{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:30:30Z","timestamp":1778081430893,"version":"3.51.4"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208752","type":"print"},{"value":"9783030208769","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-20876-9_39","type":"book-chapter","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T14:03:53Z","timestamp":1558793033000},"page":"620-634","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Video-Based Person Re-identification via 3D Convolutional Networks and Non-local Attention"],"prefix":"10.1007","author":[{"given":"Xingyu","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxiao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhouwang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,26]]},"reference":[{"key":"39_CR1","doi-asserted-by":"publisher","unstructured":"Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 60\u201365, June 2005. \n                      https:\/\/doi.org\/10.1109\/CVPR.2005.38","DOI":"10.1109\/CVPR.2005.38"},{"key":"39_CR2","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. CoRR abs\/1705.07750 (2017). \n                      http:\/\/arxiv.org\/abs\/1705.07750"},{"key":"39_CR3","unstructured":"Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: In IEEE International Workshop on Performance Evaluation for Tracking and Surveillance, Rio de Janeiro (2007)"},{"key":"39_CR4","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? CoRR abs\/1711.09577 (2017). \n                      http:\/\/arxiv.org\/abs\/1711.09577"},{"key":"39_CR5","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778, June 2016. \n                      https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR6","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. CoRR abs\/1502.01852 (2015). \n                      http:\/\/arxiv.org\/abs\/1502.01852"},{"key":"39_CR7","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. CoRR abs\/1703.07737 (2017). \n                      http:\/\/arxiv.org\/abs\/1703.07737"},{"key":"39_CR8","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). \n                      https:\/\/doi.org\/10.1007\/978-3-642-21227-7_9"},{"issue":"1","key":"39_CR9","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). \n                      https:\/\/doi.org\/10.1109\/TPAMI.2012.59","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR10","unstructured":"Kay, W., et al.: The kinetics human action video dataset. CoRR abs\/1705.06950 (2017). \n                      http:\/\/arxiv.org\/abs\/1705.06950"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Li, S., Bak, S., Carr, P., Wang, X.: Diversity regularized spatiotemporal attention for video-based person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00046"},{"key":"39_CR12","doi-asserted-by":"publisher","unstructured":"Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 152\u2013159, June 2014. \n                      https:\/\/doi.org\/10.1109\/CVPR.2014.27","DOI":"10.1109\/CVPR.2014.27"},{"key":"39_CR13","doi-asserted-by":"publisher","unstructured":"Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2197\u20132206, June 2015. \n                      https:\/\/doi.org\/10.1109\/CVPR.2015.7298832","DOI":"10.1109\/CVPR.2015.7298832"},{"key":"39_CR14","unstructured":"Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Yang, Y.: Improving person re-identification by attribute and identity learning. CoRR abs\/1703.07220 (2017). \n                      http:\/\/arxiv.org\/abs\/1703.07220"},{"key":"39_CR15","unstructured":"Liu, H., et al.: Video-based person re-identification with accumulative motion context. CoRR abs\/1701.00193 (2017). \n                      http:\/\/arxiv.org\/abs\/1701.00193"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, J., Ouyang, W.: Quality aware network for set to set recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.499"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Martinez del Rincon, J., Miller, P.: Recurrent convolutional network for video-based person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.148"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., Wang, L.: Mask-guided contrastive attention model for person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00129"},{"key":"39_CR19","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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46466-4_52"},{"key":"39_CR20","unstructured":"Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K.M.: Part-aligned bilinear representations for person re-identification. CoRR abs\/1804.07094 (2018). \n                      http:\/\/arxiv.org\/abs\/1804.07094"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.308"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.510"},{"key":"39_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008. Curran Associates, Inc. (2017). \n                      http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf"},{"key":"39_CR24","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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10593-2_45"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00813"},{"key":"39_CR26","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint \n                      arXiv:1712.04851\n                      \n                     (2017)"},{"key":"39_CR27","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: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.507"},{"key":"39_CR28","unstructured":"Yan, Y., Ni, B., Song, Z., Ma, C., Yan, Y., Yang, X.: Person re-identification via recurrent feature aggregation. CoRR abs\/1701.06351 (2017). \n                      http:\/\/arxiv.org\/abs\/1701.06351"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Spindle Net: person re-identification with human body region guided feature decomposition and fusion. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.103"},{"key":"39_CR30","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Tian, Q.: Person re-identification in the wild. CoRR abs\/1604.02531 (2016). \n                      http:\/\/arxiv.org\/abs\/1604.02531"},{"key":"39_CR31","doi-asserted-by":"publisher","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: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6776\u20136785, July 2017. \n                      https:\/\/doi.org\/10.1109\/CVPR.2017.717","DOI":"10.1109\/CVPR.2017.717"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20876-9_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T14:10:16Z","timestamp":1558793416000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20876-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208752","9783030208769"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20876-9_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"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"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}