Person reidentification via discrepancy matrix and matrix metric
Person reidentification (re-id), as an important task in video surveillance and forensics
applications, has been widely studied. Previous research efforts toward solving the person …
applications, has been widely studied. Previous research efforts toward solving the person …
Robust distance metric learning via Bayesian inference
D Wang, X Tan - IEEE Transactions on Image Processing, 2017 - ieeexplore.ieee.org
Distance metric learning (DML) has achieved great success in many computer vision tasks.
However, most existing DML algorithms are based on point estimation, and thus are …
However, most existing DML algorithms are based on point estimation, and thus are …
Orthogonality-promoting distance metric learning: convex relaxation and theoretical analysis
Distance metric learning (DML), which learns a distance metric from labeled" similar" and"
dissimilar" data pairs, is widely utilized. Recently, several works investigate orthogonality …
dissimilar" data pairs, is widely utilized. Recently, several works investigate orthogonality …
Cross-modality person re-identification based on intermediate modal generation
J Lu, S Zhang, M Chen, X Chen, K Zhang - Optics and Lasers in …, 2024 - Elsevier
In the context of cross-modal person re-identification, researchers often employ methods that
utilize visible modality information to generate both an 'X'modality and a grayscale modality …
utilize visible modality information to generate both an 'X'modality and a grayscale modality …
A new patch selection method based on parsing and saliency detection for person re-identification
Person re-identification is an important technique towards automatic recognition of a person
across non-overlapping cameras. In this paper, a novel patch selection method based on …
across non-overlapping cameras. In this paper, a novel patch selection method based on …
[PDF][PDF] 基于双向参考集矩阵度量学习的行人再识别
陈莹, 许潇月 - 电子与信息学报, 2020 - jeit.ac.cn
针对行人再识别中由于外观差异不显著导致特征描述不准确的问题, 该文提出一种基于双向参考
集矩阵度量学习(BRM2L) 的行人再识别算法. 首先通过互近邻算法获得每个摄像头下的互近邻 …
集矩阵度量学习(BRM2L) 的行人再识别算法. 首先通过互近邻算法获得每个摄像头下的互近邻 …
Matrix metric learning for person re-identification based on bidirectional reference set
Y CHEN, X XU - 电子与信息学报, 2020 - jeit.ac.cn
To solve the problem of inaccurate feature representation caused by indistinctive
appearance difference in person re-identification domain, a new Matrix Metric Learning …
appearance difference in person re-identification domain, a new Matrix Metric Learning …
基于辨识特征后融合的行人再识别.
刘琦, 侯丽, 彭章友 - Application Research of Computers …, 2019 - search.ebscohost.com
跨摄像机行人因光照, 视角, 姿态的差异, 会使其外观变化显著, 给行人再识别的研究带来严峻
挑战. 基于多特征融合和距离度量学习技术, 提出辨识特征后融合的算法, 并将其应用于行人再 …
挑战. 基于多特征融合和距离度量学习技术, 提出辨识特征后融合的算法, 并将其应用于行人再 …
Integrated metric learning with adaptive constraints for person re-identification
L Hao, W Yao, C Pei, Y Zhu - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
Person re-identification is an important technique to search a probe person against a set of
gallery persons and metric learning methods have shown their effectiveness in matching …
gallery persons and metric learning methods have shown their effectiveness in matching …