iccv iccv2013 iccv2013-305 iccv2013-305-reference knowledge-graph by maker-knowledge-mining

305 iccv-2013-POP: Person Re-identification Post-rank Optimisation


Source: pdf

Author: Chunxiao Liu, Chen Change Loy, Shaogang Gong, Guijin Wang

Abstract: Owing to visual ambiguities and disparities, person reidentification methods inevitably produce suboptimal ranklist, which still requires exhaustive human eyeballing to identify the correct target from hundreds of different likelycandidates. Existing re-identification studies focus on improving the ranking performance, but rarely look into the critical problem of optimising the time-consuming and error-prone post-rank visual search at the user end. In this study, we present a novel one-shot Post-rank OPtimisation (POP) method, which allows a user to quickly refine their search by either “one-shot” or a couple of sparse negative selections during a re-identification process. We conduct systematic behavioural studies to understand user’s searching behaviour and show that the proposed method allows correct re-identification to converge 2.6 times faster than the conventional exhaustive search. Importantly, through extensive evaluations we demonstrate that the method is capable of achieving significant improvement over the stateof-the-art distance metric learning based ranking models, even with just “one shot” feedback optimisation, by as much as over 30% performance improvement for rank 1reidentification on the VIPeR and i-LIDS datasets.


reference text

[1] S. Ali, O. Javed, N. Haering, and T. Kanade. Interactive retrieval of targets for wide area surveillance. In ACM MM, 2010. 2

[2] M. B ¨auml, M. Fischer, K. Bernardin, H. K. Ekenel, and R. Stiefelhagen. Interactive person-retrieval in tv series and distributed surveillance video. In ACM MM, 2010. 2

[3] M. Belkin, P. Niyogi, and V. Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. JMLR, 7:2399–2434, 2006. 5

[4] L. Breiman. Random forests. ML, 45(1):5–32, 2001. 3, 4

[5] A. Criminisi, J. Shotton, and E. Konukoglu. Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision, 7(2-3):81–227, 2012. 4

[6] R. Fergus, H. Bernal, Y. Weiss, and A. Torralba. Semantic label sharing for learning with many categories. In ECCV, 2010. 4

[7] M. Fischer, H. K. Ekenel, and R. Stiefelhagen. Interactive person re-identification in tv series. In CBMI, 2010. 2

[8] A. Globerson and S. T. Roweis. Metric learning by collapsing classes. In NIPS, pages 451–458, 2005. 6, 7

[9] D. Gray and H. Tao. Viewpoint invariant pedestrain recognition with an ensemble of localized features. In ECCV, 2008. 5

[10] J. He, M. Li, Z. Li, H. Zhang, H. Tong, and C. Zhang. Pseudo relevance feedback based on iterative probabilistic one-class SVMs in web image retrieval. PCM, 2005. 2, 7

[11] J. He, M. Li, H. Zhang, H. Tong, and C. Zhang. Manifold-ranking based image retrieval. In ACM MM, 2004. 4

[12] M. Hirzer, C. Beleznai, P. Roth, and H. Bischof. Person reidentification by descriptive and discriminative classification. In SCIA, pages 91–102, 2011. 2

[13] M. Hirzer, P. Roth, M. K ¨ostinger, and H. Bischof. Relaxed pairwise learned metric for person re-identification. In ECCV, 2012. 1

[14] Y. Huang, Q. Liu, S. Zhang, and D. Metaxas. Image retrieval via probabilistic hypergraph ranking. In CVPR, 2010. 4

[15] C. Liu, S. Gong, C. C. Loy, and X. Lin. Person re-identification: What features are important ? In ECCV Workshop on Person Reidentification, 2012. 5

[16] C. C. Loy, C. Liu, and S. Gong. Person re-identification by manifold ranking. In ICIP, 2013. 1, 4, 5

[17] A. Mignon and F. Jurie. PCCA: A new approach for distance learning from sparse pairwise constraints. In CVPR, 2012. 1

[18] A. Parkash and D. Parikh. Attributes for classifier feedback. In ECCV, 2012. 2

[19] B. Prosser, W. Zheng, S. Gong, and T. Xiang. Person re-identification by support vector ranking. In BMVC, 2010. 1, 3, 5, 6, 7

[20] R. Salakhutdinov, A. Torralba, and J. Tenenbaum. Learning to share visual appearance for multiclass object detection. In CVPR, 2011. 4

[21] X. Tang, K. Liu, J. Cui, F. Wen, and X. Wang. Intentsearch: Capturing user intention for one-click internet image search. TPAMI,

[22]

[23]

[24]

[25]

[26]

[27]

[28] 34(7): 1342–1353, 2012. 2 U. Von Luxburg, M. Belkin, and O. Bousquet. Consistency of spectral clustering. The Annals of Statistics, pages 555–586, 2008. 5 B. Xu, J. Bu, C. Chen, D. Cai, X. He, W. Liu, and J. Luo. Efficient manifold ranking for image retrieval. In SIGIR, 2011. 4, 7 R. Yan, A. Hauptmann, and R. Jin. Negative pseudo-relevance feedback in content-based video retrieval. In ACM MM, 2003. 2, 7 R. Zhao, W. Ouyang, and X. Wang. Person re-identification by salience matching. In ICCV, 2013. 1 W. Zheng, S. Gong, and T. Xiang. Re-identification by relative distance comparison. TPAMI, 35(3):653–668, 2013. 1, 3, 5, 6, 7 X. Zhu, C. C. Loy, and S. Gong. Video synopsis by heterogeneous multi-source correlation. In ICCV, 2013. 4 H. Zitouni, S. Sevil, D. Ozkan, and P. Duygulu. Re-ranking of web image search results using a graph algorithm. In ICPR, 2008. 2 448