In this paper, to exploit more discriminative information of the global-body and body-parts features, we present a novel deep multi-metric learning (DMML) network for person re-identification under the triplet framewo...
详细信息
In this paper, to exploit more discriminative information of the global-body and body-parts features, we present a novel deep multi-metric learning (DMML) network for person re-identification under the triplet framework. The main novelty of our learning framework lies in two aspects: 1) Unlike most existing metric learning-based approaches, which learn only one distance metric for comparison, our DMM-L method aims to learn different metrics for the global-body and body-parts features respectively by using convolutional neural network (CNN); 2) A new multi-metric loss function is proposed to train the DMML network, under which the distance of each negative pair is greater than that of each positive pair by a predefined margin, and the correlations of different metrics are maximized. Compared with the previous person re-identification methods that have shown state-of-the-art performances, our DMML approach can achieve competitive results on the challenging CUHK03, CUHKOl, VIPeR and iLIDS datasets.
Deep learning techniques have obtained much attention in image denoising. However, deep learning methods of different types deal with the noise have enormous differences. Specifically, discriminative learning based on...
详细信息
In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accuratel...
In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2, 1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.
Pattern matching(or string matching) is an essential task in computer science, especially in sequential pattern mining, since pattern matching methods can be used to calculate the support(or the number of occurrences)...
详细信息
Pattern matching(or string matching) is an essential task in computer science, especially in sequential pattern mining, since pattern matching methods can be used to calculate the support(or the number of occurrences) of a pattern and then to determine whether the pattern is frequent or not. A state-of-the-art sequential pattern mining with gap constraints(or flexible wildcards) uses the number of non-overlapping occurrences to denote the frequency of a pattern. Non-overlapping means that any two occurrences cannot use the same character of the sequence at the same position of the pattern. In this paper, we investigate strict pattern matching under the non-overlapping condition. We show that the problem is in P at first. Then we propose an algorithm, called NETLAP-Best, which uses Nettree structure. NETLAP-Best transforms the pattern matching problem into a Nettree and iterates to find the rightmost root-leaf path, to prune the useless nodes in the Nettree after removing the rightmost root-leaf path. We show that NETLAP-Best is a complete algorithm and analyse the time and space complexities of the algorithm. Extensive experimental results demonstrate the correctness and efficiency of NETLAP-Best.
Recently, the development of quantum chips has made great progress-the number of qubits is increasing and the fidelity is getting higher. However, qubits of these chips are not always fully connected, which sets addit...
详细信息
In 1996, President Clinton presented Peter Rose with the National Medal of Technology and Innovation. This paper describes his innovations in ion implantation technology which led to the award presented twenty years l...
详细信息
ISBN:
(纸本)9781538668306
In 1996, President Clinton presented Peter Rose with the National Medal of Technology and Innovation. This paper describes his innovations in ion implantation technology which led to the award presented twenty years later.
In a full-duplex (FD) multi-user network, the system performance is not only limited by the self-interference but also by the co-channel interference due to the simultaneous uplink and downlink transmissions. Joint de...
详细信息
The invasive red imported fire ant (Solenopsis invicta Buren) (Hymenoptera: Formicidae) has been continuing to expand its range in China, resulting in adverse ecological impacts to where it has invaded. As such, the r...
The invasive red imported fire ant (Solenopsis invicta Buren) (Hymenoptera: Formicidae) has been continuing to expand its range in China, resulting in adverse ecological impacts to where it has invaded. As such, the reliable detection of Solenopsis invicta Buren nests is needed to effectively manage the species. In this paper, the spectral features of the Solenopsis invicta Buren nests were demonstrated using spectra samples obtained by ASD FieldSpec 4 during field surveys in Shanggao County, Jiangxi Province. Furthermore, channel reflectance estimations for three unmanned aerial vehicle (UAV)-based multispectral sensors were simulated correspondingly. Based on the channel reflectance from individual sensors, the detection of the Solenopsis invicta Buren nests was investigated. Generally, between-class differences in reflectance were relatively significant in both Green channel and Red channel, which suggests the importance of these two channels for the detection of Solenopsis invicta Buren nest. Minor between-sensor differences observed in both Green channel and Red channel suggest that detection results obtained from UAV-based multispectral observations could be comparable among the three sensors, considering only the spectral features. There are significant differences in reflectance between the soil of Solenopsis invicta Buren nests and ordinary soil over the longwave region of near infrared (NIR). It suggests the spectral measurement over the longwave region of NIR could be more useful in distinguishing the soil of Solenopsis invicta Buren nests from ordinary soil. Nevertheless, the multispectral sensors provided with channels covering visible and the shortwave region of NIR, possibly do not meet requirements completely for application. An effective method for detecting Solenopsis invicta Buren nests using UAV-based multispectral sensors is currently being evaluated.
Sparse coding and supervised dictionary learning have rapidly developed in recent years,and achieved impressive performance in image classification. However, there is usually a limited number of labeled training sampl...
详细信息
Sparse coding and supervised dictionary learning have rapidly developed in recent years,and achieved impressive performance in image classification. However, there is usually a limited number of labeled training samples and a huge amount of unlabeled data in practical image classification,which degrades the discrimination of the learned dictionary. How to effectively utilize unlabeled training data and explore the information hidden in unlabeled data has drawn much attention of researchers. In this paper, we propose a novel discriminative semisupervised dictionary learning method using label propagation(SSD-LP). Specifically, we utilize a label propagation algorithm based on class-specific reconstruction errors to accurately estimate the identities of unlabeled training samples, and develop an algorithm for optimizing the discriminative dictionary and discriminative coding vectors *** experiments on face recognition, digit recognition, and texture classification demonstrate the effectiveness of the proposed method.
This paper introduces a kind of partial-order algorithm of model-checking in finite-control mobile ambients against μ-predicate ambient logic(Ambient logic based on first-order μ-calculus). Based on Tarski's fix...
详细信息
暂无评论