No abstract

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

No abstract

No abstract

No abstract

Machine olfaction is an intelligent system that combines a cross-sensitivity chemical sensor array and an effective pattern recognition algorithm for the detection, identification, or quantification of various odors. Data collected by the sensor array are the multivariate time series signals with a complex structure, and these signals become more difficult to analyze due to sensor drift. In this work, we focus on improving the classification performance under sensor drift by using the deep learning method, which is popular nowadays. Compared with other methods, our method can effectively tackle sensor drift by automatically extracting features, thus not only removing the complexity of designing the hand-made features but also making it pervasive for a variety of application in machine olfaction. Our experimental results show that the deep learning method can learn the features that are more robust to drift than the original input and achieves high classification accuracy. C 2015 Wiley Periodicals, Inc.

The convergence of Oja's principal component analysis (PCA) learning algorithms is a difficult topic for direct study and analysis. Traditionally, the convergence of these algorithms is indirectly analyzed via certain deterministic continuous time (DCT) systems. Such a method will require the learning rate to converge to zero, which is not a reasonable requirement to impose in many practical applications. Recently, deterministic discrete time (DDT) systems have been proposed instead to indirectly interpret the dynamics of the learning algorithms. Unlike DCT systems, DDT systems allow learning rates to be constant (which can be a nonzero). This paper will provide some important results relating to the convergence of a DDT system of Oja's PCA learning algorithm. It has the following contributions: 1) A number of invariant sets are obtained, based on which we can show that any trajectory starting from a point in the invariant set will remain in the set forever. Thus, the nondivergence of the trajectories is guaranteed. 2) The convergence of the DDT system is analyzed rigorously. It is proven, in the paper, that almost all trajectories of the system starting from points in an invariant set will converge exponentially to the unit eigenvector associated with the largest eigenvalue of the correlation matrix. In addition, exponential convergence rate are obtained, providing useful guidelines for the selection of fast convergence learning rate. 3) Since the trajectories may diverge, the careful choice of initial vectors is an important issue. This paper suggests to use the domain of unit hyper sphere as initial vectors to guarantee convergence. 4) Simulation results will be furnished to illustrate the theoretical results achieved.

Abnormal crowd behavior detection is an important research issue in computer vision. The traditional methods first extract the local spatio-temporal cuboid from video. Then the cuboid is described by optical flow or gradient features, etc. Unfortunately, because of the complex environmental conditions, such as severe occlusion, over-crowding, etc., the existing algorithms cannot be efficiently applied. In this paper, we derive the high-frequency and spatio-temporal (HFST) features to detect the abnormal crowd behaviors in videos. They are obtained by applying the wavelet transform to the plane in the cuboid which is parallel to the time direction. The high-frequency information characterize the dynamic properties of the cuboid. The HFST features are applied to the both global and local abnormal crowd behavior detection. For the global abnormal crowd behavior detection, Latent Dirichlet Allocation is used to model the normal scenes. For the local abnormal crowd behavior detection, Multiple Hidden Markov Models, with an competitive mechanism, is employed to model the normal scenes. The comprehensive experiment results show that the speed of detection has been greatly improved using our approach.Moreover, a good accuracy has been achieved considering the false positive and false negative detection rates.