{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:43:39Z","timestamp":1785843819107,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819541089","type":"print"},{"value":"9789819541096","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4109-6_18","type":"book-chapter","created":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T20:15:13Z","timestamp":1763324113000},"page":"254-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Video Deepfake Detection via\u00a0Quality-Aware and\u00a0Multi-scale Audio-Visual Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2408-4874","authenticated-orcid":false,"given":"Jingfei","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6144-8065","authenticated-orcid":false,"given":"Xun","family":"Che","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0998-1517","authenticated-orcid":false,"given":"Qianmu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7414-7636","authenticated-orcid":false,"given":"Qian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: Proceedings of the 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20137 (2018). https:\/\/doi.org\/10.1109\/WIFS.2018.8630761","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Farid, H., Fried, O., Agrawala, M.: Detecting deep-fake videos from phoneme-viseme mismatches. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020)","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, Y., Song, Y., Liu, L., Wang, J.: Self-supervised learning of adversarial example: towards good generalizations for deepfake detection. arXiv preprint arXiv:2203.12208 (2022)","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, D., Yang, Z.X., Wu, E.: Robust and efficient memory network for video object segmentation. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1769\u20131774. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00304"},{"issue":"5","key":"18_CR5","doi-asserted-by":"publisher","first-page":"3340","DOI":"10.1109\/TCSVT.2023.3321977","volume":"34","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Zhang, D., Zheng, Y., Yang, Z.X., Wu, E., Zhao, H.: Boosting video object segmentation via robust and efficient memory network. IEEE Trans. Circuits Syst. Video Technol. 34(5), 3340\u20133352 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"18_CR6","unstructured":"Cheng, H., Guo, Y., Wang, T., Li, Q., Chang, X., Nie, L.: Voice-face homogeneity tells deepfake. arXiv preprint arXiv:2203.02195 (2022)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chugh, K., Gupta, P., Dhall, A., Subramanian, R.: Not made for each other: audio-visual dissonance-based deepfake detection and localization. In: Proceedings of 28th ACM International Conference on Multimedia (ACM MM), pp. 439\u2013447 (2020)","DOI":"10.1145\/3394171.3413700"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Proceedings of Asian Conference on Computer Vision Workshops (ACCV Workshops), pp. 251\u2013263 (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"18_CR9","unstructured":"Dolhansky, B., et al.: The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Feng, C., Chen, Z., Owens, A.: Self-supervised video forensics by audio-visual anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10491\u201310503 (2023)","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Georgescu, M., Fonseca, E., Ionescu, R.T., Lucic, M., Schmid, C., Arnab, A.: Audiovisual masked autoencoders. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16144\u201316154 (2023)","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"18_CR12","unstructured":"Gong, Y., et al.: Contrastive audio-visual masked autoencoder. In: Proceedings of International Conference on Learning Representations (ICLR) (2023)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Mira, R., Petridis, S., Pantic, M.: Leveraging real talking faces via self-supervision for robust forgery detection. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14950\u201314962 (2022)","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., Pantic, M.: Lips don\u2019t lie: a generalisable and robust approach to face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5039\u20135049 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00500","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124","volume":"136","author":"H Ilyas","year":"2023","unstructured":"Ilyas, H., Javed, A., Malik, K.M.: AVFakeNet: a unified end-to-end dense swin transformer deep learning model for audio-visual deepfakes detection. Appl. Soft Comput. 136, 110124 (2023)","journal-title":"Appl. Soft Comput."},{"key":"18_CR17","unstructured":"Khalid, H., Tariq, S., Uddin, M., Woo, S.S.: FakeAVCeleb: a novel audio-video multimodal deepfake dataset. arXiv preprint arXiv:2108.05080 (2021)"},{"key":"18_CR18","unstructured":"Korshunov, P., Marcel, S.: Deepfakes: a new threat to face recognition? Assessment and detection. arXiv preprint arXiv:1812.08685 (2018)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Kwon, P., You, J., Nam, G., Park, S., Chae, G.: Kodf: a large-scale Korean deepfake detection dataset. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10744\u201310753 (2021)","DOI":"10.1109\/ICCV48922.2021.01057"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Face x-ray for more general face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, M.C., Lyu, S.: In ictu oculi: exposing AI created fake videos by detecting eye blinking. In: Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS) (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"18_CR22","unstructured":"Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: Emotions don\u2019t lie: an audio-visual deepfake detection method using affective cues. In: ACM International Conference on Multimedia, pp. 2823\u20132832 (2020)","DOI":"10.1145\/3394171.3413570"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Yamagishi, J., Echizen, I.: Use of a capsule network to detect fake images and videos. arXiv preprint arXiv:1910.12467 (2019)","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Oorloff, T., et al.: AVFF: audio-visual feature fusion for video deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"18_CR26","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1109\/TASLP.2021.3057230","volume":"29","author":"Y Qian","year":"2021","unstructured":"Qian, Y., Chen, Z., Wang, S.: Audio-visual deep neural network for robust person verification. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1079\u20131092 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"R\u00f6ssler, 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 (ICCV), pp. 1\u201311 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00009","DOI":"10.1109\/ICCV.2019.00009"},{"key":"18_CR28","unstructured":"Sabir, E., Chen, J., Jaiswal, A., AbdAlmageed, W., Masi, I., Natarajan, P.: Recurrent convolutional strategies for face manipulation detection in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2019)"},{"key":"18_CR29","unstructured":"Wodajo, D., Atnafu, S.: Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:2102.11126 (2021)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Yang, W., et al.: AVoiD-DF: audio-visual joint learning for detecting deepfake. IEEE Trans. Inf. Forensics Secur. 18, 2015\u20132029 (2023)","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8261\u20138265 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683164","DOI":"10.1109\/ICASSP.2019.8683164"},{"issue":"8","key":"18_CR32","doi-asserted-by":"publisher","first-page":"4451","DOI":"10.1007\/s00521-023-09318-x","volume":"36","author":"D Zhang","year":"2024","unstructured":"Zhang, D., Yan, H., Chen, Y., Li, D., Hao, C.: Cross-domain few-shot learning based on feature adaptive distillation. Neural Comput. Appl. 36(8), 4451\u20134465 (2024)","journal-title":"Neural Comput. Appl."},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Lim, S.: Joint audio-visual deepfake detection. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14800\u201314809 (2021)","DOI":"10.1109\/ICCV48922.2021.01453"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4109-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:43:55Z","timestamp":1785840235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4109-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"ISBN":["9789819541089","9789819541096"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4109-6_18","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"17 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}