{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:07:00Z","timestamp":1760404020850,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030606381"},{"type":"electronic","value":"9783030606398"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-60639-8_31","type":"book-chapter","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T10:04:02Z","timestamp":1602669842000},"page":"369-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Cue and Temporal Attention for Person Recognition in Videos"],"prefix":"10.1007","author":[{"given":"Wenzhe","family":"Wang","sequence":"first","affiliation":[]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Fangtao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zihe","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,15]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Song, G., Leng, B., Liu, Y., Hetang, C., Cai, S.: Region-based quality estimation network for large-scale person re-identification. In: AAAI, pp. 7347\u20137354 (2018)","DOI":"10.1609\/aaai.v32i1.12305"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: CVPR, pp. 2138\u20132147 (2019)","DOI":"10.1109\/CVPR.2019.00224"},{"issue":"4","key":"31_CR5","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Oh, S.J., Benenson, R., Fritz, M., Schiele, B.: Person recognition in personal photo collections. In: ICCV, pp. 3862\u20133870 (2015)","DOI":"10.1109\/ICCV.2015.440"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Kumar, V., Namboodiri, A., Paluri, M., Jawahar, C.V.: Pose-aware person recognition. In: CVPR, pp. 6223\u20136232 (2017)","DOI":"10.1109\/CVPR.2017.719"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Taigman, Y., Fergus, R., Bourdev, L.: Beyond frontal faces: Improving person recognition using multiple cues. In: CVPR, pp. 4804\u20134813 (2015)","DOI":"10.1109\/CVPR.2015.7299113"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Li, H., Brandt, J., Lin, Z., Shen, X., Hua, G.: A multi-level contextual model for person recognition in photo albums. In: CVPR, pp. 1297\u20131305 (2016)","DOI":"10.1109\/CVPR.2016.145"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Lin, D.: Unifying identification and context learning for person recognition. In: CVPR, pp. 2217\u20132225 (2018)","DOI":"10.1109\/CVPR.2018.00236"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: iQIYI celebrity video identification challenge. In: ACM MM, pp. 2516\u20132520 (2019)","DOI":"10.1145\/3343031.3356081"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., Chang, Y., Chen, W., Shen, Q., Liao, J.: Residualdensenetwork: a simple approach for video person identification. In: ACM MM, pp. 2521\u20132525 (2019)","DOI":"10.1145\/3343031.3356050"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Fang, X., Zou, Y.: Make the best of face clues in iQIYI celebrity video identification challenge 2019. In: ACM MM, pp. 2526\u20132530 (2019)","DOI":"10.1145\/3343031.3356056"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Dong, C., Gu, Z., Huang, Z., Ji, W., Huo, J., Gao, Y.: Deepmef: a deep model ensemble framework for video based multi-modal person identification. In: ACM MM, pp. 2531\u20132534 (2019)","DOI":"10.1145\/3343031.3356057"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Chen, J., Yang, L., Xu, Y., Huo, J., Shi, Y., Gao, Y.: A novel deep multi-modal feature fusion method for celebrity video identification. In: ACM MM, pp. 2535\u20132538 (2019)","DOI":"10.1145\/3343031.3356067"},{"key":"31_CR16","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on Faces in \u2019Real-Life\u2019 Images: Detection, Alignment, and Recognition, pp. 1\u201314 (2008)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Q., Liu, W., Lin, D.: Person search in videos with one portrait through visual and temporal links. In: ECCV, pp. 425\u2013441 (2018)","DOI":"10.1007\/978-3-030-01261-8_26"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Gool, L.V.: Temporal segment networks: towards good practices for deep action recognition. In: ECCV, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"31_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"10","key":"31_CR21","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sig. Process. Lett. 23(10), 1499\u20131503 (2016)","journal-title":"IEEE Sig. Process. Lett."},{"key":"31_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Marin-Jimenez, M.J., Kalogeiton, V., Medina-Suarez, P., Zisserman, A.: LAEO-Net: revisiting people looking at each other in videos. In: CVPR, pp. 3477\u20133485 (2019)","DOI":"10.1109\/CVPR.2019.00359"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Vu, T.H., Osokin, A., Laptev, I.: Context-aware cnns for person head detection. In: ICCV, pp. 2893\u20132901 (2015)","DOI":"10.1109\/ICCV.2015.331"},{"key":"31_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-46487-9_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Guo","year":"2016","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87\u2013102. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"31_CR27","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, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"}],"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\/978-3-030-60639-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T22:04:52Z","timestamp":1760393092000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60639-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030606381","9783030606398"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60639-8_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 October 2020","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":"Nanjing","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/index_en.html","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 system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"402","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":"158","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":"39% - 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)"}}]}}