{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:57:12Z","timestamp":1775066232725,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197741","type":"print"},{"value":"9783031197758","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\/978-3-031-19775-8_35","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"596-613","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Hierarchical Contrastive Inconsistency Learning for\u00a0Deepfake Video Detection"],"prefix":"10.1007","author":[{"given":"Zhihao","family":"Gu","sequence":"first","affiliation":[]},{"given":"Taiping","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Beuve, N., Hamidouche, W., Deforges, O.: DmyT: dummy triplet loss for deepfake detection. In: WSMMADGD (2021)","DOI":"10.1145\/3476099.3484316"},{"key":"35_CR2","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, X., Guo, Z., Zhang, X., Sun, J.: Dynamic region-aware convolution. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"35_CR5","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: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"35_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, B., Xu, J., Wu, S., Ding, S., Zhang, W.: Towards practical certifiable patch defense with vision transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01472"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"35_CR9","unstructured":"Dolhansky, B., Howes, R., Pflaum, B., Baram, N., Ferrer, C.C.: The deepfake detection challenge (DFDC) preview dataset. In: arXiv (2019)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Fung, S., Lu, X., Zhang, C., Li, C.T.: Deepfakeucl: deepfake detection via unsupervised contrastive learning. In: IJCNN (2021)","DOI":"10.1109\/IJCNN52387.2021.9534089"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Gu, Q., Chen, S., Yao, T., Chen, Y., Ding, S., Yi, R.: Exploiting fine-grained face forgery clues via progressive enhancement learning. In: AAAI (2021)","DOI":"10.1609\/aaai.v36i1.19954"},{"key":"35_CR12","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: ACM MM (2021)","DOI":"10.1145\/3474085.3475508"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Gu, Z., Chen, Y., Yao, T., Ding, S., Li, J., Ma, L.: Delving into the local: dynamic inconsistency learning for deepfake video detection. In: AAAI (2022)","DOI":"10.24963\/ijcai.2022\/129"},{"key":"35_CR14","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: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. In: NC (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Hu, Z., Xie, H., Wang, Y., Li, J., Wang, Z., Zhang, Y.: Dynamic inconsistency-aware deepfake video detection. In: IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/102"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, Z., Guo, Y.: Supervae: superpixelwise variational autoencoder for salient object detection. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018569"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, Z., Li, Q., Wu, Y., Hu, A.: Group-wise deep object co-segmentation with co-attention recurrent neural network. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00861"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, Z., Tang, L., Hu, A.: Two-B-real net: two-branch network for real-time salient object detection. In: ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8683022"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, Z., Tang, L., Sun, Y., Shi, J.: Detecting robust co-saliency with recurrent co-attention neural network. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/115"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, Z., Wang, Q., Li, Q.: Co-saliency detection based on hierarchical consistency. In: ACM MM (2019)","DOI":"10.1145\/3343031.3351016"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Li, B., Xu, J., Wu, S., Ding, S., Li, J., Huang, F.: Detecting adversarial patch attacks through global-local consistency. CoRR (2021)","DOI":"10.1145\/3475724.3483606"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Face X-ray for more general face forgery detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Sharp multiple instance learning for deepfake video detection. In: ACM MM (2020)","DOI":"10.1145\/3394171.3414034"},{"key":"35_CR27","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 (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"35_CR28","unstructured":"Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. arXiv (2018)"},{"key":"35_CR29","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., Li, J., Huang, F., Lu, T.: TEINet: towards an efficient architecture for video recognition. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: TAM: temporal adaptive module for video recognition. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"35_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1007\/978-3-030-58571-6_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"I Masi","year":"2020","unstructured":"Masi, I., Killekar, A., Mascarenhas, R.M., Gurudatt, S.P., AbdAlmageed, W.: Two-branch recurrent network for isolating deepfakes in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 667\u2013684. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_39"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Matern, F., Riess, C., Stamminger, M.: Exploiting visual artifacts to expose deepfakes and face manipulations. In: CVPRW (2019)","DOI":"10.1109\/WACVW.2019.00020"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Yamagishi, J., Echizen, I.: Capsule-forensics: using capsule networks to detect forged images and videos. In: ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"35_CR36","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv (2018)"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Qi, H., et al.: DeepRhythm: exposing deepfakes with attentional visual heartbeat rhythms. In: ACM MM (2020)","DOI":"10.1145\/3394171.3413707"},{"key":"35_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-58610-2_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Qian","year":"2020","unstructured":"Qian, Y., Yin, G., Sheng, L., Chen, Z., Shao, J.: Thinking in frequency: face forgery detection by mining frequency-aware clues. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 86\u2013103. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_6"},{"key":"35_CR39","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"35_CR41","doi-asserted-by":"crossref","unstructured":"Sohrawardi, S.J., et al.: Poster: towards robust open-world detection of deepfakes. In: ACM CCCS (2019)","DOI":"10.1145\/3319535.3363269"},{"key":"35_CR42","doi-asserted-by":"crossref","unstructured":"Sun, K., Yao, T., Chen, S., Ding, S., Ji, R., et al.: Dual contrastive learning for general face forgery detection. In: AAAI (2021)","DOI":"10.1609\/aaai.v36i2.20130"},{"key":"35_CR43","doi-asserted-by":"crossref","unstructured":"Tang, L., Li, B.: CLASS: cross-level attention and supervision for salient objects detection. In: Ishikawa, H., Liu, C., Pajdla, T., Shi, J. (eds.) ACCV (2020)","DOI":"10.1007\/978-3-030-69535-4_26"},{"key":"35_CR44","unstructured":"Tang, L., Li, B., Zhong, Y., Ding, S., Song, M.: Disentangled high quality salient object detection. In: ICCV (2021)"},{"key":"35_CR45","doi-asserted-by":"crossref","unstructured":"Wang, G., Jiang, Q., Jin, X., Li, W., Cui, X.: MC-LCR: multi-modal contrastive classification by locally correlated representations for effective face forgery detection. arXiv (2021)","DOI":"10.1016\/j.knosys.2022.109114"},{"key":"35_CR46","unstructured":"Wang, G., Zhou, J., Wu, Y.: Exposing deep-faked videos by anomalous co-motion pattern detection. arXiv (2020)"},{"key":"35_CR47","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"35_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"35_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Yao, T., Ding, S., Ma, L.: Face manipulation detection via auxiliary supervision. In: ICONIP (2020)","DOI":"10.1007\/978-3-030-63830-6_27"},{"key":"35_CR50","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"35_CR51","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: DSANet: Dynamic segment aggregation network for video-level representation learning. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475344"},{"key":"35_CR52","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"35_CR53","doi-asserted-by":"crossref","unstructured":"Xu, Y., Raja, K., Pedersen, M.: Supervised contrastive learning for generalizable and explainable deepfakes detection. In: WCACV (2022)","DOI":"10.1109\/WACVW54805.2022.00044"},{"key":"35_CR54","doi-asserted-by":"crossref","unstructured":"Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"35_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, D., Li, C., Lin, F., Zeng, D., Ge, S.: Detecting deepfake videos with temporal dropout 3DCNN. In: AAAI (2021)","DOI":"10.24963\/ijcai.2021\/178"},{"key":"35_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Towards efficient data free black-box adversarial attack. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01469"},{"key":"35_CR57","unstructured":"Zhang, S., Guo, S., Huang, W., Scott, M.R., Wang, L.: V4D: 4D convolutional neural networks for video-level representation learning. arXiv (2020)"},{"key":"35_CR58","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Li, B., Tang, L., Kuang, S., Wu, S., Ding, S.: Detecting camouflaged object in frequency domain. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"35_CR59","unstructured":"Zhong, Y., Li, B., Tang, L., Tang, H., Ding, S.: Highly efficient natural image matting. CoRR (2021)"},{"key":"35_CR60","doi-asserted-by":"crossref","unstructured":"Zi, B., Chang, M., Chen, J., Ma, X., Jiang, Y.G.: Wilddeepfake: a challenging real-world dataset for deepfake detection. In: ACM MM (2020)","DOI":"10.1145\/3394171.3413769"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19775-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T10:19:52Z","timestamp":1728209992000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19775-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197741","9783031197758"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19775-8_35","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":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}