{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:02:43Z","timestamp":1743102163661,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533105"},{"type":"electronic","value":"9783031533112"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_7","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"86-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MobileViT-FocR: MobileViT with\u00a0Fixed-One-Centre Loss and\u00a0Gradient Reversal for\u00a0Generalised Fake Face Detection"],"prefix":"10.1007","author":[{"given":"Ting","family":"Peng","sequence":"first","affiliation":[]},{"given":"Yihang","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Rong","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yizhi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Yuqi","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Pursuing knowledge consistency: supervised hierarchical contrastive learning for facial action unit recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 111\u2013119 (2022)","DOI":"10.1145\/3503161.3548116"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Dang, H., Liu, F., Stehouwer, J., Liu, X., Jain, A.K.: On the detection of digital face manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5781\u20135790 (2020)","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"7_CR3","unstructured":"Dolhansky, B., et al.: The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Forgerynet: a versatile benchmark for comprehensive forgery analysis. arXiv preprint arXiv:2103.05630 (2021)","DOI":"10.1109\/CVPR46437.2021.00434"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Hu, J., Ren, Y., Yuan, Y., Li, Y., Chen, L.: Pathosisgan: sick face image synthesis with generative adversarial network. In: 2021 2nd International Conference on Artificial Intelligence and Information Systems, pp. 1\u20136 (2021)","DOI":"10.1145\/3469213.3470691"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Huang, J., Wang, X., Du, B., Du, P., Xu, C.: Deepfake mnist+: a deepfake facial animation dataset. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1973\u20131982 (2021)","DOI":"10.1109\/ICCVW54120.2021.00224"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Jia, Y., Zhang, J., Shan, S., Chen, X.: Single-side domain generalization for face anti-spoofing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8484\u20138493 (2020)","DOI":"10.1109\/CVPR42600.2020.00851"},{"key":"7_CR9","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Xie, H., Li, J., Wang, Z., Zhang, Y.: Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6458\u20136467 (2021)","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Li, W., Ma, Z., Deng, L.J., Fan, X., Tian, Y.: Neuron-based spiking transmission and reasoning network for robust image-text retrieval. IEEE Trans. Circ. Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3233042"},{"key":"7_CR13","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":"7_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Long, Q., Xu, L., Fang, Z., Song, G.: Hgk-gnn: heterogeneous graph kernel based graph neural networks. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1129\u20131138 (2021)","DOI":"10.1145\/3447548.3467429"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., Liu, W.: Generalizing face forgery detection with high-frequency features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16317\u201316326 (2021)","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Lyu, S.: Deepfake detection: current challenges and next steps. In: 2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/ICMEW46912.2020.9105991"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Ma, Z., Ju, W., Luo, X., Chen, C., Hua, X.S., Lu, G.: Improved deep unsupervised hashing via prototypical learning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 659\u2013667 (2022)","DOI":"10.1145\/3503161.3548403"},{"key":"7_CR20","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Ren, Y., et al.: Crossing the gap: Domain generalization for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2871\u20132880 (2023)","DOI":"10.1109\/CVPR52729.2023.00281"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"7_CR23","unstructured":"Seeprettyface.com: New version of face generators based on StyleGAN2. https:\/\/github.com\/a312863063\/generators-with-stylegan2\/, (April 26 2023)"},{"key":"7_CR24","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Toshpulatov, M., Lee, W., Lee, S.: Talking human face generation: a survey. Expert Syst. Appli. 119678 (2023)","DOI":"10.1016\/j.eswa.2023.119678"},{"key":"7_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-030-58542-6_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Viazovetskyi","year":"2020","unstructured":"Viazovetskyi, Y., Ivashkin, V., Kashin, E.: StyleGAN2 distillation for feed-forward image manipulation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 170\u2013186. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_11"},{"key":"7_CR27","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TIP.2023.3242777","volume":"32","author":"H Wang","year":"2023","unstructured":"Wang, H., et al.: Toward effective domain adaptive retrieval. IEEE Trans. Image Process. 32, 1285\u20131299 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: Cnn-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8695\u20138704 (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"7_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-319-46478-7_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Wen","year":"2016","unstructured":"Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499\u2013515. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_31"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Xu, K., Feng, M., Huang, W.: Seeing speech: magnetic resonance imaging-based vocal tract deformation visualization using cross-modal transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6947\u20136949 (2022)","DOI":"10.1145\/3503161.3547728"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Yang, C., An, Z., Cai, L., Xu, Y.: Hierarchical self-supervised augmented knowledge distillation. In: International Joint Conference on Artificial Intelligence, pp. 1217\u20131223 (2021)","DOI":"10.24963\/ijcai.2021\/168"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Yang, C., An, Z., Cai, L., Xu, Y.: Mutual contrastive learning for visual representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 36, pp. 3045\u20133053 (2022)","DOI":"10.1609\/aaai.v36i3.20211"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12319\u201312328 (2022)","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., Yu, N.: Multi-attentional deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2185\u20132194 (2021)","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, H., Fei, H., Lei, Z., Li, S.Z.: Face forgery detection by 3d decomposition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2929\u20132939 (2021)","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Cheng, X., Huang, Z., Chen, D., Zou, Y.: Enhancing code-switching for cross-lingual slu: a unified view of semantic and grammatical coherence. In: Proceedings of EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.486"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Cheng, X., Huang, Z., Chen, D., Zou, Y.: Towards unified spoken language understanding decoding via label-aware compact linguistics representations. In: Proceedings of ACL Findings (2023)","DOI":"10.18653\/v1\/2023.findings-acl.793"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:23:29Z","timestamp":1710257009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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)"}}]}}