Person Re-Identification by Regularized Smoothing KISS Metric Learning

Tao, Dapeng; Jin, Lianwen; Wang, Yongfei; Yuan, Yuan; Li, Xuelong

doi:10.1109/tcsvt.2013.2255413

Cited by 158 publications

(86 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng et al [23] learned a Mahalanobis distance metric with a probabilistic relative distance comparison method. Kostinger et al [24] introduced a simpler metric function (KISSME) to fit pairwise samples based on Gaussian distribution hypothesis, and Tao et al [25] got better estimation of the covariance matrices of KISS metric learning by seamlessly integrating smoothing and regularization. Mignon et al [26] learn distance metric from sparse pairwise similarity/dissimilarity constraints in high dimensional space called pairwise constrained component analysis.…”

Section: Related Workmentioning

confidence: 99%

“…(ii) Subspace and metric learning aims at seeking a proper subspace or distance measure by Mahalanobis-like metric learning [21][22][23][24][25][26][27][28][29][30]. Given a set of person image pairs, metric learning based methods are to learn an optimal positive semidefinite matrix for the validity of metric that maximizes the probability of true matches pair having smaller distance than wrong match pairs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Co-Metric Learning for Person Re-Identification

Leng

2018

Advances in Multimedia

View full text Add to dashboard Cite

Person re-identification, aiming to identify the same pedestrian images across disjoint camera views, is a key technique of intelligent video surveillance. Although existing methods have developed both theories and experimental results, most of effective ones pertain to fully supervised training styles, which suffer the small sample size (SSS) problem a lot, especially in label-insufficient practical applications. To bridge SSS problem and learning model with small labels, a novel semisupervised co-metric learning framework is proposed to learn a discriminative Mahalanobis-like distance matrix for label-insufficient person re-identification. Different from typical co-training task that contains multiview data originally, single-view person images are firstly decomposed into pseudo two views, and then metric learning models are produced and jointly updated based on both pseudo-labels and references iteratively. Experiments carried out on three representative person re-identification datasets show that the proposed method performs better than state of the art and possesses low label sensitivity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Co-Metric Learning for Person Re-Identification

Leng

2018

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…According to the Re-ID taxonomy summarized by Vezzani et al [1], local features and pedestrian body model-based features are very common because they capture detailed and localized information for matching. Among local features, it is very popular to use combination features of color and texture histograms, for example, color histograms (from HSV color space) and scale invariant local ternary pattern (SILTP) histograms [5], color histograms (from RGB, YUV, and HSV color spaces) and local binary pattern (LBP) histograms [6,7], color histograms (from RGB and HSV color spaces) and LBP histograms [8], color histograms (from RGB, YCbCr, and HS color spaces) and texture histograms of Gabor filters and Schmid filters [9], and color histograms (from HSV and Lab color spaces) and LBP histograms [10,11]. The implementation details of these color and texture histograms might be different.…”

Section: Related Workmentioning

confidence: 99%

“…Köstinger et al [15] presented KISS classification metric learned from equivalence constraints based on statistical inference rather than computational complex optimization. However, this classification metric learning could be unstable under a small-sized training set, mentioned in [10]. Thus, Tao et al [10] integrated smoothing and regularization techniques in KISS for robust estimation of covariance matrices and stable performance and proposed regularized smoothing KISS.…”

Section: Related Workmentioning

confidence: 99%

“…However, this classification metric learning could be unstable under a small-sized training set, mentioned in [10]. Thus, Tao et al [10] integrated smoothing and regularization techniques in KISS for robust estimation of covariance matrices and stable performance and proposed regularized smoothing KISS. Pedagadi et al [16] used local Fisher discriminant analysis (LFDA) to learn similarity classification metric from a set of labeled feature pairs, which consisted of features extracted from high-dimensional features by unsupervised PCA.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Color Distribution Pattern Metric for Person Reidentification

Zhang

2017

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Accompanying the growth of surveillance infrastructures, surveillance IP cameras mount up rapidly, crowding Internet of Things (IoT) with countless surveillance frames and increasing the need of person reidentification (Re-ID) in video searching for surveillance and forensic fields. In real scenarios, performance of current proposed Re-ID methods suffers from pose and viewpoint variations due to feature extraction containing background pixels and fixed feature selection strategy for pose and viewpoint variations. To deal with pose and viewpoint variations, we propose the color distribution pattern metric ( ) method, employing color distribution pattern ( ) for feature representation and SVM for classification. Different from other methods, does not extract features over a certain number of dense blocks and is free from varied pedestrian image resolutions and resizing distortion. Moreover, it provides more precise features with less background influences under different body types, severe pose variations, and viewpoint variations. Experimental results show that our method achieves state-of-the-art performance on both 3DPeS dataset and ImageLab Pedestrian Recognition dataset with 68.8% and 79.8% rank 1 accuracy, respectively, under the single-shot experimental setting.

show abstract

Domain adaptation metric learning method embedded with structural information for person re‐identification in internet of autonomous unmanned vehicles

Qian

2022

Softw Pract Exp

View full text Add to dashboard Cite

Internet of autonomous unmanned vehicles (IAUV) is a global network of sensors, robots, and autonomous vehicles. Person re‐identification (Re‐ID) is an important intelligent transportation application in IAUV, which needs to be solved using artificial intelligence algorithms. In this study, a domain adaptation metric learning method embedded with structural information (called DAML‐ESI) is designed for person Re‐ID in IAUV. Due to the lack of labeling information in the target domain, DAML‐ESI realizes person Re‐ID with the help of the discriminative and structural information of pedestrian images of related domains. DAML‐ESI projects pedestrian images selected from different domains into a common metric space and establishes a discriminative metric learning model, which requires that the positive sample pair be mapped to a point, and the distance distribution of the negative sample pair be mapped to a fixed value. The projection matrix learned by DAML‐ESI is used to eliminate the distribution differences between different domains, and the distance metric is used to ensure that the learned metric learning model has strong discriminative ability in the metric space. To verify the effectiveness of DAML‐ESI, experimental comparisons are conducted on three person Re‐ID datasets, and DAML‐ESI achieves satisfactory recognition performance.

show abstract

Person Re-Identification by Regularized Smoothing KISS Metric Learning

Cited by 158 publications

References 55 publications

Co-Metric Learning for Person Re-Identification

Co-Metric Learning for Person Re-Identification

Color Distribution Pattern Metric for Person Reidentification

Domain adaptation metric learning method embedded with structural information for person re‐identification in internet of autonomous unmanned vehicles

Contact Info

Product

Resources

About