arXiv subjects

Lei Zhao

Publications and source records attributed to Lei Zhao.

At least 181 records · Page 10Linked to original sources

arXiv2021

Knowledge Enhanced Sports Game Summarization

Sports game summarization aims at generating sports news from live commentaries. However, existing datasets are all constructed through automated collection and cleaning processes, resulting in a lot of noise. Besides, current works neglect the knowledge gap between live commentaries and sports news, which limits the performance of sports game summarization. In this paper, we introduce K-SportsSum, a new dataset with two characteristics: (1) K-SportsSum collects a large amount of data from massive games. It has 7,854 commentary-news pairs. To improve the quality, K-SportsSum employs a manual cleaning process; (2) Different from existing datasets, to narrow the knowledge gap, K-SportsSum further provides a large-scale knowledge corpus that contains the information of 523 sports teams and 14,724 sports players. Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news. Extensive experiments on K-SportsSum and SportsSum datasets show that our model achieves new state-of-the-art performances. Qualitative analysis and human study further verify that our model generates more informative sports news.

cs.CL↗

arXiv2021

Quaternion-Based Graph Convolution Network for Recommendation

Graph Convolution Network (GCN) has been widely applied in recommender systems for its representation learning capability on user and item embeddings. However, GCN is vulnerable to noisy and incomplete graphs, which are common in real world, due to its recursive message propagation mechanism. In the literature, some work propose to remove the feature transformation during message propagation, but making it unable to effectively capture the graph structural features. Moreover, they model users and items in the Euclidean space, which has been demonstrated to have high distortion when modeling complex graphs, further degrading the capability to capture the graph structural features and leading to sub-optimal performance. To this end, in this paper, we propose a simple yet effective Quaternion-based Graph Convolution Network (QGCN) recommendation model. In the proposed model, we utilize the hyper-complex Quaternion space to learn user and item representations and feature transformation to improve both performance and robustness. Specifically, we first embed all users and items into the Quaternion space. Then, we introduce the quaternion embedding propagation layers with quaternion feature transformation to perform message propagation. Finally, we combine the embeddings generated at each layer with the mean pooling strategy to obtain the final embeddings for recommendation. Extensive experiments on three public benchmark datasets demonstrate that our proposed QGCN model outperforms baseline methods by a large margin.

cs.IR↗

arXiv2021

RSS-based Multiple Sources Localization with Unknown Log-normal Shadow Fading

Multi-source localization based on received signal strength (RSS) has drawn great interest in wireless sensor networks. However, the shadow fading term caused by obstacles cannot be separated from the received signal, which leads to severe error in location estimate. In this paper, we approximate the log-normal sum distribution through Fenton-Wilkinson method to formulate a non-convex maximum likelihood (ML) estimator with unknown shadow fading factor. In order to overcome the difficulty in solving the non-convex problem, we propose a novel algorithm to estimate the locations of sources. Specifically, the region is divided into $N$ grids firstly, and the multi-source localization is converted into a sparse recovery problem so that we can obtain the sparse solution. Then we utilize the K-means clustering method to obtain the rough locations of the off-grid sources as the initial feasible point of the ML estimator. Finally, an iterative refinement of the estimated locations is proposed by dynamic updating of the localization dictionary. The proposed algorithm can efficiently approach a superior local optimal solution of the ML estimator. It is shown from the simulation results that the proposed method has a promising localization performance and improves the robustness for multi-source localization in unknown shadow fading environments. Moreover, the proposed method provides a better computational complexity from $O(K^3N^3)$ to $O(N^3)$.

eess.SP↗

arXiv2021

Conformal Transformations and Integrable Mechanical Billiards

In this article we explain that several integrable mechanical billiards in the plane are connected via conformal transformations. We first remark that the free billiard in the plane are conformal equivalent to infinitely many billiard systems defined in central force problems on a particular fixed energy level. We then explain that the classical Hooke-Kepler correspondence can be carried over to a correspondence between integrable Hooke-Kepler billiards. As part of the conclusion we show that any focused conic section gives rise to integrable Kepler billiards, which brings generalizations to a previous work of Gallavotti-Jauslin. We discuss several generalizations of integrable Stark billiards. We also show that any confocal conic sections give rise to integrable billiard systems of Euler's two-center problems.

math.DS↗

arXiv2021

The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations

Background: The worldwide surge in coronavirus cases has led to the COVID-19 testing demand surge. Rapid, accurate, and cost-effective COVID-19 screening tests working at a population level are in imperative demand globally. Methods: Based on the eye symptoms of COVID-19, we developed and tested a COVID-19 rapid prescreening model using the eye-region images captured in China and Spain with cellphone cameras. The convolutional neural networks (CNNs)-based model was trained on these eye images to complete binary classification task of identifying the COVID-19 cases. The performance was measured using area under receiver-operating-characteristic curve (AUC), sensitivity, specificity, accuracy, and F1. The application programming interface was open access. Findings: The multicenter study included 2436 pictures corresponding to 657 subjects (155 COVID-19 infection, 23.6%) in development dataset (train and validation) and 2138 pictures corresponding to 478 subjects (64 COVID-19 infections, 13.4%) in test dataset. The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0.913 (95% CI, 0.898-0.927), with a sensitivity of 0.695 (95% CI, 0.643-0.748), a specificity of 0.904 (95% CI, 0.891 -0.919), an accuracy of 0.875(0.861-0.889), and a F1 of 0.611(0.568-0.655). Interpretation: The CNN-based model for COVID-19 rapid prescreening has reliable specificity and sensitivity. This system provides a low-cost, fully self-performed, non-invasive, real-time feedback solution for continuous surveillance and large-scale rapid prescreening for COVID-19. Funding: This project is supported by Aimomics (Shanghai) Intelligent

eess.IV↗

arXiv2021

VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.

cs.CV↗

arXiv2021

Rapid COVID-19 Risk Screening by Eye-region Manifestations

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts. On the other hand, there are more and more ocular manifestations that have been reported in the COVID-19 patients as growing clinical evidence[1]. This inspired this project. We have conducted the joint clinical research since January 2021 at the ShiJiaZhuang City, Heibei province, China, which approved by the ethics committee of The fifth hospital of ShiJiaZhuang of Hebei Medical University. We undertake several blind tests of COVID-19 patients by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Meantime as an important part of the ongoing globally COVID-19 eye test program by AIMOMICS since February 2020, we propose a new fast screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras. This could reliably make a rapid risk screening of COVID-19 with the sustainable stable high performance in different countries and races. Our model for COVID-19 rapid prescreening have the merits of the lower cost, fully self-performed, non-invasive, importantly real-time, and thus enables the continuous health surveillance. We further implement it as the open accessible APIs, and provide public service to the world. Our pilot experiments show that our model is ready to be usable to all kinds of surveillance scenarios, such as infrared temperature measurement device at airports and stations, or directly pushing to the target people groups smartphones as a packaged application.

eess.IV↗

arXiv2021

On Compression of Unsupervised Neural Nets by Pruning Weak Connections

Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction,unsupervised weight initialization and density estimation. In this paper,we demonstrate that the parameters of these neural nets can be dramatically reduced without affecting their performance. We describe a method to reduce the parameters required by RBM which is the basic building block for deep architectures. Further we propose an unsupervised sparse deep architectures selection algorithm to form sparse deep neural networks.Experimental results show that there is virtually no loss in either generative or discriminative performance.

cs.CV↗

arXiv2021

Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization

Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain. Conditional generative adversarial networks (cGANs) are often adopted for modeling such a conditional distribution. However, cGANs are prone to ignore the latent code and learn a unimodal distribution in conditional image synthesis, which is also known as the mode collapse issue of GANs. To solve the problem, we propose a simple yet effective method that explicitly estimates and maximizes the mutual information between the latent code and the output image in cGANs by using a deep mutual information neural estimator in this paper. Maximizing the mutual information strengthens the statistical dependency between the latent code and the output image, which prevents the generator from ignoring the latent code and encourages cGANs to fully utilize the latent code for synthesizing diverse results. Our method not only provides a new perspective from information theory to improve diversity for I2IT but also achieves disentanglement between the source domain content and the target domain style for free.

cs.CV↗

arXiv2021

Projective Dynamics and an Integrable Boltzmann Billiard Model

The aim of this note is to explain the integrability of an integrable Boltzmann billiard model, previously established by Gallavotti and Jauslin in arXiv:2008.01955, alternatively via the viewpoint of projective dynamics. The additional first integral is shown to be related to the energy of a corresponding system on a hemisphere. We show that this viewpoint applies to certain other billiard models in the plane defined through Kepler-Coulomb problems as well. The approach also leads to a family of integrable billiard models on the sphere defined through the spherical Kepler-Coulomb problem.

math.DS↗

arXiv2020

A stochastic optimization algorithm for analyzing planar central and balanced configurations in the $n$-body problem

A stochastic optimization algorithm for analyzing planar central and balanced configurations in the $n$-body problem is presented. We find a comprehensive list of equal mass central configurations satisfying the Morse equality up to $n=12$. We show some exemplary balanced configurations in the case $n=5$, as well as some balanced configurations without any axis of symmetry in the cases $n=4$ and $n=10$.

math.DS↗

arXiv2020

Graph Learning for Spatiotemporal Signals with Long- and Short-Term Characterization

Mining natural associations from high-dimensional spatiotemporal signals plays an important role in various fields including biology, climatology, and financial analysis. However, most existing works have mainly studied time-independent signals without considering the correlations of spatiotemporal signals that achieve high learning accuracy. This paper aims to learn graphs that better reflect underlying data relations by leveraging the long- and short-term characteristics of spatiotemporal signals. First, a spatiotemporal signal model is presented that considers both spatial and temporal relations. In particular, we integrate a low-rank representation and a Gaussian Markov process to describe the temporal correlations. Then, the graph learning problem is formulated as a joint low-rank component estimation and graph Laplacian inference. Accordingly, we propose a low rank and spatiotemporal smoothness-based graph learning method (GL-LRSS), which introduces a spatiotemporal smoothness prior into time-vertex signal analysis. By jointly exploiting the low rank of long-time observations and the smoothness of short-time observations, the overall learning performance can be effectively improved. Experiments on both synthetic and real-world datasets demonstrate substantial improvements in the learning accuracy of the proposed method over the state-of-the-art low-rank component estimation and graph learning methods.

cs.SI↗

arXiv2020

Design of a Time-to-Digital Converter ASIC and a mini-DAQ system for the Phase-2 Upgrade of the ATLAS Monitored Drift Tube detector

We present the second prototype of a time-to-digital (TDC) ASIC for the upgrade of the ATLAS Monitored Drift Tube (MDT) detector for High-Luminosity LHC operations. Compared to the first prototype, triple modular redundancy has been implemented for the configuration and flow control logic. The total power consumption is increased by less than 10 mW while achieving the same time resolution and channel uniformity. A mini-DAQ system has been built to verify the front-end electronics chain with the new prototype together with other ASICs and boards in triggered mode. Cosmic ray tests with a small-diameter MDT chamber indicate that the configuration and data transmission of the readout electronics perform well. It is expected that this prototype design will be used in the final production.

physics.ins-det↗

arXiv2020

Generalized Periodic Orbits of Time-Periodically Forced Kepler Problem Accumulating the Center and of Circular and Elliptic Restricted Three-Body Problems

In this paper, we consider a time-periodically forced Kepler problem in any dimensions, with an external force which we only assume to be regular in a neighborhood of the attractive center. We prove that there exist infinitely many periodic orbits in this system, with possible double collisions with the center regularized, which accumulate the attractive center. The result is obtained via a localization argument combined with a result on $C^{1}$-persistence of closed orbits by a local homotopy-streching argument. Consequently, by formulating the circular and elliptic restricted three-body problems of any dimensions as time-periodically forced Kepler problems, we obtain that there exists infinitely many periodic orbits, with possible double collisions with the primaries regularized, accumulating to each of the primaries.

math.DS↗

arXiv2020

Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming

Linear constrained convex programming has many practical applications, including support vector machine and machine learning portfolio problems. We propose the randomized primal-dual coordinate (RPDC) method, a randomized coordinate extension of the first-order primal-dual method by Cohen and Zhu, 1984 and Zhao and Zhu, 2019, to solve linear constrained convex programming. We randomly choose a block of variables based on a uniform distribution, linearize, and apply a Bregman-like function (core function) to the selected block to obtain simple parallel primal-dual decomposition. We then establish almost surely convergence and expected O(1/t) convergence rate, and expected linear convergence under global strong metric subregularity. Finally, we discuss implementation details for the randomized primal-dual coordinate approach and present numerical experiments on support vector machine and machine learning portfolio problems to verify the linear convergence.

math.OC↗

arXiv2020

Level-set Subdifferential Error Bounds and Linear Convergence of Variable Bregman Proximal Gradient Method

In this work, we develop a level-set subdifferential error bound condition aiming towards convergence rate analysis of a variable Bregman proximal gradient (VBPG) method for a broad class of nonsmooth and nonconvex optimization problems. It is proved that the aforementioned condition guarantees linear convergence of VBPG, and is weaker than Kurdyka-Lojasiewicz property, weak metric subregularity and Bregman proximal error bound. Along the way, we are able to derive a number of verifiable conditions for level-set subdifferential error bounds to hold, and necessary conditions and sufficient conditions for linear convergence relative to a level set for nonsmooth and nonconvex optimization problems. The newly established results not only enable us to show that any accumulation point of the sequence generated by VBPG is at least a critical point of the limiting subdifferential or even acritical point of the proximal subdifferential with a fixed Bregman function in each iteration, but also provide a fresh perspective that allows us to explore inner-connections among many known sufficient conditions for linear convergence of various first-order methods.

math.OC↗

arXiv2020

MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction

Click-through rate (CTR) prediction is a critical task in online advertising systems. Existing works mainly address the single-domain CTR prediction problem and model aspects such as feature interaction, user behavior history and contextual information. Nevertheless, ads are usually displayed with natural content, which offers an opportunity for cross-domain CTR prediction. In this paper, we address this problem and leverage auxiliary data from a source domain to improve the CTR prediction performance of a target domain. Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad. In order to effectively leverage news data for predicting CTRs of ads, we propose the Mixed Interest Network (MiNet) which jointly models three types of user interest: 1) long-term interest across domains, 2) short-term interest from the source domain and 3) short-term interest in the target domain. MiNet contains two levels of attentions, where the item-level attention can adaptively distill useful information from clicked news / ads and the interest-level attention can adaptively fuse different interest representations. Offline experiments show that MiNet outperforms several state-of-the-art methods for CTR prediction. We have deployed MiNet in UC Toutiao and the A/B test results show that the online CTR is also improved substantially. MiNet now serves the main ad traffic in UC Toutiao.

cs.IR↗

arXiv2020

A First-Order Primal-Dual Method for Nonconvex Constrained Optimization Based On the Augmented Lagrangian

Nonlinearly constrained nonconvex and nonsmooth optimization models play an increasingly important role in machine learning, statistics and data analytics. In this paper, based on the augmented Lagrangian function we introduce a flexible first-order primal-dual method, to be called nonconvex auxiliary problem principle of augmented Lagrangian (NAPP-AL), for solving a class of nonlinearly constrained nonconvex and nonsmooth optimization problems. We demonstrate that NAPP-AL converges to a stationary solution at the rate of o(1/\sqrt{k}), where k is the number of iterations. Moreover, under an additional error bound condition (to be called VP-EB in the paper), we further show that the convergence rate is in fact linear. Finally, we show that the famous Kurdyka- Lojasiewicz property and the metric subregularity imply the afore-mentioned VP-EB condition.

math.OC↗