{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T16:17:27Z","timestamp":1771604247122,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2221-E-007-077-MY3"],"award-info":[{"award-number":["112-2221-E-007-077-MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 113-2634-F-002-003"],"award-info":[{"award-number":["NSTC 113-2634-F-002-003"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 113-2627-M-006-005"],"award-info":[{"award-number":["NSTC 113-2627-M-006-005"]}],"id":[{"id":"10.13039\/501100020950","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":[[2026,1]]},"DOI":"10.1007\/s11263-025-02606-0","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T03:44:08Z","timestamp":1767757448000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Ching-Yi","family":"Lai","sequence":"first","affiliation":[]},{"given":"Chih-Yu","family":"Jian","sequence":"additional","affiliation":[]},{"given":"Pei-Cheng","family":"Chuang","sequence":"additional","affiliation":[]},{"given":"Chia-Ming","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Chih-Chung","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Chiou-Ting","family":"Hsu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-2318","authenticated-orcid":false,"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"2606_CR1","first-page":"2661","volume":"1406","author":"IJ Goodfellow","year":"2014","unstructured":"Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks.,1406, 2661.","journal-title":"Generative adversarial networks."},{"key":"2606_CR2","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising Diffusion Probabilistic Models (2020). https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"2606_CR3","doi-asserted-by":"crossref","unstructured":"Zhuang, W., Chu, Q., Tan, Z., Liu, Q., Yuan, H., Miao, C., Luo, Z., Yu, N.: UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In: Proc. European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"2606_CR4","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., Shao, J.: Thinking in frequency: Face forgery detection by mining frequency-aware clues. In: EProc. Uropean Conference on Computer Vision, pp. 86\u2013103 (2020)","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"2606_CR5","doi-asserted-by":"crossref","unstructured":"Pan, K., Yin, Y., Wei, Y., Lin, F., Ba, Z., Liu, Z., Wang, Z., Cavallaro, L., Ren, K.: DFIL: Deepfake incremental learning by exploiting domain-invariant forgery clues. In: Proc. ACM International Conference on Multimedia, pp. 8035\u20138046 (2023)","DOI":"10.1145\/3581783.3612377"},{"key":"2606_CR6","unstructured":"Hernandez-Ortega, J., Tolosana, R., Fierrez, J., Morales, A.: DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation (2020)"},{"key":"2606_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, M.-C., Lyu, S.: In ictu oculi: Exposing ai generated fake face videos by detecting eye blinking. arXiv preprint arXiv:1806.02877 (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"2606_CR8","unstructured":"Xu, Y., Liang, J., Jia, G., Yang, Z., Zhang, Y., He, R.: TALL: Thumbnail Layout for Deepfake Video Detection (2024). https:\/\/arxiv.org\/abs\/2307.07494"},{"issue":"2","key":"2606_CR9","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/TIFS.2011.2106121","volume":"6","author":"Y-L Chen","year":"2011","unstructured":"Chen, Y.-L., & Hsu, C.-T. (2011). Detecting recompression of jpeg images via periodicity analysis of compression artifacts for tampering detection. IEEE Transactions on Information Forensics and Security,6(2), 396\u2013406. https:\/\/doi.org\/10.1109\/TIFS.2011.2106121","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2606_CR10","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Nie, L., Liu, Z.: Deepfake-adapter: Dual-level adapter for deepfake detection. International Journal of Computer Vision (2024)","DOI":"10.1007\/s11263-024-02274-6"},{"key":"2606_CR11","unstructured":"Facebook Engineering Team: How Meta Encodes Your Videos. https:\/\/engineering.fb.com\/2021\/04\/05\/video-engineering\/how-facebook-encodes-your-videos\/"},{"issue":"10","key":"2606_CR12","doi-asserted-by":"publisher","first-page":"193","DOI":"10.3390\/jimaging7100193","volume":"7","author":"F Marcon","year":"2021","unstructured":"Marcon, F., et al. (2021). Detection of manipulated face videos over social networks: A large-scale study. Journal of Imaging,7(10), 193. https:\/\/doi.org\/10.3390\/jimaging7100193","journal-title":"Journal of Imaging"},{"key":"2606_CR13","doi-asserted-by":"publisher","unstructured":"Le, B.M., Woo, S.S.: Quality-agnostic deepfake detection with intra-model collaborative learning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22321\u201322332 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.02045","DOI":"10.1109\/ICCV51070.2023.02045"},{"key":"2606_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, D., Li, Y., Zhou, J., Li, Y.: Dpl: Cross-quality deepfake detection via dual progressive learning. In: Asian Conference on Computer Vision (ACCV), pp. 140\u2013156 (2025)","DOI":"10.1007\/978-981-96-0960-4_9"},{"key":"2606_CR15","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, T., Liu, Z.: Detecting and grounding multi-modal media manipulation. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"2606_CR16","unstructured":"Lai, C.-Y., Hsu, C.-T., Hsu, C.-C., Lin, C.-W.: Prompt-guided multi-modal contrastive learning for cross-compression-rate deepfake detection. In: Proc. British Machine Vision Conference (BMVC) (2024)"},{"key":"2606_CR17","doi-asserted-by":"crossref","unstructured":"Cai, Z., Ghosh, S., Adatia, A.P., Hayat, M., Dhall, A., Gedeon, T., Stefanov, K.: AV-Deepfake1M: A large-scale llm-driven audio-visual deepfake dataset. In: Proc. ACM International Conference on Multimedia, pp. 7414\u20137423 (2024)","DOI":"10.1145\/3664647.3680795"},{"key":"2606_CR18","doi-asserted-by":"crossref","unstructured":"Roessler, A., Cozzolino, D., Verdoliva, L., R\u00f6ssler, M., Nie\u00dfner, M.: Faceforensics++: Learning to detect manipulated facial images. Proc. IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"2606_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-df: A large-scale challenging dataset for deepfake forensics. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3207\u20133216 (2020)","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"2606_CR20","unstructured":"Dufour, N., Gully, A., Karlsson, P., Vorbyov, A., Leung, T., Childs, J., Bregler, C.: Deepfakes detection dataset. Google and Jigsaw (2019)"},{"key":"2606_CR21","doi-asserted-by":"crossref","unstructured":"Tan, C., Zhao, Y., Wei, S., Gu, G., Liu, P., Wei, Y.: Frequency-aware deepfake detection: improving generalizability through frequency space domain learning. In: Proc. AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"2606_CR22","doi-asserted-by":"crossref","unstructured":"Hu, S., Li, Y., Lyu, S.: Exposing gan-generated faces using inconsistent corneal specular highlights. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/ICASSP39728.2021.9414582"},{"key":"2606_CR23","doi-asserted-by":"crossref","unstructured":"Masi, I., al.: Two-branch recurrent network for isolating deepfakes in videos. arXiv preprint arXiv:2008.03412 (2020)","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"2606_CR24","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., Pantic, M.: Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5039\u20135049 (2021)","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"2606_CR25","unstructured":"Durall, R., Keuper, M., Keuper, J.: Watch your up-conv: Cnn-based gans can\u2019t hide their artifacts. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)"},{"issue":"4","key":"2606_CR26","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1109\/TAI.2023.3299894","volume":"5","author":"S Chhabra","year":"2024","unstructured":"Chhabra, S., Thakral, K., Mittal, S., Vatsa, M., & Singh, R. (2024). Low-quality deepfake detection via unseen artifacts. IEEE Transactions on Artificial Intelligence,5(4), 1573\u20131585.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"2606_CR27","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"2606_CR28","doi-asserted-by":"crossref","unstructured":"Hashmi, A., Shahzad, S.A., Lin, C.-W., Tsao, Y., Wang, H.-M.: AVTENet: A human-cognition-inspired audio-visual transformer-based ensemble network for video deepfake detection. IEEE Transactions on Cognitive and Developmental Systems 17(6) (2025)","DOI":"10.1109\/TCDS.2025.3554477"},{"key":"2606_CR29","unstructured":"Yu, C., Chen, P., Tian, J., et al.: A unified framework for modality-agnostic deepfake detection. arXiv preprint arXiv:2307.14491 (2023)"},{"key":"2606_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Wu, Z., Chen, J., Jiang, Y.-G.: M2tr: Multi-modal multi-scale transformers for deepfake detection. In: International Conference on Multimedia Retreval (2022)","DOI":"10.1145\/3512527.3531415"},{"key":"2606_CR31","unstructured":"Yang, M., Li, Y., Zhang, C., Hu, P., Peng, X.: Test-time adaptation against multi-modal reliability bias. In: International Conference on Learning Representations (2024)"},{"key":"2606_CR32","doi-asserted-by":"crossref","unstructured":"Gao, J., Ruan, J., Xiang, S., Yu, Z., Ji, K., Xie, M., Liu, T., Fu, Y.: LAMM: Label alignment for multi-modal prompt learning. arXiv preprint arXiv:2312.08212 (2023)","DOI":"10.1609\/aaai.v38i3.27950"},{"key":"2606_CR33","doi-asserted-by":"crossref","unstructured":"Xin, Y., Du, J., Wang, Q., Yan, K., Ding, S.: MmAP: multi-modal alignment prompt for cross-domain multi-task learning. In: Proc. AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i14.29540"},{"key":"2606_CR34","doi-asserted-by":"crossref","unstructured":"Huang, Y., Tang, J., Chen, Z., Zhang, R., Zhang, X., Chen, W., Zhao, Z., Zhao, Z., Lv, T., Hu, Z., Zhang, W.: Structure-clip: Towards scene graph knowledge to enhance multi-modal structured representations. In: Proc. AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"2606_CR35","doi-asserted-by":"crossref","unstructured":"Lee, J., Chung, S.-W., Kim, S., Kang, H.-G., Sohn, K.: Looking into your speech: Learning cross-modal affinity for audio-visual speech separation. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00139"},{"key":"2606_CR36","unstructured":"Liang, W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.: Intriguing properties of contrastive losses. In: Proc. Advances in Neural Information Processing Systems (2023)"},{"key":"2606_CR37","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of Machine Learning Research 9(11) (2008)"},{"key":"2606_CR38","doi-asserted-by":"crossref","unstructured":"Yu, Z., Shen, Y., Shi, J., Zhao, H., Torr, P.H., Zhao, G.: Physformer: Facial video-based physiological measurement with temporal difference transformer. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4186\u20134196 (2022)","DOI":"10.1109\/CVPR52688.2022.00415"},{"key":"2606_CR39","doi-asserted-by":"crossref","unstructured":"Sun, Z., Han, Y., Hua, Z., Ruan, N., Jia, W.: Improving the efficiency and robustness of deepfakes detection through precise geometric features. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3609\u20133618 (2021)","DOI":"10.1109\/CVPR46437.2021.00361"},{"key":"2606_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2606_CR41","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: Proc. International Conference on Machine Learning, pp. 8748\u20138763 (2021). PMLR"},{"key":"2606_CR42","unstructured":"Yu, Z., Li, X., Zhao, G.: Remote photoplethysmograph signal measurement from facial videos using spatio-temporal networks. arXiv preprint arXiv:1905.02419 (2019)"},{"key":"2606_CR43","doi-asserted-by":"crossref","unstructured":"Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: Faceforensics++: Learning to detect manipulated facial images. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"2606_CR44","unstructured":"Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., Ferrer, C.C.: The DeepFake Detection Challenge Dataset (2020)"},{"key":"2606_CR45","unstructured":"Diederik, P.K., Ba, J.: Adam: A Method for Stochastic Optimization (2017). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"2606_CR46","doi-asserted-by":"crossref","unstructured":"Niu, X., Han, H., Shan, S., Chen, X.: Vipl-hr: A multi-modal database for pulse estimation from less-constrained face video. In: Proc. Asian Conference on Computer Vision, pp. 562\u2013576 (2019)","DOI":"10.1007\/978-3-030-20873-8_36"},{"issue":"10","key":"2606_CR47","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters,23(10), 1499\u20131503.","journal-title":"IEEE Signal Processing Letters"},{"key":"2606_CR48","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1109\/TIFS.2023.3249566","volume":"18","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Liang, J., Xu, Y., Zhang, X.-Y., & He, R. (2023). Masked relation learning for deepfake detection. IEEE Transactions on Information Forensics and Security,18, 1696\u20131708.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2606_CR49","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., Ye, D.: Implicit identity driven deepfake face swapping detection. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2023)","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"2606_CR50","doi-asserted-by":"crossref","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: Proc. IEEE International Workshop on Information Forensics and Security, pp. 1\u20137 (2018). IEEE","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"2606_CR51","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., Guo, B.: Face x-ray for more general face forgery detection. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5001\u20135010 (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"2606_CR52","unstructured":"Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018)"},{"key":"2606_CR53","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.-Z., Hospedales, T.: Learning to generalize: Meta-learning for domain generalization. In: AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"2606_CR54","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Fang, F., Yamagishi, J., Echizen, I.: Multi-task learning for detecting and segmenting manipulated facial images and videos. In: Proc. IEEE International Conference on Biometrics Theory, Applications and Systems, pp. 1\u20138 (2019)","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"2606_CR55","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., Liu, W.: Generalizing face forgery detection with high-frequency features. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16317\u201316326 (2021)","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"2606_CR56","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., Yu, N.: Spatial-phase shallow learning: rethinking face forgery detection in frequency domain. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 772\u2013781 (2021)","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"2606_CR57","doi-asserted-by":"crossref","unstructured":"Sun, K., Liu, H., Ye, Q., Gao, Y., Liu, J., Shao, L., Ji, R.: Domain general face forgery detection by learning to weight. In: Proc. AAAI Conference on Artificial Intelligence, vol. 35, pp. 2638\u20132646 (2021)","DOI":"10.1609\/aaai.v35i3.16367"},{"key":"2606_CR58","doi-asserted-by":"crossref","unstructured":"Masi, I., Killekar, A., Mascarenhas, R.M., Gurudatt, S.P., AbdAlmageed, W.: Two-branch recurrent network for isolating deepfakes in videos. In: Proc. European Conference on Computer Vision, pp. 667\u2013684 (2020)","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"2606_CR59","doi-asserted-by":"crossref","unstructured":"Chen, S., Yao, T., Chen, Y., Ding, S., Li, J., Ji, R.: Local relation learning for face forgery detection. In: Proc. AAAI Conference on Artificial Intelligence, vol. 35, pp. 1081\u20131088 (2021)","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"2606_CR60","doi-asserted-by":"crossref","unstructured":"Sun, K., Yao, T., Chen, S., Ding, S., Li, J., Ji, R.: Dual contrastive learning for general face forgery detection. In: Proc. AAAI Conference on Artificial Intelligence, vol. 36, pp. 2316\u20132324 (2022)","DOI":"10.1609\/aaai.v36i2.20130"},{"key":"2606_CR61","doi-asserted-by":"crossref","unstructured":"Gu, Z., Chen, Y., Yao, T., Ding, S., Li, J., Huang, F., Ma, L.: Spatiotemporal inconsistency learning for deepfake video detection. In: Proc. ACM International Conference on Multimedia, pp. 3473\u20133481 (2021)","DOI":"10.1145\/3474085.3475508"},{"key":"2606_CR62","doi-asserted-by":"crossref","unstructured":"Sun, K., Liu, H., Yao, T., Sun, X., Chen, S., Ding, S., Ji, R.: An information theoretic approach for attention-driven face forgery detection. In: Proc. European Conference on Computer Vision, pp. 111\u2013127 (2022)","DOI":"10.1007\/978-3-031-19781-9_7"},{"key":"2606_CR63","doi-asserted-by":"crossref","unstructured":"Zhuang, W., Chu, Q., Tan, Z., Liu, Q., Yuan, H., Miao, C., Luo, Z., Yu, N.: Uia-vit: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In: Proc. European Conference on Computer Vision, pp. 391\u2013407 (2022)","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"2606_CR64","doi-asserted-by":"crossref","unstructured":"Khan, S.A., Dai, H.: Video transformer for deepfake detection with incremental learning. In: Proc. ACM International Conference on Multimedia, pp. 1821\u20131828 (2021)","DOI":"10.1145\/3474085.3475332"},{"key":"2606_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., Yu, N.: Multi-attentional deepfake detection. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2185\u20132194 (2021)","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"2606_CR66","doi-asserted-by":"crossref","unstructured":"Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., Ge, Z.: Implicit identity leakage: The stumbling block to improving deepfake detection generalization. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134004 (2023)","DOI":"10.1109\/CVPR52729.2023.00389"},{"key":"2606_CR67","doi-asserted-by":"crossref","unstructured":"Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., Yang, X.: End-to-end reconstruction-classification learning for face forgery detection. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4113\u20134122 (2022)","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"2606_CR68","doi-asserted-by":"crossref","unstructured":"Shi, L., Zhang, J., Shan, S.: Real face foundation representation learning for generalized deepfake detection. arXiv preprint arXiv:2303.08439 (2023)","DOI":"10.2139\/ssrn.4620605"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02606-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02606-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02606-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:42:17Z","timestamp":1771602137000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02606-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":68,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2606"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02606-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"1 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Codes will be made publicly available after the paper gets accepted.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"40"}}