Sharable and Individual Multi-View Metric Learning Hu, Junlin; Lu, Jiwen; Tan, Yap-Peng
IEEE transactions on pattern analysis and machine intelligence,
09/2018, Letnik:
40, Številka:
9
Journal Article
Recenzirano
This paper presents a sharable and individual multi-view metric learning (MvML) approach for visual recognition. Unlike conventional metric leaning methods which learn a distance metric on either a ...single type of feature representation or a concatenated representation of multiple types of features, the proposed MvML jointly learns an optimal combination of multiple distance metrics on multi-view representations, where not only it learns an individual distance metric for each view to retain its specific property but also a shared representation for different views in a unified latent subspace to preserve the common properties. The objective function of the MvML is formulated in the large margin learning framework via pairwise constraints, under which the distance of each similar pair is smaller than that of each dissimilar pair by a margin. Moreover, to exploit the nonlinear structure of data points, we extend MvML to a sharable and individual multi-view deep metric learning (MvDML) method by utilizing the neural network architecture to seek multiple nonlinear transformations. Experimental results on face verification, kinship verification, and person re-identification show the effectiveness of the proposed sharable and individual multi-view metric learning methods.
This paper presents a new discriminative deep metric learning (DDML) method for face and kinship verification in wild conditions. While metric learning has achieved reasonably good performance in ...face and kinship verification, most existing metric learning methods aim to learn a single Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, which cannot capture the nonlinear manifold where face images usually lie on. To address this, we propose a DDML method to train a deep neural network to learn a set of hierarchical nonlinear transformations to project face pairs into the same latent feature space, under which the distance of each positive pair is reduced and that of each negative pair is enlarged. To better use the commonality of multiple feature descriptors to make all the features more robust for face and kinship verification, we develop a discriminative deep multi-metric learning method to jointly learn multiple neural networks, under which the correlation of different features of each sample is maximized, and the distance of each positive pair is reduced and that of each negative pair is enlarged. Extensive experimental results show that our proposed methods achieve the acceptable results in both face and kinship verification.
Over the past three decades, a number of face recognition methods have been proposed in computer vision, and most of them use holistic face images for person identification. In many real-world ...scenarios especially some unconstrained environments, human faces might be occluded by other objects, and it is difficult to obtain fully holistic face images for recognition. To address this, we propose a new partial face recognition approach to recognize persons of interest from their partial faces. Given a pair of gallery image and probe face patch, we first detect keypoints and extract their local textural features. Then, we propose a robust point set matching method to discriminatively match these two extracted local feature sets, where both the textural information and geometrical information of local features are explicitly used for matching simultaneously. Finally, the similarity of two faces is converted as the distance between these two aligned feature sets. Experimental results on four public face data sets show the effectiveness of the proposed approach.
The unprecedented availability of social media data offers substantial opportunities for data owners, system operators, solution providers, and end users to explore and understand social dynamics. ...However, the exponential growth in the volume, velocity, and variability of social media data prevents people from fully utilizing such data. Visual analytics, which is an emerging research direction, has received considerable attention in recent years. Many visual analytics methods have been proposed across disciplines to understand large-scale structured and unstructured social media data. This objective, however, also poses significant challenges for researchers to obtain a comprehensive picture of the area, understand research challenges, and develop new techniques. In this paper, we present a comprehensive survey to characterize this fast-growing area and summarize the state-of-the-art techniques for analyzing social media data. In particular, we classify existing techniques into two categories: gathering information and understanding user behaviors. We aim to provide a clear overview of the research area through the established taxonomy. We then explore the design space and identify the research trends. Finally, we discuss challenges and open questions for future studies.
Deep Metric Learning for Visual Tracking Hu, Junlin; Lu, Jiwen; Tan, Yap-Peng
IEEE transactions on circuits and systems for video technology,
11/2016, Letnik:
26, Številka:
11
Journal Article
Recenzirano
In this paper, we propose a deep metric learning (DML) approach for robust visual tracking under the particle filter framework. Unlike most existing appearance-based visual trackers, which use ...hand-crafted similarity metrics, our DML tracker learns a nonlinear distance metric to classify the target object and background regions using a feed-forward neural network architecture. Since there are usually large variations in visual objects caused by varying deformations, illuminations, occlusions, motions, rotations, scales, and cluttered backgrounds, conventional linear similarity metrics cannot work well in such scenarios. To address this, our proposed DML tracker first learns a set of hierarchical nonlinear transformations in the feed-forward neural network to project both the template and particles into the same feature space where the intra-class variations of positive training pairs are minimized and the interclass variations of negative training pairs are maximized simultaneously. Then, the candidate that is most similar to the template in the learned deep network is identified as the true target. Experiments on the benchmark data set including 51 challenging videos show that our DML tracker achieves a very competitive performance with the state-of-the-art trackers.
In this paper, we propose a new deep coupled metric learning (DCML) method for cross-modal matching, which aims to match samples captured from two different modalities (e.g., texts versus images, ...visible versus near infrared images). Unlike existing cross-modal matching methods which learn a linear common space to reduce the modality gap, our DCML designs two feedforward neural networks which learn two sets of hierarchical nonlinear transformations (one set for each modality) to nonlinearly map samples from different modalities into a shared latent feature subspace, under which the intraclass variation is minimized and the interclass variation is maximized, and the difference of each data pair captured from two modalities of the same class is minimized, respectively. Experimental results on four different cross-modal matching datasets validate the efficacy of the proposed approach.
Conventional appearance-based face recognition methods usually assume that there are multiple samples per person (MSPP) available for discriminative feature extraction during the training phase. In ...many practical face recognition applications such as law enhancement, e-passport, and ID card identification, this assumption, however, may not hold as there is only a single sample per person (SSPP) enrolled or recorded in these systems. Many popular face recognition methods fail to work well in this scenario because there are not enough samples for discriminant learning. To address this problem, we propose in this paper a novel discriminative multimanifold analysis (DMMA) method by learning discriminative features from image patches. First, we partition each enrolled face image into several nonoverlapping patches to form an image set for each sample per person. Then, we formulate the SSPP face recognition as a manifold-manifold matching problem and learn multiple DMMA feature spaces to maximize the manifold margins of different persons. Finally, we present a reconstruction-based manifold-manifold distance to identify the unlabeled subjects. Experimental results on three widely used face databases are presented to demonstrate the efficacy of the proposed approach.
Deep Transfer Metric Learning Hu, Junlin; Lu, Jiwen; Tan, Yap-Peng ...
IEEE transactions on image processing,
12/2016, Letnik:
25, Številka:
12
Journal Article
Recenzirano
Odprti dostop
Conventional metric learning methods usually assume that the training and test samples are captured in similar scenarios so that their distributions are assumed to be the same. This assumption does ...not hold in many real visual recognition applications, especially when samples are captured across different data sets. In this paper, we propose a new deep transfer metric learning (DTML) method to learn a set of hierarchical nonlinear transformations for cross-domain visual recognition by transferring discriminative knowledge from the labeled source domain to the unlabeled target domain. Specifically, our DTML learns a deep metric network by maximizing the inter-class variations and minimizing the intra-class variations, and minimizing the distribution divergence between the source domain and the target domain at the top layer of the network. To better exploit the discriminative information from the source domain, we further develop a deeply supervised transfer metric learning (DSTML) method by including an additional objective on DTML, where the output of both the hidden layers and the top layer are optimized jointly. To preserve the local manifold of input data points in the metric space, we present two new methods, DTML with autoencoder regularization and DSTML with autoencoder regularization. Experimental results on face verification, person re-identification, and handwritten digit recognition validate the effectiveness of the proposed methods.
Metal halide perovskites, such as CsPbX3 (X = Cl, Br, and I), have gained extensive attention due to their increasing demand in optoelectronic applications such as solar cells and lighting-emitting ...devices. Herein, we report a versatile approach to synthesize high-quality CsPbBr3 perovskite nanocrystals (sized 5–15 nm) by ligand-assisted reprecipitation at room temperature. The monodispersed CsPbBr3 nanocube perovskites displayed relatively high photoluminescence quantum yields of 50–80%. By virtue of the quantum size effects, the bandgap energies were manipulated from blue to green spectral regions (410–530 nm). In addition, through compositional modulations of the anion exchange technique, the bright photoluminescence could be almost tuned over the entire visible spectral region (450–650 nm). Furthermore, the photoluminescence of the CsPbBr3 nanocrystals was characterized by narrow emission line widths of 15–50 nm and radiative lifetimes of 5–15 ns. Finally, by taking advantage of these outstanding merits, the CsPbBr3 perovskites were successfully utilized in the application of highly fluorescent patterning and color-purity light-emitting diodes.
Lithium–oxygen batteries are considered the next‐generation power sources for many applications. The commercialization of this technology, however, is hindered by a variety of technical hurdles, ...including low obtainable capacity, poor energy efficiency, and limited cycle life of the electrodes, especially the cathode (or oxygen) electrode. During the last decade, tremendous efforts have been devoted to the development of new cathode materials. Among them, perovskite oxides have attracted much attention due to the extraordinary tunability of their compositions, structures, and functionalities (e.g., high electrical conductivities and catalytic activities), demonstrating the potential to achieve superior battery performance. This article focuses on the recent advances of perovskite oxides as the electrode materials in nonaqueous lithium–oxygen batteries. The electrochemical mechanisms of oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) on the surface of perovskite oxides are first summarized. Then, the effect of nanostructure and morphology on ORR and OER activities is reviewed, from nanoparticles to hierarchical porous structures. Moreover, perovskite‐oxide‐based composite electrodes are discussed, highlighting the enhancement in electrical conductivities, catalytic activities, and durability under realistic operating conditions. Finally, the remaining challenges and new directions for achieving rational design of perovskite oxides for nonaqueous lithium–oxygen batteries are outlined and discussed.
Perovskite oxides as the electrode materials in nonaqueous lithium–oxygen batteries are reviewed. Future research directions of perovskite oxides should focus on the understanding of electrochemical mechanisms during the oxygen reduction and evolution processes, the structure design from nanoparticles to hierarchical porous structures, and the composite incorporation with improved electrical conductivities, catalytic activities, and structural merits.