Sparse Hashing Tracking

Real-Time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model

3-D action recognition is referred to as the classification of action sequences which consist of 3-D skeleton joints. While many research works are devoted to 3-D action recognition, it mainly suffers from three problems: 1) highly complicated articulation; 2) a great amount of noise; and 3) low implementation efficiency. To tackle all these problems, we propose a real-time 3-D action-recognition framework by integrating the locally aggregated kinematic-guided skeletonlet (LAKS) with a supervised hashing-by-analysis (SHA) model. We first define the skeletonlet as a few combinations of joint offsets grouped in terms of the kinematic principle and then represent an action sequence using LAKS, which consists of a denoising phase and a locally aggregating phase. The denoising phase detects the noisy action data and adjusts it by replacing all the features within it with the features of the corresponding previous frame, while the locally aggregating phase sums the difference between an offset feature of the skeletonlet and its cluster center together over all the offset features of the sequence. Finally, the SHA model combines sparse representation with a hashing model, aiming at promoting the recognition accuracy while maintaining high efficiency. Experimental results on MSRAction3D, UTKinectAction3D, and Florence3DAction datasets demonstrate that the proposed method outperforms state-of-the-art methods in both recognition accuracy and implementation efficiency.

Profiling and predicting the problem-solving patterns in China’s research systems: A methodology of intelligent bibliometrics and empirical insights

Uncovering the driving forces, strategic landscapes, and evolutionary mechanisms of China’s research systems is attracting rising interest around the globe. One topic of interest is to understand the problem-solving patterns in China’s research systems now and in the future. Targeting a set of high-quality research articles published by Chinese researchers between 2009 and 2018, and indexed in the Essential Science Indicators database, we developed an intelligent bibliometrics-based methodology for identifying the problem-solving patterns from scientific documents. Specifically, science overlay maps incorporating link prediction were used to profile China’s disciplinary interactions and predict potential cross-disciplinary innovation at a macro level. We proposed a function incorporating word embedding techniques to represent subjects, actions, and objects (SAO) retrieved from combined titles and abstracts into vectors and constructed a tri-layer SAO network to visualize SAOs and their semantic relationships. Then, at a micro level, we developed network analytics for identifying problems and solutions from the SAO network, and recommending potential solutions for existing problems. Empirical insights derived from this study provide clues to understand China’s research strengths and the science policies underlying them, along with the key research problems and solutions that Chinese researchers are focusing on now and might pursue in the future.

Robust Visual Tracking via Online Discriminative and Low-Rank Dictionary Learning

In this paper, we propose a novel and robust tracking framework based on online discriminative and low-rank dictionary learning. The primary aim of this paper is to obtain compact and low-rank dictionaries that can provide good discriminative representations of both target and background. We accomplish this by exploiting the recovery ability of low-rank matrices. That is if we assume that the data from the same class are linearly correlated, then the corresponding basis vectors learned from the training set of each class shall render the dictionary to become approximately low-rank. The proposed dictionary learning technique incorporates a reconstruction error that improves the reliability of classification. Also, a multiconstraint objective function is designed to enable active learning of a discriminative and robust dictionary. Further, an optimal solution is obtained by iteratively computing the dictionary, coefficients, and by simultaneously learning the classifier parameters. Finally, a simple yet effective likelihood function is implemented to estimate the optimal state of the target during tracking. Moreover, to make the dictionary adaptive to the variations of the target and background during tracking, an online update criterion is employed while learning the new dictionary. Experimental results on a publicly available benchmark dataset have demonstrated that the proposed tracking algorithm performs better than other state-of-the-art trackers.

Global Hashing System for Fast Image Search

Hashing methods have been widely investigated for fast approximate nearest neighbor searching in large data sets. Most existing methods use binary vectors in lower dimensional spaces to represent data points that are usually real vectors of higher dimensionality. We divide the hashing process into two steps. Data points are first embedded in a low-dimensional space, and the global positioning system method is subsequently introduced but modified for binary embedding. We devise dataindependent and data-dependent methods to distribute the satellites at appropriate locations. Our methods are based on finding the tradeoff between the information losses in these two steps. Experiments show that our data-dependent method outperforms other methods in different-sized data sets from 100k to 10M. By incorporating the orthogonality of the code matrix, both our data-independent and data-dependent methods are particularly impressive in experiments on longer bits.

A Fast Optimization Method for General Binary Code Learning

Hashing or binary code learning has been recognized to accomplish efficient near neighbor search, and has thus attracted broad interests in recent retrieval, vision, and learning studies. One main challenge of learning to hash arises from the involvement of discrete variables in binary code optimization. While the widely used continuous relaxation may achieve high learning efficiency, the pursued codes are typically less effective due to accumulated quantization error. In this paper, we propose a novel binary code optimization method, dubbed discrete proximal linearized minimization (DPLM), which directly handles the discrete constraints during the learning process. Specifically, the discrete (thus nonsmooth nonconvex) problem is reformulated as minimizing the sum of a smooth loss term with a nonsmooth indicator function. The obtained problem is then efficiently solved by an iterative procedure with each iteration admitting an analytical discrete solution, which is thus shown to converge very fast. In addition, the proposed method supports a large family of empirical loss functions, which is particularly instantiated in this paper by both a supervised and an unsupervised hashing losses, together with the bits uncorrelation and balance constraints. In particular, the proposed DPLM with a supervised ℓ₂ loss encodes the whole NUS-WIDE database into 64-b binary codes within 10 s on a standard desktop computer. The proposed approach is extensively evaluated on several large-scale data sets and the generated binary codes are shown to achieve very promising results on both retrieval and classification tasks.

Occlusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency

In this paper, we present a robust tracking method by exploiting a fragment-based appearance model with consideration of both temporal continuity and discontinuity information. From the perspective of probability theory, the proposed tracking algorithm can be viewed as a two-stage optimization problem. In the first stage, by adopting the estimated occlusion state as a prior, the optimal state of the tracked object can be obtained by solving an optimization problem, where the objective function is designed based on the classification score, occlusion prior, and temporal continuity information. In the second stage, we propose a discriminative occlusion model, which exploits both foreground and background information to detect the possible occlusion, and also models the consistency of occlusion labels among different frames. In addition, a simple yet effective training strategy is introduced during the model training (and updating) process, with which the effects of spatial-temporal consistency are properly weighted. The proposed tracker is evaluated by using the recent benchmark data set, on which the results demonstrate that our tracker performs favorably against other state-of-the-art tracking algorithms.