On-the-fly feature importance mining for person re-identification

State-of-the-art person re-identification methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with generic weights, which are assumed to be universally and equally good for all individuals, independent of people's different appearances. In this study, we show that certain features play more important role than others under different viewing conditions. To explore this characteristic, we propose a novel unsupervised approach to bottom-up feature importance mining on-the-fly specific to each re-identification probe target image, so features extracted from different individuals are weighted adaptively driven by their salient and inherent appearance attributes. Extensive experiments on three public datasets give insights on how feature importance can vary depending on both the viewing condition and specific person's appearance, and demonstrate that unsupervised bottom-up feature importance mining specific to each probe image can facilitate more accurate re-identification especially when it is combined with generic universal weights obtained using existing distance metric learning methods.

[1]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.

[2]  Masayuki Mukunoki,et al.  Set Based Discriminative Ranking for Recognition , 2012, ECCV.

[3]  Shaogang Gong,et al.  Spectral clustering with eigenvector selection , 2008, Pattern Recognit..

[4]  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.

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

[6]  Brendan J. Frey,et al.  Stel component analysis: Modeling spatial correlations in image class structure , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Philip S. Yu,et al.  Clustering through decision tree construction , 2000, CIKM '00.

[8]  Alessandro Perina,et al.  Multiple-shot person re-identification by chromatic and epitomic analyses , 2012, Pattern Recognit. Lett..

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

[10]  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.

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

[12]  Pierre Vandergheynst,et al.  Cascade of descriptors to detect and track objects across any network of cameras , 2010, Comput. Vis. Image Underst..

[13]  Shaogang Gong,et al.  Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding , 2010, International Journal of Computer Vision.

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

[15]  Matej Kristan,et al.  Non-sequential Multi-view Detection, Localization and Identification of People Using Multi-modal Feature Maps , 2012, ACCV.

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

[17]  Slawomir Bak,et al.  Person Re-identification Using Haar-based and DCD-based Signature , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[18]  Fuchun Sun,et al.  Person re-identification based on visual saliency , 2012, 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA).

[19]  Pascal Fua,et al.  Tracking multiple people under global appearance constraints , 2011, 2011 International Conference on Computer Vision.

[20]  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.

[21]  Slawomir Bak,et al.  Person Re-identification Using Spatial Covariance Regions of Human Body Parts , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[22]  Chunxiao Liu,et al.  Person Re-identification: What Features Are Important? , 2012, ECCV Workshops.

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

[24]  Slawomir Bak,et al.  Multiple-shot human re-identification by Mean Riemannian Covariance Grid , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

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

[26]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

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

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  Shaogang Gong,et al.  Person Re-identification by Attributes , 2012, BMVC.

[30]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

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