This paper concerns the existence of affine-periodic solutions for perturbed affine-periodic *** kind of affine-periodic solutions has the form of x(t+T)≡Qx(t) with some nonsingular matrix Q,which may be quasi-period...
详细信息
This paper concerns the existence of affine-periodic solutions for perturbed affine-periodic *** kind of affine-periodic solutions has the form of x(t+T)≡Qx(t) with some nonsingular matrix Q,which may be quasi-periodic when Q is an orthogonal matrix. It can be even unbounded but x(t)/|x(t)| is quasi-periodic,like a helical line. for example x(t)=e^(at)(cos ωt, sin ωt), when Q is not an orthogonal matrix. The averaging method of higher order for finding affine-periodic solutions is given by topological degree.
This paper presents an unmanned aerial vehicle (UAV) pose estimation system based on monocular simultaneous localization and mapping (SLAM) guided by the desired shot. The system enables UAV to automatically adjust th...
详细信息
Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglecte...
ISBN:
(纸本)9781713829546
Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding Euclidean space, and hence to detect them becomes difficult for machine learning models. To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. We present a novel angle-based sectional curvature, termed ABS curvature, and accordingly three kinds of curvature regularization to induce flat embedding manifolds during graph embedding. We integrate curvature regularization into five popular proximity-preserving embedding methods, and empirical results in two applications show significant improvements on a wide range of open graph datasets.
Bayesian optimization (BO) is an effective method of finding the global optima of black-box functions. Recently BO has been applied to neural architecture search and shows better performance than pure evolutionary str...
详细信息
This paper gives a tutorial on how to prove Lyapunov type criteria by optimal control methods. Firstly, we consider stability criteria on Hill’s equations with nonnegative potential. By optimal control methods develo...
详细信息
This paper gives a tutorial on how to prove Lyapunov type criteria by optimal control methods. Firstly, we consider stability criteria on Hill’s equations with nonnegative potential. By optimal control methods developed in 1990s, we obtain several stability criteria including Lyapunov’s criterion, Neǐgauz and Lidskiǐ’s criterion. Secondly, we present stability criteria on Hill’s equations with sign-changing potential in which Brog’s criterion and Krein’s criterion are included.
With the rapid development of the movie industry, it is vital to evaluate and predict a movie's quality. In this paper, a movie score prediction model is proposed based on the movie plots. Movie data was processed...
With the rapid development of the movie industry, it is vital to evaluate and predict a movie's quality. In this paper, a movie score prediction model is proposed based on the movie plots. Movie data was processed with the word2 vec method, and the linear regression model and back propagation neural network algorithm were employed to establish the movie score prediction model. The high-quality classic movie plots of high-scoring movies summed up by big data contributed to a high synthesis of the wonderful content of the *** results show that it is effective in terms of movie evaluation and prediction, and helpful in understanding people's preferences for movie plots.
In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this techniq...
In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this technique, this paper introduces camera exposure parameters and puts the data association and pose estimation into a unified nonlinear optimization problem. Moreover, the direct monocular vision odometer is transplanted into the augmented reality system through the position adjustment module. We compare it with the traditional visual odometry method that matches the feature points. The results show that this improved method can be used to track more quickly and build a more visual semi-dense point cloud map, which can be used to support the registration and tracking of virtual objects in augmented reality.
Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic m...
详细信息
Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic models, supervised Latent Dirichlet Allocation （sLDA） is acknowledged as a popular and competitive supervised topic model. How- ever, the gradual increase of the scale of datasets makes sLDA more and more inefficient and time-consuming, and limits its applications in a very narrow range. To solve it, a parallel online sLDA, named PO-sLDA （Parallel and Online sLDA）, is proposed in this study. It uses the stochastic variational inference as the learning method to make the training procedure more rapid and efficient, and a parallel computing mechanism implemented via the MapReduce framework is proposed to promote the capacity of cloud computing and big data processing. The online training capacity supported by PO-sLDA expands the application scope of this approach, making it instrumental for real-life applications with high real-time demand. The validation using two datasets with different sizes shows that the proposed approach has the comparative accuracy as the sLDA and can efficiently accelerate the training procedure. Moreover, its good convergence and online training capacity make it lucrative for the large-scale text data analyzing and processing.
In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof ...
In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof the direct method and the feature point method. We use both photometric bundle adjustment which is robust to camera exposure time and motion bundle adjustment which is geometrically robust based on feature points to do tracking process. This approach can maintain an intuitive direct local map as well as a reusable global sparse feature point map. Through the processing of point clouds, such as PCA plane detection and grid reconstruction, we greatly improve the effect of the augmented reality system.
A low-than character feature embedding called radical embedding is proposed,and applied on a long-short term memory(LSTM) model for sentence segmentation of pre-modern Chinese *** dataset includes over 150 classical C...
详细信息
A low-than character feature embedding called radical embedding is proposed,and applied on a long-short term memory(LSTM) model for sentence segmentation of pre-modern Chinese *** dataset includes over 150 classical Chinese books from 3 different dynasties and contains different literary ***-conditional random fields(LSTM-CRF) model is a state-of-the-art method for the sequence labeling *** model adds a component of radical embedding,which leads to improved *** results based on the aforementioned Chinese books demonstrate better accuracy than earlier methods on sentence segmentation,especial in Tang’s epitaph texts(achieving an F1-score of 81.34%).
暂无评论