Book ChapterDOI
Relaxed pairwise learned metric for person re-identification
Martin Hirzer,Peter M. Roth,Martin Köstinger,Horst Bischof +3 more
- pp 780-793
TLDR
This paper proposes to learn a metric from pairs of samples from different cameras, so that even less sophisticated features describing color and texture information are sufficient for finally getting state-of-the-art classification results.Abstract:
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.read more
Citations
More filters
Proceedings ArticleDOI
Scalable Person Re-identification: A Benchmark
TL;DR: A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
Proceedings ArticleDOI
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
TL;DR: A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset.
Proceedings ArticleDOI
Person re-identification by Local Maximal Occurrence representation and metric learning
TL;DR: This paper proposes an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA), and presents a practical computation method for XQDA.
Proceedings ArticleDOI
Unsupervised Salience Learning for Person Re-identification
TL;DR: A novel perspective for person re-identification based on unsupervised salience learning, which applies adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations.
Posted Content
Person Re-identification: Past, Present and Future
TL;DR: The history of person re-identification and its relationship with image classification and instance retrieval is introduced and two new re-ID tasks which are much closer to real-world applications are described and discussed.
References
More filters
Proceedings ArticleDOI
Information-theoretic metric learning
TL;DR: An information-theoretic approach to learning a Mahalanobis distance function that can handle a wide variety of constraints and can optionally incorporate a prior on the distance function and derive regret bounds for the resulting algorithm.
Proceedings ArticleDOI
Person re-identification by symmetry-driven accumulation of local features
TL;DR: An appearance-based method for person re-identification that consists in the extraction of features that model three complementary aspects of the human appearance: the overall chromatic content, the spatial arrangement of colors into stable regions, and the presence of recurrent local motifs with high entropy.
Book ChapterDOI
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features
Douglas Gray,Hai Tao +1 more
TL;DR: It is shown how both an object class specific representation and a discriminative recognition model can be learned using the AdaBoost algorithm, which allows many different kinds of simple features to be combined into a single similarity function.
Evaluating Appearance Models for Recognition, Reacquisition, and Tracking
TL;DR: It is shown that appearance models for these three problems can be evaluated using a cumulative matching curve on a standardized dataset, and that this one curve can be converted to a synthetic reacquisition or disambiguation rate for tracking.
Related Papers (5)
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features
Douglas Gray,Hai Tao +1 more