Search

Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at http://vipl.ict.ac.cn/resources/codes/code/SANet_code.zip. [ABSTRACT FROM AUTHOR]

Information-theoretic quantities like entropy and mutual information have found numerous uses in machine learning. It is well known that there is a strong connection between these entropic quantities and submodularity since entropy over a set of random variables is submodular. In this paper, we study combinatorial information measures that generalize independence, (conditional) entropy, (conditional) mutual information, and total correlation defined over sets of (not necessarily random) variables. These measures strictly generalize the corresponding entropic measures since they are all parameterized via submodular functions that themselves strictly generalize entropy. Critically, we show that, unlike entropic mutual information in general, the submodular mutual information is actually submodular in one argument, holding the other fixed, for a large class of submodular functions whose third-order partial derivatives satisfy a non-negativity property. This turns out to include a number of practically useful cases such as the facility location and set-cover functions. We study specific instantiations of the submodular information measures on these, as well as the probabilistic coverage, graph-cut, log-determinants, and saturated coverage functions and see that they all have mathematically intuitive and practically useful expressions. Finally, we also study generalized independence between subsets of datapoints (random variables in the entropic case), and connect the independence characterizations to independence in log-submodular distributions. Regarding applications, we connect the maximization of submodular (conditional) mutual information to problems such as mutual-information-based, query-based, and privacy preserving summarization—and we connect optimizing the multi-set submodular mutual information to clustering and robust partitioning. We perform real world as well as synthetic experiments on various data summarization tasks. [ABSTRACT FROM AUTHOR]

In recommender systems, cold-start issues are situations where no previous events, e.g., ratings, are known for certain users or items. In this paper, we focus on the item cold-start problem. Both content information (e.g., item attributes) and initial user ratings are valuable for seizing users’ preferences on a new item. However, previous methods for the item cold-start problem either (1) incorporate content information into collaborative filtering to perform hybrid recommendation, or (2) actively select users to rate the new item without considering content information and then do collaborative filtering. In this paper, we propose a novel recommendation scheme for the item cold-start problem by leveraging both active learning and items’ attribute information. Specifically, we design useful user selection criteria based on items’ attributes and users’ rating history, and combine the criteria in an optimization framework for selecting users. By exploiting the feedback ratings, users’ previous ratings and items’ attributes, we then generate accurate rating predictions for the other unselected users. Experimental results on two real-world datasets show the superiority of our proposed method over traditional methods. [ABSTRACT FROM AUTHOR]

Different from previous imputation methods which impute missing values in the incomplete samples by using the information in the complete samples, this paper proposes a Date-drive Incremental imputation Model, DIM for short, which uses all available information in the data set to impute missing values economically, effectively, orderly, and iteratively. To this end, we propose a scoring rule to rank the missing features by taking into account both the economical criterion and the effective imputation information. The economical criterion takes both the imputation cost and the discriminative ability of the feature into account, while the effective imputation information enables to use all observed information in the data set including the imputed missing values to impute the left missing values. During the imputation process, our DIM first detects the neednot-impute samples for reducing the imputation cost and noise, and then selects the missing features with the top rank to impute first. The imputation process orderly imputes the missing features until all missing values are imputed or the imputation cost is exhausted. Experimental results on UCI data sets demonstrated the advantages of our proposed DIM, compared to the comparison methods, in terms of prediction accuracy and classification accuracy. [ABSTRACT FROM AUTHOR]

Label distribution learning (LDL) is proposed for solving the label ambiguity problem in recent years, which can be seen as an extension of multi-label learning. To improve the performance of label distribution learning, some existing algorithms exploit label correlations in a global manner that assumes the label correlations are shared by all instances. However, the instances in different groups may share different label correlations, and few label correlations are globally applicable in real-world tasks. In this paper, two novel label distribution learning algorithms are proposed by exploiting label correlations on local samples, which are called GD-LDL-SCL and Adam-LDL-SCL, respectively. To utilize the label correlations on local samples, the influence of local samples is encoded, and a local correlation vector is designed as the additional features for each instance, which is based on the different clustered local samples. Then, the label distribution for an unseen instance can be predicted by exploiting the original features and the additional features simultaneously. Extensive experiments on some real-world data sets validate that our proposed methods can address the label distribution problems effectively and outperform state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Ensemble clustering has been a popular research topic in data mining and machine learning. Despite its significant progress in recent years, there are still two challenging issues in the current ensemble clustering research. First, most of the existing algorithms tend to investigate the ensemble information at the object-level, yet often lack the ability to explore the rich information at higher levels of granularity. Second, they mostly focus on the direct connections (e.g., direct intersection or pair-wise co-occurrence) in the multiple base clusterings, but generally neglect the multiscale indirect relationship hidden in them. To address these two issues, this paper presents a novel ensemble clustering approach based on fast propagation of cluster-wise similarities via random walks. We first construct a cluster similarity graph with the base clusters treated as graph nodes and the cluster-wise Jaccard coefficient exploited to compute the initial edge weights. Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information. Specifically, by investigating the propagating trajectories starting from different nodes, a new cluster-wise similarity matrix can be derived by considering the trajectory relationship. Then, the newly obtained cluster-wise similarity matrix is mapped from the cluster-level to the object-level to achieve an enhanced co-association matrix, which is able to simultaneously capture the object-wise co-occurrence relationship as well as the multiscale cluster-wise relationship in ensembles. Finally, two novel consensus functions are proposed to obtain the consensus clustering result. Extensive experiments on a variety of real-world datasets have demonstrated the effectiveness and efficiency of our approach. [ABSTRACT FROM AUTHOR]

This paper addresses two fundamental problems: 1) learning discriminative model parameters and 2) avoiding over-fitting, which often occurs in regression-based classification tasks. We formulate these two problems in terms of relaxing both the strict binary label matrix and graph regularization term into more flexible forms so that the margins between different classes are enlarged as much as possible and the problem of over-fitting is avoided to some extent. This task is accomplished by the proposed double relaxed regression (DRR) method. The convex problem of DRR is solved efficiently with an iterative procedure. Extensive experiments on synthetic and real world image data sets demonstrate the effectiveness of the proposed method in terms of both classification accuracy and running time. [ABSTRACT FROM AUTHOR]

Given a graph $G$G and a vertex $q\in G$q∈G, the community search (CS) problem aims to efficiently find a subgraph of $G$G whose vertices are closely related to $q$q. Communities are prevalent in social and biological networks, and can be used in product advertisement and social event recommendation. In this paper, we study profiled community search (PCS), where CS is performed on a profiled graph. This is a graph in which each vertex has labels arranged in a hierarchical manner. Extensive experiments show that PCS can identify communities with themes that are common to their vertices, and is more effective than existing CS approaches. As a naive solution for PCS is highly expensive, we have also developed a tree index, which facilitates efficient and online solutions for PCS. [ABSTRACT FROM AUTHOR]

In order to improve the interpretation of principal components, many sparse principal component analysis (PCA) methods have been proposed by in the form of self-contained regression-type. In this paper, we generalize the steps needed to move from PCA-like methods to its self-contained regression-type, and propose a joint sparse pixel weighted PCA method. More specifically, we generalize a self-contained regression-type framework of graph embedding. Unlike the regression-type of graph embedding relying on the regular low-dimensional data, the self-contained regression-type framework does not rely on the regular low-dimensional data of graph embedding. The learned low-dimensional data in the form of self-contained regression theoretically approximates to the regular low-dimensional data. Under this self-contained regression-type, sparse regularization term can be arbitrarily added, and hence, the learned sparse regression coefficients can interpret the low-dimensional data. By using the joint sparse $\ell _{2,1}$ -norm regularizer, a sparse self-contained regression-type of pixel weighted PCA can be produced. Experiments on six data sets demonstrate that the proposed method is both feasible and effective. [ABSTRACT FROM AUTHOR]

In this paper, we give a complete answer to the conjecture on restricted isometry property (RIP) constants \delta tk (00,\,\,\delta tk<({t}/({4-t}))+\epsilon cannot guarantee the exact recovery of some k -sparse signals. Furthermore, it will be shown that similar characterizations also hold for low-rank matrix recovery. Thus, combined with T. Cai and A. Zhang’s work, a complete characterization for sharp RIP constants \delta _{tk} for all t > 0$ is obtained to guarantee the exact recovery of all k$ -sparse signals and matrices with rank at most k$ by -norm minimization and nuclear norm minimization, respectively. Noisy cases and approximately sparse cases are also considered. To solve the conjecture, we construct a few identities so that RIP of order $tk$ , which is the target of our main results, can be perfectly applied to them. [ABSTRACT FROM PUBLISHER]

Mining massive and high-speed data streams among the main contemporary challenges in machine learning. This calls for methods displaying a high computational efficacy, with ability to continuously update their structure and handle ever-arriving big number of instances. In this paper, we present a new incremental and distributed classifier based on the popular nearest neighbor algorithm, adapted to such a demanding scenario. This method, implemented in Apache Spark, includes a distributed metric-space ordering to perform faster searches. Additionally, we propose an efficient incremental instance selection method for massive data streams that continuously update and remove outdated examples from the case-base. This alleviates the high computational requirements of the original classifier, thus making it suitable for the considered problem. Experimental study conducted on a set of real-life massive data streams proves the usefulness of the proposed solution and shows that we are able to provide the first efficient nearest neighbor solution for high-speed big and streaming data. [ABSTRACT FROM AUTHOR]

Toward weather condition recognition, we emphasize the importance of regional cues in this paper and address a few important problems regarding appropriate representation, its differentiation among regions, and weather-condition feature construction. Our major contribution is, first, to construct a multi-class benchmark data set containing 65 000 images from six common categories for sunny, cloudy, rainy, snowy, haze, and thunder weather. This data set also benefits weather classification and attribute recognition. Second, we propose a deep learning framework named region selection and concurrency model (RSCM) to help discover regional properties and concurrency. We evaluate RSCM on our multi-class benchmark data and another public data set for weather recognition. [ABSTRACT FROM AUTHOR]

Class evolution, the phenomenon of class emergence and disappearance, is an important research topic for data stream mining. All previous studies implicitly regard class evolution as a transient change, which is not true for many real-world problems. This paper concerns the scenario where classes emerge or disappear gradually. A class-based ensemble approach, namely Class-Based ensemble for Class Evolution (CBCE), is proposed. By maintaining a base learner for each class and dynamically updating the base learners with new data, CBCE can rapidly adjust to class evolution. A novel under-sampling method for the base learners is also proposed to handle the dynamic class-imbalance problem caused by the gradual evolution of classes. Empirical studies demonstrate the effectiveness of CBCE in various class evolution scenarios in comparison to existing class evolution adaptation methods. [ABSTRACT FROM PUBLISHER]

Recent years have witnessed a surge of interest in graph-based transductive image classification. Existing simple graph-based transductive learning methods only model the pairwise relationship of images, however, and they are sensitive to the radius parameter used in similarity calculation. Hypergraph learning has been investigated to solve both difficulties. It models the high-order relationship of samples by using a hyperedge to link multiple samples. Nevertheless, the existing hypergraph learning methods face two problems, i.e., how to generate hyperedges and how to handle a large set of hyperedges. This paper proposes an adaptive hypergraph learning method for transductive image classification. In our method, we generate hyperedges by linking images and their nearest neighbors. By varying the size of the neighborhood, we are able to generate a set of hyperedges for each image and its visual neighbors. Our method simultaneously learns the labels of unlabeled images and the weights of hyperedges. In this way, we can automatically modulate the effects of different hyperedges. Thorough empirical studies show the effectiveness of our approach when compared with representative baselines. [ABSTRACT FROM PUBLISHER]

On face recognition, most previous works on dimensionality reduction and classification would first transform the input image into 1-D vector, which ignores the underlying data structure and often leads to the small sample size problem. More recently, 2-D discriminant analysis has become an interesting technique which can overcome the aforementioned drawbacks. However, 2-D methods extract features based on the rows or the columns of all images, so it is possible that the features using 2-D methods still contain some redundant information. In addition, most existing 2-D methods cannot provide an automatic strategy to choose discriminant vectors. In this paper, we study the combination of 2-D discriminant analysis and 1-D discriminant analysis and propose a two-stage framework: "(2D)2MMC + LDA." Because the extracted features based on maximal margin criterion (MMC) is robust, stable, and efficient, in the first stage, a 2-D two-directional feature extraction technique, (2D)2MMC, is presented. In the second stage, the linear discriminant analysis (LDA) step is performed in the (2D)2MMC subspace. Experiments with Feret, Olivetti and Oracle Research Laboratory, and Carnegie Mellon University Pose, Illumination, and Expression databases are conducted to evaluate our method in terms of classification accuracy and robustness. [ABSTRACT FROM AUTHOR]

Abstract-Face recognition applications commonly suffer from three main drawbacks: a reduced training set, information lying in high-dimensional subspaces, and the need to incorporate new people to recognize. In the recent literature, the extension of a face classifier in order to include new people in the model has been solved using online feature extraction techniques. The most successful approaches of those are the extensions of the principal component analysis or the linear discriminant analysis. In the current paper, a new online boosting algorithm is introduced: a face recognition method that extends a boosting-based classifier by adding new classes while avoiding the need of retraining the classifier each time a new person joins the system. The classifier is learned using the multitask learning principle where multiple verification tasks are trained together sharing the same feature space. The new classes are added taking advantage of the structure learned previously, being the addition of new classes not computationally demanding. The present proposal has been (experimentally) validated with two different facial data sets by comparing our approach with the current state-of-the-art techniques. The resuIts show that the proposed online boosting algorithm fares better in terms of final accuracy. In addition, the global performance does not decrease drastically even when the number of classes of the base problem is multiplied by eight. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach to identify states with similar subpolicies and show how they can be integrated into the reinforcement learning framework to improve learning performance. The method utilizes a specialized tree structure to identify common action sequences of states, which are derived from possible optimal policies, and defines a similarity function between two states based on the number of such sequences. Using this similarity function, updates on the action-value function of a state are reflected onto all similar states. This allows experience that is acquired during learning to be applied to a broader context. The effectiveness of the method is demonstrated empirically. [ABSTRACT FROM AUTHOR]

While distance function learning for supervised learning tasks has a long history, extending it to learning tasks with weaker supervisory information has only been studied recently. In particular, some methods have been proposed for semisupervised metric learning based on pairwise similarity or dissimilarity information. In this paper, we propose a kernel approach for semisupervised metric learning and present in detail two special cases of this kernel approach. The metric learning problem is thus formulated as an optimization problem for kernel learning. An attractive property of the optimization problem is that it is convex and, hence, has no local optima. While a closed-form solution exists for the first special case, the second case is solved using an iterative majorization procedure to estimate the optimal solution asymptotically. Experimental results based on both synthetic and real-world data show that this new kernel approach is promising for nonlinear metric learning. [ABSTRACT FROM AUTHOR]

An important goal of indoor location estimation systems is to increase the estimation accuracy while reducing the power consumption. In this paper, we present a novel algorithm known as CaDet for power-efficient location estimation by intelligently selecting the number of Access Points (APs) used for location estimation. We show that by employing machine learning techniques, CaDet is able to use a small subset of the APs in the environment to detect a client's location with high accuracy. CaDet uses a combination of information theory, clustering analysis, and a decision tree algorithm. By collecting data and testing our algorithms in a realistic WLAN environment in the computer science department area of the Hong Kong University of Science and Technology, we show that CaDet (Clustering and Decision Tree-based method) can be much higher in accuracy as compared to other methods. We also show through experiments that, by intelligently selecting APs, we are able to save the power on the client device while achieving the same level of accuracy. [ABSTRACT FROM AUTHOR]