{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:28:43Z","timestamp":1760171323150,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984688"},{"type":"electronic","value":"9789819984695"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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\/978-981-99-8469-5_3","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T17:02:18Z","timestamp":1703437338000},"page":"29-43","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Video Face Recognition Leveraging Temporal Information Based on\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jiewen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xingbo","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Xingguo","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Xuejun","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"3_CR2","unstructured":"Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. In: 4th International Conference on Learning Representations, ICLR 2016 (2015)"},{"key":"3_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Proceedings of the International Conference on Machine Learning (ICML), vol. 2, p. 4 (2021)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"4","key":"3_CR5","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TPAMI.2017.2700390","volume":"40","author":"C Ding","year":"2017","unstructured":"Ding, C., Tao, D.: Trunk-branch ensemble convolutional neural networks for video-based face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 1002\u20131014 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"issue":"10s","key":"3_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3507902","volume":"54","author":"H Du","year":"2022","unstructured":"Du, H., Shi, H., Zeng, D., Zhang, X.P., Mei, T.: The elements of end-to-end deep face recognition: a survey of recent advances. ACM Comput. Surv. (CSUR) 54(10s), 1\u201342 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gong, S., Shi, Y., Kalka, N.D., Jain, A.K.: Video face recognition: component-wise feature aggregation network (C-FAN). In: 2019 International Conference on Biometrics (ICB), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/ICB45273.2019.8987385"},{"key":"3_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102805","volume":"189","author":"G Guo","year":"2019","unstructured":"Guo, G., Zhang, N.: A survey on deep learning based face recognition. Comput. Vis. Image Underst. 189, 102805 (2019)","journal-title":"Comput. Vis. Image Underst."},{"issue":"6","key":"3_CR11","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1109\/THMS.2017.2681425","volume":"47","author":"F Hajati","year":"2017","unstructured":"Hajati, F., Tavakolian, M., Gheisari, S., Gao, Y., Mian, A.S.: Dynamic texture comparison using derivative sparse representation: application to video-based face recognition. IEEE Trans. Hum.-Mach. Syst. 47(6), 970\u2013982 (2017)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"H\u00f6rmann, S., Cao, Z., Knoche, M., Herzog, F., Rigoll, G.: Face aggregation network for video face recognition. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 2973\u20132977. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506037"},{"key":"3_CR14","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017)"},{"key":"3_CR15","unstructured":"Hu, W., Huang, Y., Zhang, F., Li, R., Li, W., Yuan, G.: Seqface: make full use of sequence information for face recognition. arXiv preprint arXiv:1803.06524 (2018)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Kim, S.T., Kim, D.H., Ro, Y.M.: Spatio-temporal representation for face authentication by using multi-task learning with human attributes. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2996\u20133000. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532909"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S.T., Ro, Y.M.: Facial dynamics interpreter network: what are the important relations between local dynamics for facial trait estimation? In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 464\u2013480 (2018)","DOI":"10.1007\/978-3-030-01258-8_29"},{"issue":"3","key":"3_CR18","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.cviu.2005.02.002","volume":"99","author":"K Lee","year":"2005","unstructured":"Lee, K., Ho, J., Yang, M., Kriegman, D.: Visual tracking and recognition using probabilistic appearance manifolds. Comput. Vis. Image Underst. 99(3), 303\u2013331 (2005)","journal-title":"Comput. Vis. Image Underst."},{"key":"3_CR19","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.neucom.2018.02.037","volume":"297","author":"Y Li","year":"2018","unstructured":"Li, Y., Zheng, W., Cui, Z., Zhang, T.: Face recognition based on recurrent regression neural network. Neurocomputing 297, 50\u201358 (2018)","journal-title":"Neurocomputing"},{"issue":"27","key":"3_CR20","doi-asserted-by":"publisher","first-page":"19493","DOI":"10.1007\/s11042-019-08408-0","volume":"79","author":"J Lin","year":"2020","unstructured":"Lin, J., Xiao, L., Wu, T., Bian, W.: Image set-based face recognition using pose estimation with facial landmarks. Multimedia Tools Appl. 79(27), 19493\u201319507 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"3_CR21","unstructured":"Liu, Y., et al.: iQIYI-VID: a large dataset for multi-modal person identification. arXiv preprint arXiv:1811.07548 (2018)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Maze, B., et al.: IARPA Janus benchmark-C: face dataset and protocol. In: 2018 International Conference on Biometrics (ICB), pp. 158\u2013165. IEEE (2018)","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"3_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107129","volume":"100","author":"F Mokhayeri","year":"2020","unstructured":"Mokhayeri, F., Granger, E.: A paired sparse representation model for robust face recognition from a single sample. Pattern Recogn. 100, 107129 (2020)","journal-title":"Pattern Recogn."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. arXiv preprint arXiv:2102.00719 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lu, J., Zhou, J.: Attention-aware deep reinforcement learning for video face recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3931\u20133940 (2017)","DOI":"10.1109\/ICCV.2017.424"},{"key":"3_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265\u20135274 (2018)","DOI":"10.1109\/CVPR.2018.00552"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: CVPR 2011, pp. 529\u2013534. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"3_CR29","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Neural aggregation network for video face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4362\u20134371 (2017)","DOI":"10.1109\/CVPR.2017.554"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Yang, J., Dong, X., Liu, L., Zhang, C., Shen, J., Yu, D.: Recurring the transformer for video action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14063\u201314073 (2022)","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"3_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58607-2_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Zhang","year":"2020","unstructured":"Zhang, M., Song, G., Zhou, H., Liu, Yu.: Discriminability distillation in group representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 1\u201319. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_1"},{"key":"3_CR33","unstructured":"Zhong, Y., Deng, W.: Face transformer for recognition. arXiv preprint arXiv:2103.14803 (2021)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8469-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T17:02:52Z","timestamp":1703437372000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8469-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819984688","9789819984695"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8469-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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 CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}