{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:56Z","timestamp":1777568516259,"version":"3.51.4"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2045"],"award-info":[{"award-number":["U21B2045"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11263-024-02208-2","type":"journal-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T16:02:16Z","timestamp":1723564936000},"page":"672-687","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Test-time Forgery Detection with Spatial-Frequency Prompt Learning"],"prefix":"10.1007","volume":"133","author":[{"given":"Junxian","family":"Duan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuang","family":"Ai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jipeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,13]]},"reference":[{"key":"2208_CR1","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018). Mesonet: A compact facial video forgery detection network. In IEEE International Workshop on Information Forensics and Security, pp 1\u20137.","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"2208_CR2","doi-asserted-by":"crossref","unstructured":"Bai, W., Liu, Y., Zhang, Z., Li, B., & Hu, W. (2023). Aunet: Learning relations between action units for face forgery detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 24709\u201324719.","DOI":"10.1109\/CVPR52729.2023.02367"},{"key":"2208_CR3","first-page":"3080","volume":"151","author":"A Bartler","year":"2022","unstructured":"Bartler, A., B\u00fchler, A., Wiewel, F., D\u00f6bler, M., & Yang, B. (2022). MT3: Meta test-time training for self-supervised test-time adaption. International Conference on Artificial Intelligence and Statistics, 151, 3080\u20133090.","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"2208_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2208_CR5","doi-asserted-by":"crossref","unstructured":"Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022). End-to-end reconstruction-classification learning for face forgery detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4103\u20134112.","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"2208_CR6","unstructured":"Chen, A., Yao, Y., Chen, P., Zhang, Y., & Liu, S. (2022a). Understanding and improving visual prompting: A label-mapping perspective. arxiv:abs\/2211.11635"},{"key":"2208_CR7","unstructured":"Chen, L., Zhang, Y., Song, Y., Wang, J., & Liu, L. (2022b). OST: Improving generalization of deepfake detection via one-shot test-time training. In: Advances in Neural Information Processing Systems."},{"key":"2208_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., Yao, T., Chen, Y., Ding, S., Li, J., & Ji, R. (2021). Local relation learning for face forgery detection. In Thirty-Fifth Conference on Artificial Intelligence, AAAI, pp 1081\u20131088.","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"2208_CR9","unstructured":"Cozzolino, D., Thies, J., R\u00f6ssler, A., Riess, C., Nie\u00dfner, M., & Verdoliva, L. (2018). Forensictransfer: Weakly-supervised domain adaptation for forgery detection. arxiv: abs\/1812.02510"},{"key":"2208_CR10","doi-asserted-by":"crossref","unstructured":"Dang, H., Liu, F., Stehouwer, J., Liu, X., & Jain, AK. (2020). On the detection of digital face manipulation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5780\u20135789.","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"2208_CR11","doi-asserted-by":"crossref","unstructured":"Das, S., Seferbekov, S.S., Datta, A., Islam, MS., & Amin, MR. (2021). Towards solving the deepfake problem : An analysis on improving deepfake detection using dynamic face augmentation. In IEEE\/CVF International Conference on Computer Vision Workshops, pp 3769\u20133778.","DOI":"10.1109\/ICCVW54120.2021.00421"},{"key":"2208_CR12","unstructured":"Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Canton-Ferrer, C. (2019). The deepfake detection challenge (DFDC) preview dataset. arxiv: abs\/1910.08854"},{"key":"2208_CR13","unstructured":"Dong, B., Zhou, P., Yan, S., & Zuo, W. (2023a). LPT: Long-tailed prompt tuning for image classification. In The Eleventh International Conference on Learning Representations."},{"issue":"3","key":"2208_CR14","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1109\/TPAMI.2022.3180556","volume":"45","author":"C Dong","year":"2023","unstructured":"Dong, C., Chen, X., Hu, R., Cao, J., & Li, X. (2023). Mvss-net: Multi-view multi-scale supervised networks for image manipulation detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3539\u20133553.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2208_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"2208_CR16","doi-asserted-by":"crossref","unstructured":"Gao, G., Huang, H., Fu, C., Li, Z., & He, R. (2021). Information bottleneck disentanglement for identity swapping. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3404\u20133413.","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"2208_CR17","doi-asserted-by":"crossref","unstructured":"Gu, Q., Chen, S., Yao, T., Chen, Y., Ding, S., & Yi, R. (2022). Exploiting fine-grained face forgery clues via progressive enhancement learning. In Thirty-Sixth Conference on Artificial Intelligence, AAAI, pp 735\u2013743.","DOI":"10.1609\/aaai.v36i1.19954"},{"key":"2208_CR18","doi-asserted-by":"crossref","unstructured":"Guillaro, F., Cozzolino, D., Sud, A., Dufour, N., & Verdoliva, L. (2023). Trufor: Leveraging all-round clues for trustworthy image forgery detection and localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 20606\u201320615.","DOI":"10.1109\/CVPR52729.2023.01974"},{"key":"2208_CR19","unstructured":"Gumbel, E.J. (1954). Statistical theory of extreme values and some practical applications: A series of lectures. 33."},{"key":"2208_CR20","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, H., & Ji, Q. (2022). Uncertainty-guided probabilistic transformer for complex action recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 20020\u201320029.","DOI":"10.1109\/CVPR52688.2022.01942"},{"key":"2208_CR21","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, X., Ren, Z., Grosz, S., Masi, I., & Liu, X. (2023). Hierarchical fine-grained image forgery detection and localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3155\u20133165.","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"2208_CR22","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Gesmundo, A., Attariyan, M., & Gelly, S. (2019). Parameter-efficient transfer learning for NLP. InProceedings of the 36th International Conference on Machine Learning, 97, 2790\u20132799."},{"key":"2208_CR23","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., & Ye, D. (2023a). Implicit identity driven deepfake face swapping detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4490\u20134499.","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"2208_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Q., Dong, X., Chen, D., Zhang, W., Wang, F., Hua, G., & Yu, N. (2023b). Diversity-aware meta visual prompting. arxiv: abs\/2303.08138","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"2208_CR25","doi-asserted-by":"crossref","unstructured":"Huang, S., Huang, H., Wang, Z., Xu, N., Zheng, A., & He, R. (2023c). Uncertainty-guided test-time training for face forgery detection. In: Pattern Recognition\u20147th Asian Conference, ACPR, vol 14407, pp 258\u2013272.","DOI":"10.1007\/978-3-031-47637-2_20"},{"key":"2208_CR26","unstructured":"Jang, E., Gu, S., & Poole, B. (2017). Categorical reparameterization with gumbel-softmax. In International Conference on Learning Representations."},{"key":"2208_CR27","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B., Cardie, C., Belongie, S.J., Hariharan, B., & Lim, S. (2022). Visual prompt tuning. arxiv: abs\/2203.12119","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2208_CR28","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of gans for improved quality, stability, and variation. In 6th International Conference on Learning Representations."},{"issue":"12","key":"2208_CR29","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","volume":"43","author":"T Karras","year":"2021","unstructured":"Karras, T., Laine, S., & Aila, T. (2021). A style-based generator architecture for generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(12), 4217\u20134228.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2208_CR30","unstructured":"Kowalski, M. (2021). Faceswap. https:\/\/github.com\/marekkowalski\/faceswap, 2022, April 7"},{"issue":"8","key":"2208_CR31","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1007\/s11263-022-01617-5","volume":"130","author":"M Kwon","year":"2022","unstructured":"Kwon, M., Nam, S., Yu, I., Lee, H., & Kim, C. (2022). Learning JPEG compression artifacts for image manipulation detection and localization. International Journal of Computer Vision, 130(8), 1875\u20131895.","journal-title":"International Journal of Computer Vision"},{"key":"2208_CR32","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y., & Hospedales, T.M. (2018). Learning to generalize: Meta-learning for domain generalization. In McIlraith SA, Weinberger KQ (eds) Thirty-Second AAAI Conference on Artificial Intelligence, pp 3490\u20133497.","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"2208_CR33","doi-asserted-by":"crossref","unstructured":"Li, D., Zhu, J., Wang, M., Liu, J., Fu, X., & Zha, Z. (2023). Edge-aware regional message passing controller for image forgery localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8222\u20138232.","DOI":"10.1109\/CVPR52729.2023.00795"},{"key":"2208_CR34","doi-asserted-by":"crossref","unstructured":"Li, J., Xie, H., Li, J., Wang, Z., & Zhang, Y. (2021a). Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection. In IEEE Conference on Computer Vision and Pattern Recognition, pp 6458\u20136467.","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"2208_CR35","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020a). Face x-ray for more general face forgery detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5000\u20135009.","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"2208_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020b). Celeb-df: A large-scale challenging dataset for deepfake forensics. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3204\u20133213.","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"2208_CR37","unstructured":"Li, Y., Hao, M., Di, Z., Gundavarapu, N.B., & Wang, X. (2021b). Test-time personalization with a transformer for human pose estimation. In Advances in Neural Information Processing Systems, pp 2583\u20132597."},{"key":"2208_CR38","doi-asserted-by":"publisher","first-page":"4272","DOI":"10.1109\/TIFS.2023.3293951","volume":"18","author":"D Liu","year":"2023","unstructured":"Liu, D., Dang, Z., Peng, C., Zheng, Y., Li, S., Wang, N., & Gao, X. (2023). Fedforgery: Generalized face forgery detection with residual federated learning. IEEE Transactions on Information Forensics and Security, 18, 4272\u20134284.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2208_CR39","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., & Yu, N. (2021a). Spatial-phase shallow learning: Rethinking face forgery detection in frequency domain. In IEEE Conference on Computer Vision and Pattern Recognition, pp 772\u2013781.","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"2208_CR40","doi-asserted-by":"crossref","unstructured":"Liu, H., Wu, Z., Li, L., Salehkalaibar, S., Chen, J., & Wang, K. (2022a). Towards multi-domain single image dehazing via test-time training. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5821\u20135830.","DOI":"10.1109\/CVPR52688.2022.00574"},{"key":"2208_CR41","unstructured":"Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2022b). Pseudo numerical methods for diffusion models on manifolds. In The Tenth International Conference on Learning Representations."},{"key":"2208_CR42","unstructured":"Liu, Y., Kothari, P., van Delft, B., Bellot-Gurlet, B., Mordan, T., & Alahi, A. (2021b). TTT++: When does self-supervised test-time training fail or thrive? In Advances in Neural Information Processing Systems, pp 21808\u201321820."},{"key":"2208_CR43","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., & Liu, W. (2021). Generalizing face forgery detection with high-frequency features. In IEEE Conference on Computer Vision and Pattern Recognition, pp 16317\u201316326.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"2208_CR44","first-page":"667","volume":"12352","author":"I Masi","year":"2020","unstructured":"Masi, I., Killekar, A., Mascarenhas, R. M., Gurudatt, S. P., & AbdAlmageed, W. (2020). Two-branch recurrent network for isolating deepfakes in videos. European Conference on Computer Vision, 12352, 667\u2013684.","journal-title":"European Conference on Computer Vision"},{"key":"2208_CR45","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.1109\/TIFS.2022.3198275","volume":"17","author":"C Miao","year":"2022","unstructured":"Miao, C., Tan, Z., Chu, Q., Yu, N., & Guo, G. (2022). Hierarchical frequency-assisted interactive networks for face manipulation detection. IEEE Transactions on Information Forensics and Security, 17, 3008\u20133021.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2208_CR46","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1109\/TIFS.2022.3233774","volume":"18","author":"C Miao","year":"2023","unstructured":"Miao, C., Tan, Z., Chu, Q., Liu, H., Hu, H., & Yu, N. (2023). F$${}^{\\text{2 }}$$trans: High-frequency fine-grained transformer for face forgery detection. IEEE Transactions on Information Forensics and Security, 18, 1039\u20131051.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2208_CR47","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Fang, F., Yamagishi, J., & Echizen, I. (2019a). Multi-task learning for detecting and segmenting manipulated facial images and videos. In IEEE International Conference on Biometrics Theory, Applications and Systems, pp 1\u20138.","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"2208_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen, H. H., Fang, F., Yamagishi, J., & Echizen, I. (2019). Multi-task learning for detecting and segmenting manipulated facial images and videos. 10th IEEE International Conference on Biometrics Theory (pp. 1\u20138). BTAS: Applications and Systems.","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"2208_CR49","doi-asserted-by":"crossref","unstructured":"Patel, K., Bur, A.M., Li, F., & Wang, G. (2022). Aggregating global features into local vision transformer. In International Conference on Pattern Recognition. pp 1141\u20131147.","DOI":"10.1109\/ICPR56361.2022.9956379"},{"key":"2208_CR50","first-page":"86","volume":"12357","author":"Y Qian","year":"2020","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020). Thinking in frequency: Face forgery detection by mining frequency-aware clues. European Conference on Computer Vision, 12357, 86\u2013103.","journal-title":"European Conference on Computer Vision"},{"key":"2208_CR51","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10674\u201310685.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2208_CR52","doi-asserted-by":"crossref","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nie\u00dfner, M. (2019a). Faceforensics++: Learning to detect manipulated facial images. In 2019 IEEE\/CVF International Conference on Computer Vision, pp 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"2208_CR53","doi-asserted-by":"crossref","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nie\u00dfner, M. (2019b). Faceforensics++: Learning to detect manipulated facial images. In IEEE\/CVF International Conference on Computer Vision, pp 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"2208_CR54","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","volume":"47","author":"C Sagonas","year":"2016","unstructured":"Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2016). 300 faces in-the-wild challenge: Database and results. Image and Vision Computing, 47, 3\u201318.","journal-title":"Image and Vision Computing"},{"key":"2208_CR55","unstructured":"Sanh, V., Webson, A., Raffel, C., Bach, S.H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Raja, A., & Dey, M., et al. (2022). Multitask prompted training enables zero-shot task generalization. In The Tenth International Conference on Learning Representations."},{"issue":"2","key":"2208_CR56","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020). Grad-cam: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128(2), 336\u2013359.","journal-title":"International Journal of Computer Vision"},{"key":"2208_CR57","doi-asserted-by":"crossref","unstructured":"Shiohara, K., & Yamasaki, T. (2022). Detecting deepfakes with self-blended images. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18699\u201318708.","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"2208_CR58","unstructured":"Shu, M., Nie, W., Huang, D., Yu, Z., Goldstein, T., Anandkumar, A., & Xiao, C. (2022). Test-time prompt tuning for zero-shot generalization in vision-language models. In Advances in Neural Information Processing Systems."},{"key":"2208_CR59","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., & Goldstein, T. (2023). Diffusion art or digital forgery? investigating data replication in diffusion models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6048\u20136058.","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"2208_CR60","doi-asserted-by":"crossref","unstructured":"Sun, K., Liu, H., Ye, Q., Gao, Y., Liu, J., Shao, L., & Ji, R. (2021). Domain general face forgery detection by learning to weight. In Thirty-Fifth AAAI Conference on Artificial Intelligence, pp 2638\u20132646.","DOI":"10.1609\/aaai.v35i3.16367"},{"key":"2208_CR61","doi-asserted-by":"crossref","unstructured":"Sun, K., Yao, T., Chen, S., Ding, S., Li, J., & Ji, R. (2022). Dual contrastive learning for general face forgery detection. In Thirty-Sixth AAAI Conference on Artificial Intelligence, pp 2316\u20132324.","DOI":"10.1609\/aaai.v36i2.20130"},{"key":"2208_CR62","unstructured":"Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A. A., & Hardt, M. (2020). Test-time training with self-supervision for generalization under distribution shifts. In Proceedings of the 37th International Conference on Machine Learning, 119, 9229\u20139248."},{"issue":"12","key":"2208_CR63","doi-asserted-by":"publisher","first-page":"2903","DOI":"10.1007\/s11263-022-01673-x","volume":"130","author":"V Sushko","year":"2022","unstructured":"Sushko, V., Sch\u00f6nfeld, E., Zhang, D., Gall, J., Schiele, B., & Khoreva, A. (2022). OASIS: Only adversarial supervision for semantic image synthesis. International Journal of Computer Vision, 130(12), 2903\u20132923.","journal-title":"International Journal of Computer Vision"},{"key":"2208_CR64","unstructured":"Tan, M., & Le, Q.V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International Conference on Machine Learning, ICML, vol\u00a097, pp 6105\u20136114."},{"issue":"1\u201366","key":"2208_CR65","first-page":"12","volume":"66","author":"J Thies","year":"2019","unstructured":"Thies, J., Zollh\u00f6fer, M., & Nie\u00dfner, M. (2019). Deferred neural rendering: Image synthesis using neural textures. ACM Transactions on Graphics, 66(1\u201366), 12.","journal-title":"ACM Transactions on Graphics"},{"issue":"1","key":"2208_CR66","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1145\/3292039","volume":"62","author":"J Thies","year":"2019","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., & Nie\u00dfner, M. (2019). Face2face: Real-time face capture and reenactment of RGB videos. Communications of the ACM, 62(1), 96\u2013104.","journal-title":"Communications of the ACM"},{"key":"2208_CR67","unstructured":"Tora. (2021). Deepfakes. https:\/\/github.com\/deepfakes\/faceswap, 2022, March 5."},{"key":"2208_CR68","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, pp 5998\u20136008."},{"key":"2208_CR69","doi-asserted-by":"crossref","unstructured":"Wang, C., & Deng, W. (2021). Representative forgery mining for fake face detection. In IEEE Conference on Computer Vision and Pattern Recognition, pp 14923\u201314932.","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"2208_CR70","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B.A., & Darrell, T. (2021). Tent: Fully test-time adaptation by entropy minimization. In International Conference on Learning Representations."},{"key":"2208_CR71","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.1109\/TIFS.2022.3186803","volume":"17","author":"J Wang","year":"2022","unstructured":"Wang, J., Sun, Y., & Tang, J. (2022). Lisiam: Localization invariance siamese network for deepfake detection. IEEE Transactions on Information Forensics and Security, 17, 2425\u20132436.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2208_CR72","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, O., Zhang, R., Owens, A., & Efros, A.A. (2020). Cnn-generated images are surprisingly easy to spot... for now. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8692\u20138701.","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"2208_CR73","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J.G., & Pfister, T. (2022b). Learning to prompt for continual learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 139\u2013149.","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"2208_CR74","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bao, J., Zhou, W., Wang, W., & Li, H. (2023). Altfreezing for more general video face forgery detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4129\u20134138.","DOI":"10.1109\/CVPR52729.2023.00402"},{"key":"2208_CR75","first-page":"3","volume":"11211","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. European Conference on Computer Vision, 11211, 3\u201319.","journal-title":"European Conference on Computer Vision"},{"issue":"10","key":"2208_CR76","doi-asserted-by":"publisher","first-page":"2731","DOI":"10.1007\/s11263-021-01499-z","volume":"129","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Tan, Z., Tiwari, P., Pandey, H. M., Wan, J., Lei, Z., Guo, G., & Li, S. Z. (2021). Cascaded split-and-aggregate learning with feature recombination for pedestrian attribute recognition. International Journal of Computer Vision, 129(10), 2731\u20132744.","journal-title":"International Journal of Computer Vision"},{"key":"2208_CR77","doi-asserted-by":"crossref","unstructured":"Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T., & Sun, M. (2021). CPT: Colorful prompt tuning for pre-trained vision-language models. arxiv: abs\/2109.11797","DOI":"10.18653\/v1\/2022.findings-acl.273"},{"key":"2208_CR78","unstructured":"Zhang, M., Marklund, H., Dhawan, N., Gupta, A., Levine, S., & Finn, C. (2021). Adaptive risk minimization: Learning to adapt to domain shift. In Advances in Neural Information Processing Systems, pp 23664\u201323678."},{"key":"2208_CR79","unstructured":"Zhang, Q., & Chen, Y. (2023). Fast sampling of diffusion models with exponential integrator. In The Eleventh International Conference on Learning Representations."},{"key":"2208_CR80","first-page":"493","volume":"13695","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., & Li, H. (2022). Tip-adapter: Training-free adaption of CLIP for few-shot classification. European Conference on Computer Vision, 13695, 493\u2013510.","journal-title":"European Conference on Computer Vision"},{"key":"2208_CR81","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., & Yu, N. (2021). Multi-attentional deepfake detection. In IEEE Conference on Computer Vision and Pattern Recognition, pp 2185\u20132194.","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"2208_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., & Liu, Z. (2022a). Conditional prompt learning for vision-language models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 16795\u201316804.","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"2208_CR83","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"2208_CR84","doi-asserted-by":"publisher","first-page":"8342","DOI":"10.1109\/TPAMI.2022.3233586","volume":"45","author":"X Zhu","year":"2023","unstructured":"Zhu, X., Fei, H., Zhang, B., Zhang, T., Zhang, X., Li, S. Z., & Lei, Z. (2023). Face forgery detection by 3d decomposition and composition search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7), 8342\u20138357.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2208_CR85","doi-asserted-by":"crossref","unstructured":"Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y. (2020). Wilddeepfake: A challenging real-world dataset for deepfake detection. In The 28th ACM International Conference on Multimedia, pp 2382\u20132390.","DOI":"10.1145\/3394171.3413769"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02208-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02208-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02208-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:44:07Z","timestamp":1737528247000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02208-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,13]]},"references-count":85,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2208"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02208-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,13]]},"assertion":[{"value":"15 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}