{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:47:51Z","timestamp":1775274471541,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030041663","type":"print"},{"value":"9783030041670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04167-0_40","type":"book-chapter","created":{"date-parts":[[2018,11,16]],"date-time":"2018-11-16T18:47:46Z","timestamp":1542394066000},"page":"439-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid 2D and 3D Convolution Based Recurrent Network for Video-Based Person Re-identification"],"prefix":"10.1007","author":[{"given":"Li","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Xiao-Yuan","family":"Jing","sequence":"additional","affiliation":[]},{"given":"Xiaoke","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Fumin","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Xiaodong","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chunhe","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,17]]},"reference":[{"issue":"1","key":"40_CR1","first-page":"898","volume":"29","author":"L Bazzani","year":"2008","unstructured":"Bazzani, L., Cristani, M., Perina, A., Murino, V.: Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recogn. Lett. 29(1), 898\u2013903 (2008)","journal-title":"Pattern Recogn. Lett."},{"issue":"2","key":"40_CR2","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1109\/TPAMI.2017.2666805","volume":"40","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Zhu, X., Zheng, W., Lai, J.: Person re-identification by camera correlation aware feature augmentation. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 392\u2013408 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Chung, D., Tahboub, K., Delp, E.J.: A two stream siamese convolutional neural network for person re-identification. In: International Conference on Computer Vision, ICCV, pp. 1992\u20132000. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.218"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: Computer Vision and Pattern Recognition, CVPR, pp. 2360\u20132367. IEEE Computer Society (2010)","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Computer Vision and Pattern Recognition, CVPR, pp. 1933\u20131941. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition, CVPR, pp. 580\u2013587. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Computer Vision and Pattern Recognition, CVPR, pp. 1735\u20131742 (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"40_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-642-21227-7_9","volume-title":"Image Analysis","author":"M Hirzer","year":"2011","unstructured":"Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 91\u2013102. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21227-7_9"},{"issue":"4","key":"40_CR11","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1109\/TPAMI.2017.2701380","volume":"40","author":"Y Huang","year":"2018","unstructured":"Huang, Y., Wang, W., Wang, L.: Video super-resolution via bidirectional recurrent convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 1015\u20131028 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"40_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Jing, X.Y., et al.: Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning. In: Computer Vision and Pattern Recognition, CVPR, pp. 695\u2013704. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298669"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Li, S., Shao, M., Fu, Y.: Person re-identification by cross-view multi-level dictionary learning. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1109\/TPAMI.2017.2764893"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Liu, K., Ma, B., Zhang, W., Huang, R.: A spatio-temporal appearance representation for viceo-based pedestrian re-identification. In: International Conference on Computer Vision, ICCV, pp. 3810\u20133818. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.434"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., del Rinc\u00f3n, J.M., Miller, P.C.: Recurrent convolutional network for video-based person re-identification. In: Computer Vision and Pattern Recognition, CVPR, pp. 1325\u20131334. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.148"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Computer Vision and Pattern Recognition, CVPR, pp. 815\u2013823. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Su, C., Yang, F., Zhang, S., Tian, Q., Davis, L.S., Gao, W.: Multi-task learning with low rank attribute embedding for person re-identification. In: IEEE International Conference on Computer Vision, ICCV. pp. 3739\u20133747. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.426"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 4278\u20134284. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"40_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1007\/978-3-319-10593-2_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Wang","year":"2014","unstructured":"Wang, T., Gong, S., Zhu, X., Wang, S.: Person re-identification by video ranking. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 688\u2013703. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_45"},{"issue":"11","key":"40_CR21","doi-asserted-by":"publisher","first-page":"1854","DOI":"10.1109\/LSP.2015.2440294","volume":"22","author":"Y Xie","year":"2015","unstructured":"Xie, Y., Yu, H., Gong, X., Dong, Z., Gao, Y.: Learning visual-spatial saliency for multiple-shot person re-identification. IEEE Sig. Process. Lett. 22(11), 1854\u20131858 (2015)","journal-title":"IEEE Sig. Process. Lett."},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Xu, S., Cheng, Y., Gu, K., Yang, Y., Chang, S., Zhou, P.: Jointly attentive spatial-temporal pooling networks for video-based person re-identification. In: International Conference on Computer Vision, ICCV, pp. 4743\u20134752. IEEE Computer Society (2017)","DOI":"10.1109\/ICCV.2017.507"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"You, J., Wu, A., Li, X., Zheng, W.: Top-push video-based person re-identification. In: Computer Vision and Pattern Recognition, CVPR, pp. 1345\u20131353. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.150"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Computer Vision and Pattern Recognition, CVPR, pp. 4584\u20134593. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"40_CR25","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.neucom.2017.09.012","volume":"275","author":"W Zhang","year":"2018","unstructured":"Zhang, W., Chen, Q., Zhang, W., He, X.: Video paragraph captioning using hierarchical recurrent neural networks. Neurocomputing 275, 781\u2013787 (2018)","journal-title":"Neurocomputing"},{"issue":"10","key":"40_CR26","doi-asserted-by":"publisher","first-page":"2768","DOI":"10.1109\/TCSVT.2017.2718188","volume":"28","author":"W Zhang","year":"2018","unstructured":"Zhang, W., Yu, X., He, X.: Learning bidirectional temporal cues for video-based person re-identification. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2768\u20132776 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"40_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1007\/978-3-319-46466-4_52","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Zheng","year":"2016","unstructured":"Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868\u2013884. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_52"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, L., Wang, S., Tian, L., He, F., Liu, Z., Tian, Q.: Query-adaptive late fusion for image search and person re-identification. In: Computer Vision and Pattern Recognition, CVPR, pp. 1741\u20131750 (2015)","DOI":"10.1109\/CVPR.2015.7298783"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Huang, Y., Wang, W., Wang, L., Tan, T.: See the forest for the trees: joint spatial and temporal recurrent neural networks for video-based person re-identification. In: Computer Vision and Pattern Recognition, CVPR, pp. 6776\u20136785. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.717"},{"key":"40_CR30","unstructured":"Zhu, X., Jing, X., Wu, F., Feng, H.: Video-based person re-identification by simultaneously learning intra-video and inter-video distance metrics. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI, pp. 3552\u20133559. IJCAI\/AAAI Press (2016)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04167-0_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T02:53:16Z","timestamp":1775271196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04167-0_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041663","9783030041670"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04167-0_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"17 November 2018","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":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"575","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":"401","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":"70% - 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":"4","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":"6","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)"}}]}}