{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T19:20:47Z","timestamp":1785698447804,"version":"3.56.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031064326","type":"print"},{"value":"9783031064333","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06433-3_19","type":"book-chapter","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T18:03:24Z","timestamp":1652551404000},"page":"219-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":236,"title":["Combining EfficientNet and\u00a0Vision Transformers for\u00a0Video Deepfake Detection"],"prefix":"10.1007","author":[{"given":"Davide Alessandro","family":"Coccomini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Messina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Gennaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrizio","family":"Falchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,15]]},"reference":[{"key":"19_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/978-3-030-30642-7_27","volume-title":"Image Analysis and Processing \u2013 ICIAP 2019","author":"G Amato","year":"2019","unstructured":"Amato, G., Ciampi, L., Falchi, F., Gennaro, C., Messina, N.: Learning pedestrian detection from virtual worlds. In: Ricci, E., Rota Bul\u00f2, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019, Part I. LNCS, vol. 11751, pp. 302\u2013312. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30642-7_27"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Amerini, I., Galteri, L., Caldelli, R., Del Bimbo, A.: Deepfake video detection through optical flow based CNN. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"19_CR3","unstructured":"Buslaev, A., Parinov, A., Khvedchenya, E., Iglovikov, V.I., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. ArXiv e-prints (2018)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Chesney, B., Citron, D.: Deepfakes: a looming challenge for privacy, democracy, and national security. Calif. L. Rev. 107, 1753 (2019)","DOI":"10.2139\/ssrn.3213954"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00916","DOI":"10.1109\/CVPR.2018.00916"},{"issue":"18","key":"19_CR7","doi-asserted-by":"publisher","first-page":"5250","DOI":"10.3390\/s20185250","volume":"20","author":"L Ciampi","year":"2020","unstructured":"Ciampi, L., Messina, N., Falchi, F., Gennaro, C., Amato, G.: Virtual to real adaptation of pedestrian detectors. Sensors 20(18), 5250 (2020)","journal-title":"Sensors"},{"key":"19_CR8","unstructured":"Dolhansky, B., et al.: The deepfake detection challenge (DFDC) dataset. arXiv preprint arXiv:2006.07397 (2020)"},{"key":"19_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"19_CR10","unstructured":"Dufour, N., Gully, A.: Contributing data to deep-fake detection research (2019). https:\/\/ai.googleblog.com\/2019\/09\/contributing-data-to-deepfake-detection.html"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Fagni, T., Falchi, F., Gambini, M., Martella, A., Tesconi, M.: TweepFake: about detecting deepfake tweets. PLoS ONE 16(5), e0251415 (2021)","DOI":"10.1371\/journal.pone.0251415"},{"key":"19_CR12","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021 (2021)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Giudice, O., Guarnera, L., Battiato, S.: Fighting deepfakes by detecting GAN DCT anomalies. J. Imaging 7(8), 128 (2021)","DOI":"10.3390\/jimaging7080128"},{"key":"19_CR14","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Guarnera, L., Giudice, O., Battiato, S.: Deepfake detection by analyzing convolutional traces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"19_CR16","unstructured":"Heo, Y.J., Choi, Y.J., Lee, Y.W., Kim, B.G.: Deepfake detection scheme based on vision transformer and distillation. arXiv preprint arXiv:2104.01353 (2021)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, L., Li, R., Wu, W., Qian, C., Loy, C.C.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of styleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"19_CR19","doi-asserted-by":"publisher","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. (CSUR) (2021). https:\/\/doi.org\/10.1145\/3505244","DOI":"10.1145\/3505244"},{"key":"19_CR20","unstructured":"Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: International Conference on Machine Learning, pp. 1857\u20131865. PMLR (2017)"},{"key":"19_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"19_CR22","unstructured":"Korshunov, P., Marcel, S.: Deepfakes: a new threat to face recognition? assessment and detection. arXiv preprint arXiv:1812.08685 (2018)"},{"key":"19_CR23","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3207\u20133216 (2020)","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"19_CR24","unstructured":"de Lima, O., Franklin, S., Basu, S., Karwoski, B., George, A.: Deepfake detection using spatiotemporal convolutional networks. arXiv preprint arXiv:2006.14749 (2020)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"MacAvaney, S., Nardini, F.M., Perego, R., Tonellotto, N., Goharian, N., Frieder, O.: Efficient document re-ranking for transformers by precomputing term representations. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 49\u201358 (2020)","DOI":"10.1145\/3397271.3401093"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Carrara, F., Falchi, F., Gennaro, C.: Testing deep neural networks on the same-different task. In: 2019 International Conference on Content-Based Multimedia Indexing (CBMI), pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/CBMI.2019.8877412"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Carrara, F., Gennaro, C., Falchi, F.: Solving the same-different task with convolutional neural networks. Pattern Recognit. Lett. 143, 75\u201380 (2021)","DOI":"10.1016\/j.patrec.2020.12.019"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Esuli, A., Falchi, F., Gennaro, C., Marchand-Maillet, S.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(4), 1\u201323 (2021)","DOI":"10.1145\/3451390"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Messina, N., Falchi, F., Esuli, A., Amato, G.: Transformer reasoning network for image-text matching and retrieval. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5222\u20135229. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Montserrat, D.M., et al.: Deepfakes detection with automatic face weighting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 668\u2013669 (2020)","DOI":"10.1109\/CVPRW50498.2020.00342"},{"key":"19_CR31","unstructured":"Perov, I., et al.: DeepFaceLab: A simple, flexible and extensible face swapping framework. arXiv preprint arXiv:2005.05535 (2020)"},{"key":"19_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91\u201399 (2015)"},{"key":"19_CR33","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1\u201311 (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"19_CR34","unstructured":"Seferbekov, S.: DFDC 1st place solution (2020). https:\/\/github.com\/selimsef\/dfdc_deepfake_challenge"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., Ortega-Garcia, J.: Deepfakes and beyond: a survey of face manipulation and fake detection. Inf. Fusion 64, 131\u2013148 (2020)","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"19_CR36","unstructured":"Wodajo, D., Atnafu, S.: Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:2102.11126 (2021)"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8261\u20138265. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499\u20131503 (2016)","DOI":"10.1109\/LSP.2016.2603342"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06433-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:11:15Z","timestamp":1709813475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06433-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031064326","9783031064333"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06433-3_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lecce","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2021.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"168","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}