{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:47:48Z","timestamp":1778604468509,"version":"3.51.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"36","license":[{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876100"],"award-info":[{"award-number":["61876100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072286,61572296"],"award-info":[{"award-number":["62072286,61572296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18836-2","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T07:02:37Z","timestamp":1710918157000},"page":"83677-83693","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Noise-aware progressive multi-scale deepfake detection"],"prefix":"10.1007","volume":"83","author":[{"given":"Xinmiao","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3691-4942","authenticated-orcid":false,"given":"Wen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,20]]},"reference":[{"key":"18836_CR1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.inffus.2020.06.014","volume":"64","author":"R Tolosana","year":"2020","unstructured":"Tolosana R, Vera-Rodriguez R, Fierrez J, Morales A, Ortega-Garcia J (2020) Deepfakes and beyond: A survey of face manipulation and fake detection. Information Fusion 64:131\u2013148","journal-title":"Information Fusion"},{"key":"18836_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103525","volume":"223","author":"TT Nguyen","year":"2022","unstructured":"Nguyen TT, Nguyen QVH, Nguyen DT, Nguyen DT, Huynh-The T, Nahavandi S, Nguyen TT, Pham QV, Nguyen CM (2022) Deep learning for deepfakes creation and detection: A survey. Comput Vis Image Underst 223:103525","journal-title":"Comput Vis Image Underst"},{"key":"18836_CR3","doi-asserted-by":"publisher","first-page":"6259","DOI":"10.1007\/s11042-021-11733-y","volume":"81","author":"T Zhang","year":"2022","unstructured":"Zhang T (2022) Deepfake generation and detection. Multimedia Tools and Applications 81:6259\u20136276","journal-title":"Multimedia Tools and Applications"},{"key":"18836_CR4","doi-asserted-by":"crossref","unstructured":"Yang X, Li Y, Lyu S (2019) Exposing deep fakes using inconsistent head poses. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8261\u20138265. IEEE","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"18836_CR5","doi-asserted-by":"crossref","unstructured":"Nguyen HH, Yamagishi J, Echizen I (2019) Capsule-forensics: Using capsule networks to detect forged images and videos. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2307\u20132311. IEEE","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"18836_CR6","doi-asserted-by":"crossref","unstructured":"Amerini I, Galteri L, Caldelli R, Del Bimbo A (2019) Deepfake video detection through optical flow based cnn. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"18836_CR7","doi-asserted-by":"crossref","unstructured":"Dang H, Liu F, Stehouwer J, Liu X, Jain AK (2020) On the detection of digital face manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5781\u20135790","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"18836_CR8","doi-asserted-by":"crossref","unstructured":"Afchar D, Nozick V, Yamagishi J, Echizen I (2018) Mesonet: a compact facial video forgery detection network. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1\u20137. IEEE","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"18836_CR9","unstructured":"R\u00f6ssler A, Cozzolino D, Verdoliva L, Riess C, Thies J, Nie\u00dfner M (2018) Face forensics: A large-scale video dataset for forgery detection in human faces. arXiv:1803.09179"},{"key":"18836_CR10","doi-asserted-by":"crossref","unstructured":"Cozzolino D, Poggi G, Verdoliva L (2017) Recasting residual-based local descriptors as convolutional neural networks: an application to image forgery detection. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security, pp. 159\u2013164","DOI":"10.1145\/3082031.3083247"},{"key":"18836_CR11","doi-asserted-by":"publisher","first-page":"17521","DOI":"10.1007\/s11042-022-13797-w","volume":"82","author":"M Zanardelli","year":"2022","unstructured":"Zanardelli M, Guerrini F, Leonardi R, Adami N (2022) Image forgery detection: a survey of recent deep-learning approaches. Multimedia Tools and Applications 82:17521\u201317566","journal-title":"Multimedia Tools and Applications"},{"key":"18836_CR12","doi-asserted-by":"crossref","unstructured":"Wang H, Wu X, Huang Z, Xing EP (2020) High-frequency component helps explain the generalization of convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8684\u20138694","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"18836_CR13","doi-asserted-by":"crossref","unstructured":"Qi H, Guo Q, Juefei-Xu F, Xie X, Ma L, Feng W, Liu Y, Zhao J (2020) Deeprhythm: Exposing deepfakes with attentional visual heartbeat rhythms. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 4318\u20134327","DOI":"10.1145\/3394171.3413707"},{"key":"18836_CR14","doi-asserted-by":"crossref","unstructured":"Nguyen HH, Fang F, Yamagishi J, Echizen I (2019) Multi-task learning for detecting and segmenting manipulated facial images and videos. In: 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp. 1\u20138. IEEE","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"18836_CR15","doi-asserted-by":"crossref","unstructured":"Zhou P, Han X, Morariu VI, Davis LS (2018) Learning rich features for image manipulation detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1053\u20131061","DOI":"10.1109\/CVPR.2018.00116"},{"key":"18836_CR16","doi-asserted-by":"crossref","unstructured":"Masi I, Killekar A, Mascarenhas RM, Gurudatt SP, AbdAlmageed W (2020) Two-branch recurrent network for isolating deepfakes in videos. In: European Conference on Computer Vision, pp. 667\u2013684. Springer","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"18836_CR17","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: European Conference on Computer Vision, pp. 86\u2013103. Springer","DOI":"10.1007\/978-3-030-58610-2_6"},{"issue":"3","key":"18836_CR18","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1109\/TIFS.2012.2190402","volume":"7","author":"J Fridrich","year":"2012","unstructured":"Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Secur 7(3):868\u2013882","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"18836_CR19","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1109\/TIFS.2019.2924552","volume":"15","author":"O Mayer","year":"2019","unstructured":"Mayer O, Stamm MC (2019) Forensic similarity for digital images. IEEE Trans Inf Forensics Secur 15:1331\u20131346","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"18836_CR20","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15023\u201315033","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"18836_CR21","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: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1081\u20131088","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"18836_CR22","doi-asserted-by":"publisher","first-page":"42591","DOI":"10.1007\/s11042-021-11539-y","volume":"81","author":"L Kuang","year":"2022","unstructured":"Kuang L, Wang Y, Hang T, Chen B, Zhao G (2022) A dual-branch neural network for deepfake video detection by detecting spatial and temporal inconsistencies. Multimedia Tools and Applications 81:42591\u201342606","journal-title":"Multimedia Tools and Applications"},{"key":"18836_CR23","unstructured":"Durall R, Keuper M, Pfreundt FJ, Keuper J (2019) Unmasking deepfakes with simple features. arXiv:1911.00686"},{"key":"18836_CR24","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 772\u2013781","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"18836_CR25","doi-asserted-by":"crossref","unstructured":"Li Y, Chang MC, Lyu S (2018) In ictu oculi: Exposing ai generated fake face videos by detecting eye blinking. In: IEEE International Workshop on Information Forensics and Security","DOI":"10.1109\/WIFS.2018.8630787"},{"issue":"7","key":"18836_CR26","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee K (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Industr Inf 15(7):3952\u20133961","journal-title":"IEEE Trans Industr Inf"},{"issue":"4","key":"18836_CR27","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TCYB.2014.2336697","volume":"45","author":"J Yu","year":"2015","unstructured":"Yu J, Tao D, Wang M, Rui Y (2015) Learning to rank using user clicks and visual features for image retrieval. IEEE Transactions on Cybernetics 45(4):767\u2013779","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"18836_CR28","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"44","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H, Tao D, Rui Y (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell 44(2):563\u2013578","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"18836_CR29","first-page":"5659","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoen coder for human pose recovery. IEEE Trans Industr Electron 24(12):5659\u20135670","journal-title":"IEEE Trans Industr Electron"},{"issue":"6","key":"18836_CR30","first-page":"3742","volume":"62","author":"C Hong","year":"2014","unstructured":"Hong C, Yu J, Tao D, Wang M (2014) Image-based 3d human pose recovery by multi-view locality sensitive sparse retrieval. IEEE Trans Industr Electron 62(6):3742\u20133751","journal-title":"IEEE Trans Industr Electron"},{"key":"18836_CR31","doi-asserted-by":"crossref","unstructured":"Kohli A, Gupta A (2021) Detecting deepfake, faceswap and face2face facial forgeries using frequency cnn. Multimedia Tools and Applications 80:18461\u201318478. Springer","DOI":"10.1007\/s11042-020-10420-8"},{"key":"18836_CR32","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"11","key":"18836_CR33","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.1109\/TIFS.2018.2825953","volume":"13","author":"B Bayar","year":"2018","unstructured":"Bayar B, Stamm MC (2018) Constrained convolutional neural networks: A new approach towards general purpose image manipulation detection. IEEE Trans Inf Forensics Secur 13(11):2691\u20132706","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"18836_CR34","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"18836_CR35","unstructured":"Newman MEJ (2013) DeepFakes. http:\/\/github.com\/deepfakes\/faceswap"},{"key":"18836_CR36","doi-asserted-by":"crossref","unstructured":"Thies J, Zollhofer M, Stamminger M, Theobalt C, Nie\u00dfner M (2016) Face2face: Real-time face capture and reenactment of rgb videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2387\u20132395","DOI":"10.1109\/CVPR.2016.262"},{"key":"18836_CR37","unstructured":"MarekKowalski: FaceSwap (2013). https:\/\/github.com\/MarekKowalski\/FaceSwap"},{"issue":"4","key":"18836_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323035","volume":"38","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 (TOG) 38(4):1\u201312","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"18836_CR39","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3207\u20133216","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"18836_CR40","doi-asserted-by":"crossref","unstructured":"Jiang L, Li R, Wu W, Qian C, Loy CC (2020) Deeperforensics-1.0: A large-scale dataset for real-world face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2889\u20132898","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"18836_CR41","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR"},{"issue":"10","key":"18836_CR42","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 Process Lett 23(10):1499\u20131503","journal-title":"IEEE Signal Process Lett"},{"key":"18836_CR43","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"18836_CR44","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5001\u20135010","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"18836_CR45","doi-asserted-by":"crossref","unstructured":"Nadimpalli A, Rattani A (2023) Facial forgery-based deepfake detection using fine grained features. arXiv:2310.07028v1","DOI":"10.1109\/ICMLA58977.2023.00328"},{"issue":"15","key":"18836_CR46","doi-asserted-by":"publisher","first-page":"10861","DOI":"10.1007\/s00521-023-08271-z","volume":"35","author":"L Zhao","year":"2023","unstructured":"Zhao L, Zhang M, Ding H, Cui X (2023) Fine-grained deepfake detection based on cross-modality attention. Neural computing & applications 35(15):10861\u201310874","journal-title":"Neural computing & applications"},{"key":"18836_CR47","doi-asserted-by":"crossref","unstructured":"Waseem S, Abu-Bakar SARS, Omar Z, Ahmed BA, Baloch S, Hafeezallah A (2023) Multi-attention-based approach for deepfake face and expression swap detection and localization. EURASIP Journal on Image and Video Processing 2023(1)","DOI":"10.1186\/s13640-023-00614-z"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18836-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18836-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18836-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T13:14:49Z","timestamp":1731590089000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18836-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,20]]},"references-count":47,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["18836"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18836-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,20]]},"assertion":[{"value":"13 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2024","order":4,"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 they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}