, D., Hong, S., & Lee, H. (2020). High-fidelity synthesis with disentangled representation. In ECCV (pp. 157\u2013174).","DOI":"10.1007\/978-3-030-58574-7_10"},{"key":"2339_CR20","unstructured":"Li, J., Dongxu, L., Caimingm, X., & Steven, H. (2022). Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML (pp. 12888\u201312900)."},{"key":"2339_CR21","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., & Hoi, S. C. H. (2021). Align before fuse: Vision and language representation learning with momentum distillation. NeurIPS, 34, 9694\u20139705.","journal-title":"NeurIPS"},{"key":"2339_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Xie, H., Li, J., Wang, Z., & Zhang, Y. (2021). Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection. In CVPR (pp. 16317\u201316326).","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"2339_CR23","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020). Face X-ray for more general face forgery detection. In CVPR (pp. 5001\u20135010).","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"2339_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020). CELEB-DF: A large-scale challenging dataset for deepfake forensics. In CVPR (pp. 3207\u20133216).","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"2339_CR25","unstructured":"Li, Z., Xie, Y., Shao, R., Chen, G., Jiang, D., & Nie, L. (2024). Optimus-1: Hybrid multimodal memory empowered agents excel in long-horizon tasks. In NeurIPS."},{"key":"2339_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., & Yu, N. (2021). Spatial-phase shallow learning: Rethinking face forgery detection in frequency domain. In CVPR (pp. 772\u2013781).","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"2339_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. In CVPR (pp. 3730\u20133738).","DOI":"10.1109\/ICCV.2015.425"},{"key":"2339_CR28","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., & Liu, W. (2021). Generalizing face forgery detection with high-frequency features. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"2339_CR29","unstructured":"Oord, A. V. D., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"2339_CR30","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, L., Shazeer, N., Ku, A., & Tran, D. (2018). Image transformer. In ICML (pp. 4055\u20134064)."},{"key":"2339_CR31","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020). Thinking in frequency: Face forgery detection by mining frequency-aware clues. In ECCV (pp. 86\u2013103).","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"2339_CR32","doi-asserted-by":"crossref","unstructured":"Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nie\u00dfner, M. (2019). Faceforensics++: Learning to detect manipulated facial images. In CVPR (pp. 1\u201311).","DOI":"10.1109\/ICCV.2019.00009"},{"key":"2339_CR33","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). GRAD-CAM: Visual explanations from deep networks via gradient-based localization. In ICCV (pp. 618\u2013626).","DOI":"10.1109\/ICCV.2017.74"},{"key":"2339_CR34","doi-asserted-by":"crossref","unstructured":"Shao, R., Lan, X., Li, J., & Yuen, P. C. (2019). Multi-adversarial discriminative deep domain generalization for face presentation attack detection. In CVPR (pp. 10023\u201310031).","DOI":"10.1109\/CVPR.2019.01026"},{"key":"2339_CR35","doi-asserted-by":"crossref","unstructured":"Shao, R., Lan, X., & Yuen, P. C. (2017). Deep convolutional dynamic texture learning with adaptive channel-discriminability for 3D mask face anti-spoofing. In IJCB (pp. 748\u2013755).","DOI":"10.1109\/BTAS.2017.8272765"},{"issue":"4","key":"2339_CR36","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1109\/TIFS.2018.2868230","volume":"14","author":"R Shao","year":"2018","unstructured":"Shao, R., Lan, X., & Yuen, P. C. (2018). Joint discriminative learning of deep dynamic textures for 3D mask face anti-spoofing. IEEE Transactions on Information Forensics and Security, 14(4), 923\u2013938.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2339_CR37","doi-asserted-by":"crossref","unstructured":"Shao, R., Lan, X., & Yuen, P. C. (2020). Regularized fine-grained meta face anti-spoofing. In AAAI (Vol. 34, pp. 11974\u201311981).","DOI":"10.1609\/aaai.v34i07.6873"},{"key":"2339_CR38","doi-asserted-by":"crossref","unstructured":"Shao, R., Perera, P., Yuen, P. C., & Patel, V. M. (2020). Open-set adversarial defense. In ECCV (pp. 682\u2013698).","DOI":"10.1007\/978-3-030-58520-4_40"},{"issue":"1","key":"2339_CR39","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1109\/TNNLS.2022.3172316","volume":"35","author":"R Shao","year":"2022","unstructured":"Shao, R., Perera, P., Yuen, P. C., & Patel, V. M. (2022). Federated generalized face presentation attack detection. IEEE Transactions on Neural Networks and Learning Systems, 35(1), 103\u2013116.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"2339_CR40","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1007\/s11263-022-01581-0","volume":"130","author":"R Shao","year":"2022","unstructured":"Shao, R., Perera, P., Yuen, P. C., & Patel, V. M. (2022). Open-set adversarial defense with clean-adversarial mutual learning. International Journal of Computer Vision, 130(4), 1070\u20131087.","journal-title":"International Journal of Computer Vision"},{"key":"2339_CR41","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., & Liu, Z. (2022). Detecting and recovering sequential deepfake manipulation. In ECCV (pp. 712\u2013728).","DOI":"10.1007\/978-3-031-19778-9_41"},{"key":"2339_CR42","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., & Liu, Z. (2023). Detecting and grounding multi-modal media manipulation. In CVPR (pp. 6904\u20136913).","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"2339_CR43","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Nie, L., & Liu, Z. (2025). Deepfake-adapter: Dual-level adapter for deepfake detectiong. International Journal of Computer Vision.","DOI":"10.1007\/s11263-024-02274-6"},{"key":"2339_CR44","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Wu, J., Nie, L., & Liu, Z. (2024). Detecting and grounding multi-modal media manipulation and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8), 5556\u20135574.","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"2339_CR45","unstructured":"Shen, L., Chen, G., Shao, R., Guan, W., & Nie, L. (2024). MOME: Mixture of multimodal experts for generalist multimodal large language models. In NeurIPS."},{"key":"2339_CR46","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020a). Interpreting the latent space of GANs for semantic face editing. In CVPR (pp. 9243\u20139252).","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"2339_CR47","doi-asserted-by":"crossref","unstructured":"Shen, Y., Yang, C., Tang, X., & Zhou, B. (2020b). Interfacegan: Interpreting the disentangled face representation learned by GANs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4), 2004\u20132018.","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"2339_CR48","doi-asserted-by":"crossref","unstructured":"Shen, Y., & Zhou, B. (2021). Closed-form factorization of latent semantics in GANs. In CVPR (pp. 1532\u20131540).","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"2339_CR49","unstructured":"Voynov, A., & Babenko, A. (2020). Unsupervised discovery of interpretable directions in the GAN latent space. In ICML (pp. 9786\u20139796)."},{"key":"2339_CR50","first-page":"29074","volume":"34","author":"H Wang","year":"2021","unstructured":"Wang, H., Liu, W., Bocchieri, A., & Li, Y. (2021). Can multi-label classification networks know what they don\u2019t know? NeurIPS, 34, 29074\u201329087.","journal-title":"NeurIPS"},{"key":"2339_CR51","doi-asserted-by":"crossref","unstructured":"Wang, S. Y., Wang, O., Owens, A., Zhang, R., & Efros, A. A. (2019). Detecting photoshopped faces by scripting photoshop. In CVPR (pp. 10072\u201310081).","DOI":"10.1109\/ICCV.2019.01017"},{"key":"2339_CR52","doi-asserted-by":"crossref","unstructured":"Wang, W., Alameda-Pineda, X., Xu, D., Fua, P., Ricci, E., & Sebe, N. (2018). Every smile is unique: Landmark-guided diverse smile generation. In CVPR (pp. 31\u201339).","DOI":"10.1109\/CVPR.2018.00740"},{"key":"2339_CR53","doi-asserted-by":"crossref","unstructured":"Yang, H., Huang, D., Wang, Y., & Jain, A. K. (2018). Learning face age progression: A pyramid architecture of GANs. In CVPR (pp. 31\u201339).","DOI":"10.1109\/CVPR.2018.00011"},{"key":"2339_CR54","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., & Yu, N. (2021). Multi-attentional deepfake detection. In CVPR (pp. 2185\u20132194).","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"2339_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021). Learning self-consistency for deepfake detection. In ICCV (pp. 15023\u201315033).","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"2339_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Qin, Y., & Wonka, P. (2020). Sean: Image synthesis with semantic region-adaptive normalization. In CVPR (pp. 5549\u20135558).","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"2339_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, H., Fei, H., Lei, Z., & Li, S. Z. (2021). Face forgery detection by 3D decomposition. In CVPR (pp. 2929\u20132939).","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"2339_CR58","unstructured":"Zhuang, P., Koyejo, O., & Schwing, A. G. (2021). Enjoy your editing: Controllable GANs for image editing via latent space navigation. In ICLR."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02339-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02339-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02339-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:54:29Z","timestamp":1746860069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02339-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,4]]},"references-count":58,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2339"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02339-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,4]]},"assertion":[{"value":"5 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}