Hand gesture recognition methods play an important role in human-computer interaction. Among these methods are skeleton-based recognition techniques that seem to be promising. In literature, several methods have been proposed to recognize hand gestures with skeletons. One problem with these methods is that they consider little the connectivity between the joints of a skeleton, constructing simple graphs for skeleton connectivity. Observing this, we built a new model of hand skeletons by adding three types of edges in the graph to finely describe the linkage action of joints. Then, an end-to-end deep neural network, hand gesture graph convolutional network, is presented in which the convolution is conducted only on linked skeleton joints. Since the training dataset is relatively small, this work proposes expanding the coordinate dimensionality so as to let models learn more semantic features. Furthermore, relative coordinates are employed to help hand gesture graph convolutional network learn the feature representation independent of the random starting positions of actions. The proposed method is validated on two challenging datasets, and the experimental results show that it outperforms the state-of-the-art methods. Furthermore, it is relatively lightweight in practice for hand skeleton-based gesture recognition.

Low-rank tensor completion methods have been advanced recently for modeling sparsely observed data with a multimode structure. However, low-rank priors may fail to interpret the model factors of general tensor objects. The most common method to address this drawback is to use regularizations together with the low-rank priors. However, due to the complex nature and diverse characteristics of real-world multiway data, the use of a single or a few regularizations remains far from efficient, and there are limited systematic experimental reports on the advantages of these regularizations for tensor completion. To fill these gaps, we propose a modified CP tensor factorization framework that fuses the l₂ norm constraint, sparseness (l₁ norm), manifold, and smooth information simultaneously. The factorization problem is addressed through a combination of Nesterov's optimal gradient descent method and block coordinate descent. Here, we construct a smooth approximation to the $l_1$ norm and TV norm regularizations, and then, the tensor factor is updated using the projected gradient method, where the step size is determined by the Lipschitz constant. Extensive experiments on simulation data, visual data completion, intelligent transportation systems, and GPS data of user involvement are conducted, and the efficiency of our method is confirmed by the results. Moreover, the obtained results reveal the characteristics of these commonly used regularizations for tensor completion in a certain sense and give experimental guidance concerning how to use them.

A lightweight convolutional (deep) neural networks (CNNs) based modulation format identification (MFI) scheme in 2D Stokes planes for polarization domain multiplexing (PDM) fiber communication system is proposed and demonstrated. Influences of the learning rate of CNN is discussed. Experimental verifications are performed for the PDM system at a symbol rate of 28GBaud. Six modulation formats are identified with a trained CNN from images of received signals. They are PDM-BPSK, PDM-QPSK, PDM-8PSK, PDM-16QAM, PDM-32QAM, and PDM-64QAM. By taking advantage of computer vision, the results show that the proposed scheme can significantly improve the identification performance over the existing techniques.

Generating action proposals in untrimmed videos is a challenging task, since video sequences usually contain lots of irrelevant contents and the duration of an action instance is arbitrary. The quality of action proposals is key to action detection performance. The previous methods mainly rely on sliding windows or anchor boxes to cover all ground-truth actions, but this is infeasible and computationally inefficient. To this end, this article proposes a RecapNet--a novel framework for generating action proposal, by mimicking the human cognitive process of understanding video content. Specifically, this RecapNet includes a residual causal convolution module to build a short memory of the past events, based on which the joint probability actionness density ranking mechanism is designed to retrieve the action proposals. The RecapNet can handle videos with arbitrary length and more important, a video sequence will need to be processed only in one single pass in order to generate all action proposals. The experiments show that the proposed RecapNet outperforms the state of the art under all metrics on the benchmark THUMOS14 and ActivityNet-1.3 datasets. The code is available publicly at https://github.com/tianwangbuaa/RecapNet.

This paper proposes a method of accurately assessing image quality without a reference image by using a deep convolutional neural network. Existing training based methods usually utilize a compact set of linear filters for learning features of images captured by different sensors to assess their quality. These methods may not be able to learn the semantic features that are intimately related with the features used in human subject assessment. Observing this drawback, this work proposes training a deep convolutional neural network (CNN) with labelled images for image quality assessment. The ReLU in the CNN allows non-linear transformations for extracting high-level image features, providing a more reliable assessment of image quality than linear filters. To enable the neural network to take images of any arbitrary size as input, the spatial pyramid pooling (SPP) is introduced connecting the top convolutional layer and the fully-connected layer. In addition, the SPP makes the CNN robust to object deformations to a certain extent. The proposed method taking an image as input carries out an end-to-end learning process, and outputs the quality of the image. It is tested on public datasets. Experimental results show that it outperforms existing methods by a large margin and can accurately assess the image quality on images taken by different sensors of varying sizes.