Appearance Modeling for Tracking in Multiple Non-Overlapping Cameras
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Person Reidentification Using Spatiotemporal Appearance
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Information-theoretic metric learning
Proceedings of the 24th international conference on Machine learning
Fast solvers and efficient implementations for distance metric learning
Proceedings of the 25th international conference on Machine learning
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Learning Pairwise Dissimilarity Profiles for Appearance Recognition in Visual Surveillance
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Distance metric learning vs. Fisher discriminant analysis
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Improving embeddings by flexible exploitation of side information
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Learning Discriminative Appearance-Based Models Using Partial Least Squares
SIBGRAPI '09 Proceedings of the 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing
Efficient algorithms for ranking with SVMs
Information Retrieval
Bridging the gaps between cameras
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Person Re-identification Using Haar-based and DCD-based Signature
AVSS '10 Proceedings of the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance
Pedestrian recognition with a learned metric
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part IV
Person re-identification by descriptive and discriminative classification
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
SARC3D: a new 3D body model for people tracking and re-identification
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
Person re-identification by probabilistic relative distance comparison
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Learning articulated body models for people re-identification
Proceedings of the 21st ACM international conference on Multimedia
Domain transfer for person re-identification
Proceedings of the 4th ACM/IEEE international workshop on Analysis and retrieval of tracked events and motion in imagery stream
People reidentification in surveillance and forensics: A survey
ACM Computing Surveys (CSUR)
On-the-fly feature importance mining for person re-identification
Pattern Recognition
Editor's Choice Article: A survey of approaches and trends in person re-identification
Image and Vision Computing
Features accumulation on a multiple view oriented model for people re-identification
3DOR '13 Proceedings of the Sixth Eurographics Workshop on 3D Object Retrieval
Hi-index | 0.00 |
Matching persons across non-overlapping cameras is a rather challenging task. Thus, successful methods often build on complex feature representations or sophisticated learners. A recent trend to tackle this problem is to use metric learning to find a suitable space for matching samples from different cameras. However, most of these approaches ignore the transition from one camera to the other. In this paper, we propose to learn a metric from pairs of samples from different cameras. In this way, even less sophisticated features describing color and texture information are sufficient for finally getting state-of-the-art classification results. Moreover, once the metric has been learned, only linear projections are necessary at search time, where a simple nearest neighbor classification is performed. The approach is demonstrated on three publicly available datasets of different complexity, where it can be seen that state-of-the-art results can be obtained at much lower computational costs.