2,997 Hits in 5.5 sec

Sparse representation matching for person re-identification

Le An, Xiaojing Chen, Songfan Yang, Bir Bhanu
2016 Information Sciences  
Experimental results with extensive comparisons on challenging datasets demonstrate that the proposed method outperforms the state-of-the-art methods and using 2 regularized sparse representation ( 1 +  ...  The results of person re-9 identification can be readily used in further processing tasks such as tracklet 10 association for multi-camera people tracking [7] .  ...  The generated 246 sparse representations are used for person re-identification.  ... 
doi:10.1016/j.ins.2016.02.055 fatcat:nfo4z35r4neypctfekq7kpubhy

Locality-Constrained Collaborative Sparse Approximation for Multiple-Shot Person Re-identification

Yang Wu, Masayuki Mukunoki, Michihiko Minoh
2013 2013 2nd IAPR Asian Conference on Pattern Recognition  
Person re-identification is becoming a hot research topic due to its academic importance and attractive applications in visual surveillance.  ...  This paper focuses on solving the relatively harder and more importance multiple-shot re-identification problem.  ...  Metric learning algorithms were mainly used for single-shot re-identification.  ... 
doi:10.1109/acpr.2013.14 dblp:conf/acpr/WuMM13 fatcat:65hb754rvrb4lkoyluzrw72tty

Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics [article]

Xiyang Dai, Sameh Khamis, Yangmuzi Zhang, Larry S. Davis
2016 arXiv   pre-print
Sparse representations have been successfully applied to signal processing, computer vision and machine learning.  ...  Our new representation has multiple advantages. Experiments on several vision tasks demonstrate competitive performance with the state-of-the-art methods.  ...  They exhibit large viewpoint variations among pedestrian pairs, which makes it one of the most challenging datasets in person re-identification.  ... 
arXiv:1602.02822v1 fatcat:iq5rri56fzfrrnsypaftppfndq

Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices [article]

Ming Yin, Shengli Xie, Yi Guo, Junbin Gao, Yun Zhang
2016 arXiv   pre-print
Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years.  ...  As such, there is still no satisfactory approach to conduct classification task for symmetric positive definite (SPD) matrices which is very useful in computer vision.  ...  Pedestrian Re-identification Finally, we conduct the person re-identification task by our proposed method and compare with other methods.  ... 
arXiv:1601.07336v1 fatcat:56bbzilfwjdx7gbdfhybc364ye

Machine learning for big visual analysis

Jun Yu, Xue Mei, Fatih Porikli, Jason Corso
2018 Machine Vision and Applications  
analytical least squares metric learning has shown its excellent performance in person re-identification; and sparse representation has been efficiently used in face recognition.  ...  The article entitled "Two-stream Person Re-identification with Multi-task Deep Neural Networks" proposed a twostream strategy to use parts and bodies simultaneously.  ... 
doi:10.1007/s00138-018-0948-5 fatcat:puwirktcpjg5bdfc4wxvuw77ua

Riemannian Sparse Coding for Positive Definite Matrices [chapter]

Anoop Cherian, Suvrit Sra
2014 Lecture Notes in Computer Science  
In contrast, we propose to use the intrinsic Riemannian distance on the manifold of SPD matrices.  ...  Prior works have approached this problem by defining a sparse coding loss function using either extrinsic similarity measures (such as the log-Euclidean distance) or kernelized variants of statistical  ...  ETHZ Person Re-identification Dataset: Recognition and tracking of people are essential components of a visual surveillance system.  ... 
doi:10.1007/978-3-319-10578-9_20 fatcat:zl6u7b66tzgb5kwuprfah6ucpi

Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces [chapter]

Qiang Qiu, Jie Ni, Rama Chellappa
2014 Person Re-Identification  
Re-identification refers to the problem of recognizing a person at a different location after one has been captured by a camera at a previous location.  ...  We discuss re-identification of faces using the domain adaptation approach which tackles the problem where data in the target domain (different location) are drawn from a different distribution as the  ...  The domain invariant sparse representations are used here as shared feature representation for cross domain face re-identification.  ... 
doi:10.1007/978-1-4471-6296-4_13 dblp:series/acvpr/QiuNC14 fatcat:w5ggcnr4kzglzfgpip37iamjsq

PCCA: A new approach for distance learning from sparse pairwise constraints

A. Mignon, F. Jurie
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
PCCA is experimentally validated on two challenging vision tasks, face verification and person re-identification, for which we obtain state-of-the-art results.  ...  This paper introduces Pairwise Constrained Component Analysis (PCCA), a new algorithm for learning distance metrics from sparse pairwise similarity/dissimilarity constraints in high dimensional input space  ...  Our experiments on person re-identification use the Viewpoint Invariant Pedestrian Recognition (VIPeR) database [12] .  ... 
doi:10.1109/cvpr.2012.6247987 dblp:conf/cvpr/MignonJ12 fatcat:bpqn3a6635dztfrcydf4noyyde

Continuous adaptation of multi-camera person identification models through sparse non-redundant representative selection

Abir Das, Rameswar Panda, Amit K. Roy-Chowdhury
2017 Computer Vision and Image Understanding  
We demonstrate the effectiveness of our approach on multi-camera person re-identification datasets, to demonstrate the feasibility of learning online classification models in multi-camera big data applications  ...  Das et al., Continuous adaptation of multi-camera person identification models through sparse nonredundant representative selection, Computer Vision and Image Understanding (2016), http://dx.  ...  Person re-identification: Our approach being online and adaptive is different from traditional re-identification setting as unlike traditional re-identification scenario, the proposed approach starts with  ... 
doi:10.1016/j.cviu.2016.10.012 fatcat:eezqe3ealjbx3fati3n7z4dpxy

Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection [article]

Abir Das, Rameswar Panda, Amit K. Roy-Chowdhury
2016 arXiv   pre-print
We demonstrate the effectiveness of our approach on multi-camera person re-identification datasets, to demonstrate the feasibility of learning online classification models in multi-camera big data applications  ...  We also use a structure preserving sparse reconstruction based classifier to reduce the training burden typically seen in discriminative classifiers.  ...  Person Re-identification: Our approach being online and adaptive is different from traditional re-identification setting as unlike traditional re-identification scenario, the proposed approach starts with  ... 
arXiv:1607.00417v1 fatcat:td2oduptdvbx3jnqgdarhq7aoe

Learning Invariant Color Features for Person Re-Identification [article]

Rahul Rama Varior, Gang Wang, Jiwen Lu
2014 arXiv   pre-print
Matching people across multiple camera views known as person re-identification, is a challenging problem due to the change in visual appearance caused by varying lighting conditions.  ...  Combining with other learned low-level and high-level features, we obtain promising results in ViPER, Person Re-ID 2011 and CAVIAR4REID datasets.  ...  Person Re-Identification Person re-identification research has received a good amount of attention in recent years.  ... 
arXiv:1410.1035v2 fatcat:yyypnvzo5bez5ky224xwl4eoom

Multimodal inference of articulated spine models from higher order energy functions of discrete MRFS

Samuel Kadoury, Nikos Paragios
2010 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
A personalized geometrical model is reconstructed from biplanar X-rays before spinal surgery in order to create a spinal column representation which is modeled by a series of intervertebral transformations  ...  Optimization of model parameters in a multi-modal context is achieved using efficient linear programming and duality.  ...  We use a personalized 3D spine reconstructed from biplanar X-rays to derive an articulated model represented with intervertebral transformations.  ... 
doi:10.1109/isbi.2010.5490258 dblp:conf/isbi/KadouryP10 fatcat:higtbfn3unavpl5a4bje3cf6ka

Random projections on manifolds of Symmetric Positive Definite matrices for image classification

Azadeh Alavi, Arnold Wiliem, Kun Zhao, Brian C. Lovell, Conrad Sanderson
2014 IEEE Winter Conference on Applications of Computer Vision  
Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome  ...  In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved  ...  For the person re-identification task we used the modified version [29] of the ETHZ dataset [9] .  ... 
doi:10.1109/wacv.2014.6836085 dblp:conf/wacv/AlaviWZLS14 fatcat:wo2jrq4yqzhfjngyvyu3w2fvy4

3D Skeletal Gesture Recognition via Sparse Coding of Time-Warping Invariant Riemannian Trajectories [chapter]

Xin Liu, Guoying Zhao
2018 Msphere  
Furthermore, we present a sparse coding of skeletal trajectories by explicitly considering the labeling information with each atoms to enforce the discriminant validity of dictionary.  ...  Then, a gesture skeletal sequence can be characterized by a trajectory on a Riemannian manifold.  ...  ., x N ] ∈ R K×N represents the sparse codes of observation Y, and T is a sparsity constraint factor.  ... 
doi:10.1007/978-3-030-05710-7_56 fatcat:baw2x7qyjnhwtgdejz73ddnoky

An information theoretic formulation of the Dictionary Learning and Sparse Coding Problems on Statistical Manifolds [article]

Rudrasis Chakraborty, Monami Banerjee, Victoria Crawford, Baba C. Vemuri
2017 arXiv   pre-print
In this work, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions).  ...  We therefore employ the geodesic distance between the data and a sparse approximation of the data element. This cost function is minimized using an acceleterated gradient descent algorithm.  ...  We used 40 dictionary atoms for this data. ETHZ person re-identification data: This dataset contains surveillance images of 122 subjects. We consider 10 images of each subject.  ... 
arXiv:1604.06939v2 fatcat:l6vhov2kbzainmx3o2cd7ekyf4
« Previous Showing results 1 — 15 out of 2,997 results