We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized da-ta points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approxi-mation for the tangent space at each point, and those tangent spaces are then aligned to give the global coordinates of the data pointswith respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can bequite small in some cases. We illustrate our algorithm using curves and surfaces both in 2D/3D Euclidean spaces and higher dimension-al Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.

Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

Deep learning on image denoising: An overview.

The high voltage insulator requires continuous monitoring and inspection to prevent failures and emergencies. Manual inspections are costly as it requires covering a large geographical area where insulators are often subjected to harsh weather conditions. Automatic detection of insulators from aerial images is the first step towards performing real-time classification of insulator conditions using Unmanned Aerial Vehicle (UAV). In this paper, we provide a cost-effective solution for detecting insulators under the conditions of an uncluttered background, varied object resolution and illumination conditions using You Only Look Once (YOLO) deep learning neural network model from aerial images. We apply data augmentation to avoid overfitting with a training set size of 56000 image samples. It is demonstrated experimentally that this method can accurately locate insulator on UAV based real-time image data. The detected insulator images are then successfully subjected to insulator surface condition assessment for the presence of ice, snow and water using different classifiers.

IN-YOLO: Real-Time Detection of Outdoor High Voltage Insulators Using UAV Imaging

The SIAM Journal on Optimization contains research articles on the theory and practice of optimization. The areas addressed include linear and quadratic programming, convex programming, nonlinear programming, complementarity problems, stochastic optimization, combinatorial optimization, integer programming, and convex, nonsmooth and variational analysis. Contributions may emphasize optimization theory, algorithms, software, computational practice, applications, or the links between these subjects.

SIAM Journal on Optimization

Body joints, directly obtained from a pose estimation model, have proven effective for action recognition. Existing works focus on analyzing the dynamics of human joints. However, except joints, humans also explore motions of limbs for understanding actions. Given this observation, we investigate the dynamics of human limbs for skeleton-based action recognition. Specifically, we represent an edge in a graph of a human skeleton by integrating its spatial neighboring edges (for encoding the cooperation between different limbs) and its temporal neighboring edges (for achieving the consistency of movements in an action). Based on this new edge representation, we devise a graph edge convolutional neural network (CNN). Considering the complementarity between graph node convolution and edge convolution, we further construct two hybrid networks by introducing different shared intermediate layers to integrate graph node and edge CNNs. Our contributions are twofold, graph edge convolution and hybrid networks for integrating the proposed edge convolution and the conventional node convolution. Experimental results on the Kinetics and NTU-RGB+D data sets demonstrate that our graph edge convolution is effective at capturing the characteristics of actions and that our graph edge CNN significantly outperforms the existing state-of-the-art skeleton-based action recognition methods.

Graph Edge Convolutional Neural Networks for Skeleton-Based Action Recognition

Global context based automatic road segmentation via dilated convolutional neural network

Multistage attention network for image inpainting

Image inpainting is a challenging computer vision task that aims to fill in missing regions of corrupted images with realistic contents. With the development of convolutional neural networks, many deep learning models have been proposed to solve image inpainting issues by learning information from a large amount of data. In particular, existing algorithms usually follow an encoding and decoding network architecture in which some operations with standard schemes are employed, such as static convolution, which only considers pixels with fixed grids, and the monotonous normalization style (e.g., batch normalization). However, these techniques are not well-suited for the image inpainting task because the random corrupted regions in the input images tend to mislead the inpainting process and generate unreasonable content. In this paper, we propose a novel dynamic selection network (DSNet) to solve this problem in image inpainting tasks. The principal idea of the proposed DSNet is to distinguish the corrupted region from the valid ones throughout the entire network architecture, which may help make full use of the information in the known area. Specifically, the proposed DSNet has two novel dynamic selection modules, namely, the validness migratable convolution (VMC) and regional composite normalization (RCN) modules, which share a dynamic selection mechanism that helps utilize valid pixels better. By replacing vanilla convolution with the VMC module, spatial sampling locations are dynamically selected in the convolution phase, resulting in a more flexible feature extraction process. Besides, the RCN module not only combines several normalization methods but also normalizes the feature regions selectively. Therefore, the proposed DSNet can illustrate realistic and fine-detailed images by adaptively selecting features and normalization styles. Experimental results on three public datasets show that our proposed method outperforms state-of-the-art methods both quantitatively and qualitatively.

Dynamic Selection Network for Image Inpainting

In this paper, we propose a novel nonlocal patch tensor-based visual data completion algorithm and analyze its potential problems. Our algorithm consists of two steps: the first step is initializing the image with triangulation-based linear interpolation and the second step is grouping similar nonlocal patches as a tensor then applying the proposed tensor completion technique. Specifically, with treating a group of patch matrices as a tensor, we impose the low-rank constraint on the tensor through the recently proposed tensor nuclear norm. Moreover, we observe that after the first interpolation step, the image gets blurred and, thus, the similar patches we have found may not exactly match the reference. We name the problem “Patch Mismatch,” and then in order to avoid the error caused by it, we further decompose the patch tensor into a low-rank tensor and a sparse tensor, which means the accepted horizontal strips in mismatched patches. Furthermore, our theoretical analysis shows that the error caused by Patch Mismatch can be decomposed into two components, one of which can be bounded by a reasonable assumption named local patch similarity, and the other part is lower than that using matrix completion. Extensive experimental results on real-world datasets verify our method’s superiority to the state-of-the-art tensor-based image inpainting methods.

Yipeng Zhang

Papers

Global context based automatic road segmentation via dilated convolutional neural network

Multistage attention network for image inpainting

Dynamic Selection Network for Image Inpainting

Nonlocal Low-Rank Tensor Completion for Visual Data

Discriminative subspace matrix factorization for multiview data clustering