Towards Open-World Person Re-Identification by One-Shot Group-Based Verification

Solving the problem of matching people across non-overlapping multi-camera views, known as person re-identification (re-id), has received increasing interests in computer vision. In a real-world application scenario, a watch-list (gallery set) of a handful of known target people are provided with very few (in many cases only a single) image(s) (shots) per target. Existing re-id methods are largely unsuitable to address this open-world re-id challenge because they are designed for (1) a closed-world scenario where the gallery and probe sets are assumed to contain exactly the same people, (2) person-wise identification whereby the model attempts to verify exhaustively against each individual in the gallery set, and (3) learning a matching model using multi-shots. In this paper, a novel transfer local relative distance comparison (t-LRDC) model is formulated to address the open-world person re-identification problem by one-shot group-based verification. The model is designed to mine and transfer useful information from a labelled open-world non-target dataset. Extensive experiments demonstrate that the proposed approach outperforms both non-transfer learning and existing transfer learning based re-id methods.

[1]  Luc Van Gool,et al.  Depth and Appearance for Mobile Scene Analysis , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[2]  Léon Bottou,et al.  The Tradeoffs of Large Scale Learning , 2007, NIPS.

[3]  Xiaogang Wang,et al.  Human Reidentification with Transferred Metric Learning , 2012, ACCV.

[4]  Horst Bischof,et al.  Large scale metric learning from equivalence constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[6]  Qiang Yang,et al.  Transfer Learning via Dimensionality Reduction , 2008, AAAI.

[7]  Shaogang Gong,et al.  Transfer re-identification: From person to set-based verification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Hai Tao,et al.  Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features , 2008, ECCV.

[9]  Ivor W. Tsang,et al.  Domain Transfer SVM for video concept detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Zhen Li,et al.  Learning Locally-Adaptive Decision Functions for Person Verification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Zhuowen Tu,et al.  Feature Mining for Image Classification , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Chunxiao Liu,et al.  Person re-identification by manifold ranking , 2013, 2013 IEEE International Conference on Image Processing.

[13]  Shaogang Gong,et al.  Person Re-Identification by Support Vector Ranking , 2010, BMVC.

[14]  Bo Geng,et al.  DAML: Domain Adaptation Metric Learning , 2011, IEEE Transactions on Image Processing.

[15]  Geoffrey E. Hinton,et al.  Neighbourhood Components Analysis , 2004, NIPS.

[16]  Tong Zhang,et al.  A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , 2005, J. Mach. Learn. Res..

[17]  Shimon Ullman,et al.  Cross-generalization: learning novel classes from a single example by feature replacement , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Horst Bischof,et al.  Relaxed Pairwise Learned Metric for Person Re-identification , 2012, ECCV.

[19]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Vittorio Murino,et al.  Custom Pictorial Structures for Re-identification , 2011, BMVC.

[21]  Xuelong Li,et al.  Person Re-Identification by Regularized Smoothing KISS Metric Learning , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Larry S. Davis,et al.  Learning Discriminative Appearance-Based Models Using Partial Least Squares , 2009, 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing.

[23]  Ehud Rivlin,et al.  Color Invariants for Person Reidentification , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Anil K. Jain,et al.  ViSE: Visual Search Engine Using Multiple Networked Cameras , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  Xiaogang Wang,et al.  A unified framework for subspace face recognition , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

[27]  Yi Liu,et al.  An Efficient Algorithm for Local Distance Metric Learning , 2006, AAAI.

[28]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[29]  Shaogang Gong,et al.  Associating Groups of People , 2009, BMVC.

[30]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[31]  Masayuki Mukunoki,et al.  Can feature-based inductive transfer learning help person re-identification? , 2013, 2013 IEEE International Conference on Image Processing.

[32]  Barbara Caputo,et al.  The More You Know, the Less You Learn: From Knowledge Transfer to One-shot Learning of Object Categories , 2009, BMVC.

[33]  Dit-Yan Yeung,et al.  A Convex Formulation for Learning Task Relationships in Multi-Task Learning , 2010, UAI.

[34]  Tieniu Tan,et al.  Principal axis-based correspondence between multiple cameras for people tracking , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Bingpeng Ma,et al.  Local Descriptors Encoded by Fisher Vectors for Person Re-identification , 2012, ECCV Workshops.

[36]  Shaogang Gong,et al.  Domain transfer for person re-identification , 2013, ARTEMIS '13.

[37]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Joshua B. Tenenbaum,et al.  One-Shot Learning with a Hierarchical Nonparametric Bayesian Model , 2011, ICML Unsupervised and Transfer Learning.

[39]  Sergio A. Velastin,et al.  Local Fisher Discriminant Analysis for Pedestrian Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  Alessandro Perina,et al.  Person re-identification by symmetry-driven accumulation of local features , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[41]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[42]  Shaogang Gong,et al.  Person re-identification by probabilistic relative distance comparison , 2011, CVPR 2011.

[43]  Xiaogang Wang,et al.  Unsupervised Salience Learning for Person Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[44]  Shaogang Gong,et al.  The Re-identification Challenge , 2014, Person Re-Identification.

[45]  Richard I. Hartley,et al.  Person Reidentification Using Spatiotemporal Appearance , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[46]  Kilian Q. Weinberger,et al.  Large Margin Multi-Task Metric Learning , 2010, NIPS.

[47]  Shaogang Gong,et al.  Reidentification by Relative Distance Comparison , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Xiaogang Wang,et al.  Shape and Appearance Context Modeling , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[49]  Shaogang Gong,et al.  Multi-camera Matching using Bi-Directional Cumulative Brightness Transfer Functions , 2008, BMVC.