{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:55:05Z","timestamp":1781805305651,"version":"3.54.5"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T00:00:00Z","timestamp":1627257600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T00:00:00Z","timestamp":1627257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976098"],"award-info":[{"award-number":["61976098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"crossref","award":["2018J01090"],"award-info":[{"award-number":["2018J01090"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2019J06017"],"award-info":[{"award-number":["2019J06017"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Vehicle re-identification is a challenging task that matches vehicle images captured by different cameras. Recent vehicle re-identification approaches exploit complex deep networks to learn viewpoint robust features for obtaining accurate re-identification results, which causes large computations in their testing phases to restrict the vehicle re-identification speed. In this paper, we propose a viewpoint robust knowledge distillation (VRKD) method for accelerating vehicle re-identification. The VRKD method consists of a complex teacher network and a simple student network. Specifically, the teacher network uses quadruple directional deep networks to learn viewpoint robust features. The student network only contains a shallow backbone sub-network and a global average pooling layer. The student network distills viewpoint robust knowledge from the teacher network via minimizing the Kullback-Leibler divergence between the posterior probability distributions resulted from the student and teacher networks. As a result, the vehicle re-identification speed is significantly accelerated since only the student network of small testing computations is demanded. Experiments on VeRi776 and VehicleID datasets show that the proposed VRKD method outperforms many state-of-the-art vehicle re-identification approaches with better accurate and speed performance.<\/jats:p>","DOI":"10.1186\/s13634-021-00767-x","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T17:02:42Z","timestamp":1627318962000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Viewpoint robust knowledge distillation for accelerating vehicle re-identification"],"prefix":"10.1186","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7420-3279","authenticated-orcid":false,"given":"Yi","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanqiang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,26]]},"reference":[{"key":"767_CR1","doi-asserted-by":"crossref","unstructured":"X. Liu, W. Liu, T. Mei, H. Ma, in European Conference on Computer Vision. A deep learning-based approach to progressive vehicle re-identification for urban surveillance, (2016), pp. 869\u2013884.","DOI":"10.1007\/978-3-319-46475-6_53"},{"key":"767_CR2","doi-asserted-by":"crossref","unstructured":"H. Liu, Y. Tian, Y. Wang, L. Pang, T. Huang, in IEEE Conference on Computer Vision and Pattern Recognition. Deep relative distance learning: Tell the difference between similar vehicles, (2016), pp. 2167\u20132175.","DOI":"10.1109\/CVPR.2016.238"},{"key":"767_CR3","doi-asserted-by":"crossref","unstructured":"Y. Zhou, L. Shao, in IEEE Winter Conference on Applications of Computer Vision. Vehicle re-identification by adversarial bi-directional lstm network, (2018), pp. 653\u2013662.","DOI":"10.1109\/WACV.2018.00077"},{"issue":"7","key":"767_CR4","doi-asserted-by":"publisher","first-page":"3275","DOI":"10.1109\/TIP.2018.2819820","volume":"27","author":"Y. Zhou","year":"2018","unstructured":"Y. Zhou, L. Liu, L. Shao, Vehicle re-identification by deep hidden multi-view inference. IEEE Trans. Image Process.27(7), 3275\u20133287 (2018).","journal-title":"IEEE Trans. Image Process."},{"key":"767_CR5","doi-asserted-by":"crossref","unstructured":"Y. Zhou, L. Shao, in IEEE Conference on Computer Vision and Pattern Recognition. Viewpoint-aware attentive multi-view inference for vehicle re-identification, (2018), pp. 6489\u20136498.","DOI":"10.1109\/CVPR.2018.00679"},{"key":"767_CR6","doi-asserted-by":"crossref","unstructured":"W. Lin, Y. Li, X. Yang, P. Peng, J. Xing, in IEEE International Conference on Multimedia & Expo. Multi-view learning for vehicle re-identification, (2019), pp. 832\u2013837.","DOI":"10.1109\/ICME.2019.00148"},{"key":"767_CR7","doi-asserted-by":"crossref","unstructured":"Y. Zhou, L. Shao, in British Machine Vision Conference, 1. Cross-view gan based vehicle generation for re-identification, (2017), pp. 1\u201312.","DOI":"10.5244\/C.31.186"},{"issue":"1","key":"767_CR8","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1109\/TITS.2019.2901312","volume":"21","author":"J. Zhu","year":"2020","unstructured":"J. Zhu, H. Zeng, J. Huang, S. Liao, L. Zhen, C. Cai, L. Zheng, Vehicle re-identification using quadruple directional deep learning features. IEEE Trans. Intell. Transp. Syst.21(1), 410\u2013420 (2020).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"4","key":"767_CR9","doi-asserted-by":"publisher","first-page":"2944","DOI":"10.1109\/JIOT.2020.2963996","volume":"7","author":"J. Zhu","year":"2020","unstructured":"J. Zhu, J. Huang, H. Zeng, X. Ye, B. Li, Z. Lei, L. Zheng, Object re-identification via joint quadruple decorrelation directional deep networks in smart transportation. IEEE Internet Things J.7(4), 2944\u20132954 (2020).","journal-title":"IEEE Internet Things J."},{"key":"767_CR10","doi-asserted-by":"crossref","unstructured":"P. Khorramshahi, A. Kumar, N. Peri, S. S. Rambhatla, J. -C. Chen, R. Chellappa, in IEEE International Conference on Computer Vision. A dual-path model with adaptive attention for vehicle re-identification, (2019), pp. 6132\u20136141.","DOI":"10.1109\/ICCV.2019.00623"},{"key":"767_CR11","doi-asserted-by":"crossref","unstructured":"Z. Tang, M. Naphade, S. Birchfield, J. Tremblay, W. Hodge, R. Kumar, S. Wang, X. Yang, in IEEE International Conference on Computer Vision. Pamtri: Pose-aware multi-task learning for vehicle re-identification using highly randomized synthetic data, (2019), pp. 211\u2013220.","DOI":"10.1109\/ICCV.2019.00030"},{"issue":"8","key":"767_CR12","doi-asserted-by":"publisher","first-page":"3794","DOI":"10.1109\/TIP.2019.2902112","volume":"28","author":"Y. Lou","year":"2019","unstructured":"Y. Lou, Y. Bai, J. Liu, S. Wang, L. -Y. Duan, Embedding adversarial learning for vehicle re-identification. IEEE Trans. Image Process.28(8), 3794\u20133807 (2019).","journal-title":"IEEE Trans. Image Process."},{"key":"767_CR13","doi-asserted-by":"crossref","unstructured":"B. He, J. Li, Y. Zhao, Y. Tian, in IEEE Conference on Computer Vision and Pattern Recognition. Part-regularized near-duplicate vehicle re-identification, (2019), pp. 3997\u20134005.","DOI":"10.1109\/CVPR.2019.00412"},{"key":"767_CR14","doi-asserted-by":"crossref","unstructured":"J. Zhu, H. Zeng, Z. Lei, L. Zheng, C. Cai, in IEEE International Conference on Pattern Recognition. A shortly and densely connected convolutional neural network for vehicle re-identification, (2018), pp. 3285\u20133290.","DOI":"10.1109\/ICPR.2018.8545514"},{"key":"767_CR15","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, in IEEE Conference on Computer Vision and Pattern Recognition. Deep residual learning for image recognition, (2016), pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"767_CR16","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. van der Maaten, K. Q. Weinberger, in IEEE Conference on Computer Vision and Pattern Recognition. Densely connected convolutional networks, (2017), pp. 2261\u20132269.","DOI":"10.1109\/CVPR.2017.243"},{"key":"767_CR17","doi-asserted-by":"publisher","unstructured":"Z. Zheng, T. Ruan, Y. Wei, Y. Yang, T. Mei, VehicleNet: Learning robust visual representation for vehicle re-identification. IEEE Trans. Multimed., 1\u20131 (2020). https:\/\/doi.org\/10.1109\/TMM.2020.3014488.","DOI":"10.1109\/TMM.2020.3014488"},{"key":"767_CR18","unstructured":"G. Hinton, O. Vinyals, J. Dean, in Advances in Neural Information Processing Systems Workshops. Distilling the knowledge in a neural network, (2015)."},{"key":"767_CR19","unstructured":"A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, Y. Bengio, in International Conference on Learning Representations. Fitnets: Hints for thin deep nets, (2015). https:\/\/iclr.cc\/archive\/www\/doku.php%3Fid=iclr2015:accepted-main.html."},{"key":"767_CR20","doi-asserted-by":"crossref","unstructured":"J. Yim, D. Joo, J. Bae, J. Kim, in IEEE Conference on Computer Vision and Pattern Recognition. A gift from knowledge distillation: Fast optimization, network minimization and transfer learning, (2017), pp. 4133\u20134141.","DOI":"10.1109\/CVPR.2017.754"},{"key":"767_CR21","doi-asserted-by":"publisher","first-page":"5698","DOI":"10.1109\/TIP.2020.2984362","volume":"29","author":"J. -H. Bae","year":"2020","unstructured":"J. -H. Bae, D. Yeo, J. Yim, N. -S. Kim, C. -S. Pyo, J. Kim, Densely distilled flow-based knowledge transfer in teacher-student framework for image classification. IEEE Trans. Image Process.29:, 5698\u20135710 (2020). https:\/\/doi.org\/10.1109\/TIP.2020.2984362.","journal-title":"IEEE Trans. Image Process."},{"key":"767_CR22","doi-asserted-by":"crossref","unstructured":"L. Zhang, J. Song, A. Gao, J. Chen, C. Bao, K. Ma, in 2019 IEEE\/CVF International Conference on Computer Vision. Be your own teacher: Improve the performance of convolutional neural networks via self distillation, (2019), pp. 3712\u20133721.","DOI":"10.1109\/ICCV.2019.00381"},{"key":"767_CR23","doi-asserted-by":"publisher","unstructured":"S. You, C. Xu, C. Xu, D. Tao, in ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Learning from multiple teacher networks, (2017), pp. 1285\u20131294. https:\/\/doi.org\/10.1145\/3097983.3098135.","DOI":"10.1145\/3097983.3098135"},{"key":"767_CR24","doi-asserted-by":"crossref","unstructured":"A. Wu, W. Zheng, X. Guo, J. Lai, in IEEE Conference on Computer Vision and Pattern Recognition. Distilled person re-identification: Towards a more scalable system, (2019), pp. 1187\u20131196.","DOI":"10.1109\/CVPR.2019.00128"},{"key":"767_CR25","doi-asserted-by":"crossref","unstructured":"J. H. Cho, B. Hariharan, in IEEE International Conference on Computer Vision. On the efficacy of knowledge distillation, (2019), pp. 4794\u20134802.","DOI":"10.1109\/ICCV.2019.00489"},{"key":"767_CR26","doi-asserted-by":"publisher","unstructured":"L. Wang, K. -J. Yoon, Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell., 1\u20131 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3055564.","DOI":"10.1109\/TPAMI.2021.3055564"},{"issue":"10","key":"767_CR27","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1109\/TMM.2019.2958756","volume":"22","author":"H. Luo","year":"2020","unstructured":"H. Luo, W. Jiang, Y. Gu, F. Liu, X. Liao, S. Lai, J. Gu, A strong baseline and batch normalization neck for deep person re-identification. IEEE Trans. Multimed.22(10), 2597\u20132609 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2958756.","journal-title":"IEEE Trans. Multimed."},{"key":"767_CR28","doi-asserted-by":"crossref","unstructured":"Y. Sun, X. Wang, X. Tang, in IEEE Conference on Computer Vision and Pattern Recognition. Deep learning face representation from predicting 10,000 classes, (2014), pp. 1891\u20131898.","DOI":"10.1109\/CVPR.2014.244"},{"key":"767_CR29","unstructured":"S. Ioffe, C. Szegedy, in International Conference on Machine Learning. Batch normalization: Accelerating deep network training by reducing internal covariate shift, (2015), pp. 448\u2013456."},{"key":"767_CR30","unstructured":"V. Nair, G. E. Hinton, in International Conference on Machine Learning. Rectified linear units improve restricted boltzmann machines, (2010), pp. 807\u2013814."},{"key":"767_CR31","doi-asserted-by":"crossref","unstructured":"L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, in IEEE International Conference on Computer Vision. Scalable person re-identification: A benchmark, (2015), pp. 1116\u20131124.","DOI":"10.1109\/ICCV.2015.133"},{"issue":"3","key":"767_CR32","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1109\/JIOT.2019.2960549","volume":"7","author":"J. Zhu","year":"2020","unstructured":"J. Zhu, H. Zeng, J. Huang, X. Zhu, Z. Lei, C. Cai, L. Zheng, Body symmetry and part locality guided direct nonparametric deep feature enhancement for person re-identification. IEEE Internet Things J.7(3), 2053\u20132065 (2020).","journal-title":"IEEE Internet Things J."},{"issue":"11","key":"767_CR33","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1109\/TCSVT.2017.2734740","volume":"28","author":"J. Zhu","year":"2018","unstructured":"J. Zhu, H. Zeng, S. Liao, Z. Lei, C. Cai, L. Zheng, Deep hybrid similarity learning for person re-identification. IEEE Trans. Circ. Syst. Video Technol.28(11), 3183\u20133193 (2018).","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"767_CR34","unstructured":"A. Krizhevsky, I. Sutskever, G. E. Hinton, in Advances in Neural Information Processing Systems. Imagenet classification with deep convolutional neural networks, (2012), pp. 1097\u20131105."},{"key":"767_CR35","doi-asserted-by":"crossref","unstructured":"Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34. Random erasing data augmentation, (2020), pp. 13001\u201313008.","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"767_CR36","doi-asserted-by":"crossref","unstructured":"C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, in IEEE Conference on Computer Vision and Pattern Recognition. Rethinking the inception architecture for computer vision, (2016).","DOI":"10.1109\/CVPR.2016.308"},{"key":"767_CR37","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, in Advances in Neural Information Processing Systems. Pytorch: An imperative style, high-performance deep learning library, (2019), pp. 8024\u20138035."},{"key":"767_CR38","doi-asserted-by":"crossref","unstructured":"F. Schroff, D. Kalenichenko, J. Philbin, in IEEE Conference on Computer Vision and Pattern Recognition. Facenet: A unified embedding for face recognition and clustering, (2015), pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"767_CR39","first-page":"2579","volume":"9","author":"L. Maaten","year":"2008","unstructured":"L. Maaten, G. Hinton, Visualizing data using t-SNE. J. Mach. Learn. Res.9:, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-021-00767-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-021-00767-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-021-00767-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T17:07:47Z","timestamp":1627319267000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-021-00767-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,26]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["767"],"URL":"https:\/\/doi.org\/10.1186\/s13634-021-00767-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-104548\/v1","asserted-by":"object"}]},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,26]]},"assertion":[{"value":"5 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}