检索结果-内蒙古大学图书馆

ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Ning Long, Yongchao Zou, Changqing Niu, Qun Pan, Li Wu, Hefeng School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology University of Maryland Shanghai Jiao Tong University Guangdong University of Foreign Studies WINNER Technology

We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density Map Estimator (DME) then generates high-quality density maps. With the attention-aware training scheme and multi-scale deformable convolutional scheme, the proposed ADCrowdNet achieves the capability of being more effective to capture the crowd features and more resistant to various noises. We have evaluated our method on four popular crowd counting datasets (ShanghaiTech, UCF CC 50, WorldEXPO’10, and UCSD) and an extra vehicle counting dataset TRANCOS, and our approach beats existing state-of-the-art approaches on all of these datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

Block Markov superposition transmission with pulse position modulation over free-space optical links

学校读者我要写书评

暂无评论

通信与信息网络学报（英文） 2018年第4期2卷 142-150页

作者： Jinshun Zhu Shancheng Zhao Xiao Ma School of Electronics and Information Technology Sun Yat-sen University Guangzhou 510006 China College of Information Science and Technology Jinan University Guangzhou 510632 China School of Data and Computer Science Sun Yat-sen University Guangzhou 510006 China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou 510006 China

In FSO (Free-Space Optical) communications,performance of the communication systems is severely degraded by atmospheric *** (Pulse Position Modulation) is widely used in FSO communication systems owing to its high power *** this paper,we present a combination of the BMST (Block Markov Superposition Transmission) technique and the PPM scheme to improve the reliability of the transmission over FSO *** on analyzing an equivalent system,a lower bound on the bit-error-rate of the proposed scheme is *** simulations are performed which show that the BMST-PPM system performs well under a wide range of turbulence conditions and improves the performance of the basic *** results also show that,the performance of the system with the sliding-window detection/decoding algorithm matches well with the lower bound in the low-error-rate region.

关键词： BMST FSO gamma-gamma channel model iterative detection/decoding algorithm PPM

Fog-assisted multi-user swipt networks: Local computing or offloading

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Haina Xiong, Ke Fan, Pingyi Zhong, Zhangdui Letaief, Khaled Ben School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing100044 China National Laboratory for Information Science and Technology Department of Electronic Engineering Tsinghua University Beijing100084 China State Key Lab of Rail Traffic Control and Safety Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications Beijing Jiaotong University Beijing100044 China Clear Water Bay Hong Kong

This paper investigates a fog computing-assisted multi-user simultaneous wireless information and power transfer (SWIPT) network, where multiple sensors with power splitting (PS) receiver architectures receive information and harvest energy from a hybrid access point (HAP), and then process the received data by using local computing mode or fog offloading mode. For such a system, an optimization problem is formulated to minimize the sensors' required energy while guaranteeing their required information transmissions and processing rates by jointly optimizing the multi-user scheduling, the time assignment, the sensors' transmit powers and the PS ratios. Since the problem is a mixed integer programming (MIP) problem and cannot be solved with existing solution methods, we solve it by applying problem decomposition, variable substitutions and theoretical analysis. For a scheduled sensor, the closed-form and semi-closedform solutions to achieve its minimal required energy are derived, and then an efficient multi-user scheduling scheme is presented, which can achieve the suboptimal user scheduling with low computational complexity. Numerical results demonstrate our obtained theoretical results, which show that for each sensor, when it is located close to the HAP or the fog server (FS), the fog offloading mode is the better choice;otherwise, the local computing mode should be selected. The system performances in a frame-by-frame manner are also simulated, which show that using the energy stored in the batteries and that harvested from the signals transmitted by previous scheduled sensors can further decrease the total required energy of the sensors. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy harvesting

Improving Fast Segmentation With Teacher-student Learning Oct 20

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xie, Jiafeng Shuai, Bing Hu, Jian-Fang Lin, Jingyang Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China Nanyang Technological University Singapore Guangdong Key Laboratory of Information Security Technology Key Laboratory of Machine Intelligence and Advanced Computing MOE

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their application scenarios in practice. Meanwhile, existing fast segmentation models usually fail to obtain satisfactory segmentation accuracies on public benchmarks. In this paper, we propose a teacher-student learning framework that transfers the knowledge gained by a heavy and better performed segmentation network (i.e. teacher) to guide the learning of fast segmentation networks (i.e. student). Specifically, both zero-order and first-order knowledge depicted in the fine annotated images and unlab.led auxiliary data are transferred to regularize our student learning. The proposed method can improve existing fast segmentation models without incurring extra computational overhead, so it can still process images with the same fast speed. Extensive experiments on the Pascal Context, Cityscape and VOC 2012 datasets demonstrate that the proposed teacher-student learning framework is able to significantly boost the performance of student network. Copyright © 2018, The Authors. All rights reserved.

关键词： Image enhancement

A distributed multi-exemplar affinity propagation clustering algorithm based on mapreduce 3

学校读者我要写书评

暂无评论

A distributed multi-exemplar affinity propagation clustering...

3rd IEEE International Conference on Big data Computing Service and Applications, BigdataService 2017

作者： Yang, Yu-Bo Wang, Chang-Dong Lai, Jian-Huang School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9781509063185

Clustering algorithm is one of the fundamental techniques in data mining, which plays a crucial role in various applications, such as pattern recognition, document retrieval, and computer vision. As so far, many effective algorithms have been proposed. Affinity Propagation is an algorithm requires no parameter indicating the number of clusters, which is the most distinguishing advantage compared to the k-means clustering algorithm. Multi-Exemplar Affinity Propagation (MEAP) extends the single-exemplar model to the multi-exemplar model, which could describe the dataset with more complex structure. With the amount of data increasing rapidly, the growing size of dataset makes the clustering problem become more and more challenging. To solve this problem, the parallel computing framework is widely used, such as MapReduce. However, for the MEAP algorithm, it is not a straightforward task to implement the updating of MEAP messages in MapReduce, which without proper design would be time-consuming. In this paper, we propose to utilize the stability of data distribution to apply the MEAP algorithm on the MapReduce platform and develop an efficient Distributed Multi-Exemplar Affinity Propagation (DisMEAP) clustering algorithm by using three MapReduce stages. The experiment results demonstrate that our algorithm can perform well in processing large-scale datasets and could achieve the same accuracy as the original MEAP algorithm. © 2017 IEEE.

关键词： MapReduce

Transmission of Gaussian Source Using Ternary Convolutional Low Density Generator Matrix Codes

学校读者我要写书评

暂无评论

Transmission of Gaussian Source Using Ternary Convolutional ...

International Conference on Communication Systems

作者： Qiaoqiao Wu Meiying Ji Jiachen Sun Xiao Ma School of Data and Computer Science Sun Yat-sen University Guangzhou China School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)9781538678657;9781538678640

In this paper, we propose a new joint source-channel coding (JSCC) scheme to transmit a Gaussian source over an additive white Gaussian noise (AWGN) channel, where the channel input constraint is on energy per source symbol rather than per channel symbol. The JSCC scheme is based on an embedded Lloyd-Max quantizer with adjustable quantization levels and the ternary convolutional low density generator matrix (LDGM) codes, which are easily configurable in the sense that any rational code rate can be achieved without complicated optimization. In our scheme, first, a Gaussian source is quantized into ternary symbols, which can be formatted into different symbol planes according to their contribution to the distortion. Second, the symbol planes are encoded by a ternary convolutional LDGM code, where the relatively important symbol plane is encoded with a lower code rate. Third, the coded sequence is modulated in 3-PAM and then transmitted over the channel. Numerical results show that the proposed scheme performs close to the Shannon limit, and that the distortion can be lowered down by increasing the number of quantization levels.

关键词：

Spatial image steganography based on generative adversarial network

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Jianhua Liu, Kai Kang, Xiangui Wong, Edward K. Shi, Yun-Qing Guangdong Key Lab of Information Security School of Data and Computer Science Sun Yat-Sen University Guangzhou510006 China Department of Computer Science and Engineering New York University Tandon School of Engineering BrooklynNY11201 United States Department of ECE New Jersey Institute of Technology NewarkNJ07102 United States

With the recent development of deep learning on steganalysis, embedding secret information into digital images faces great challenges. In this paper, a secure steganography algorithm by using adversarial training is proposed. The architecture contain three component modules: a generator, an embedding simulator and a discriminator. A generator based on U-NET to translate a cover image into an embedding change probability is proposed. To fit the optimal embedding simulator and propagate the gradient, a function called Tanh-simulator is proposed. As for the discriminator, the selection-channel awareness (SCA) is incorporated to resist the SCA based steganalytic methods. Experimental results have shown that the proposed framework can increase the security performance dramatically over the recently reported method ASDL-GAN, while the training time is only 30% of that used by ASDL-GAN. Furthermore, it also performs better than the hand-crafted steganographic algorithm S-UNIWARD. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

Enhanced ensemble clustering via fast propagation of cluster-wise similarities

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Huang, Dong Wang, Chang-Dong Peng, Hongxing Lai, Jianhuang Kwoh, Chee-Keong College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Ensemble clustering has been a popular research topic in data mining and machine learning. Despite its significant progress in recent years, there are still two challenging issues in the current ensemble clustering research. First, most of the existing algorithms tend to investigate the ensemble information at the object-level, yet often lack the ability to explore the rich information at higher levels of granularity. Second, they mostly focus on the direct connections (e.g., direct intersection or pairwise co-occurrence) in the multiple base clusterings, but generally neglect the multi-scale indirect relationship hidden in them. To address these two issues, this paper presents a novel ensemble clustering approach based on fast propagation of cluster-wise similarities via random walks. We first construct a cluster similarity graph with the base clusters treated as graph nodes and the cluster-wise Jaccard coefficient exploited to compute the initial edge weights. Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information. Specifically, by investigating the propagating trajectories starting from different nodes, a new cluster-wise similarity matrix can be derived by considering the trajectory relationship. Then, the newly obtained cluster-wise similarity matrix is mapped from the cluster-level to the object-level to achieve an enhanced co-association (ECA) matrix, which is able to simultaneously capture the object-wise co-occurrence relationship as well as the multi-scale cluster-wise relationship in ensembles. Finally, two novel consensus functions are proposed to obtain the consensus clustering result. Extensive experiments on a variety of real-world datasets have demonstrated the effectiveness and efficiency of our approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Cluster analysis

Computing integrals involved the gaussian function with a small standard deviation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ma, Yunyun Ma, Yunyun Xu, Yuesheng Xu, Yuesheng School of Computer Science and Network Security Dongguan University of Technology Dongguan523808 China Department of Mathematics and Statistics Old Dominion University NorfolkVA23529 United States School of Data and Computer Science Guangdong Province Key Lab of Computational Science Sun Yat-sen University Guangzhou510275 China

We develop efficient numerical integration methods for computing an integral whose integrand is a product of a smooth function and the Gaussian function with a small standard deviation. Traditional numerical integration methods applied to the integral normally lead to poor accuracy due to the rapid change in high order derivatives of its integrand when the standard deviation is small. The proposed quadrature schemes are based on graded meshes designed according to the standard deviation so that the quadrature errors on the resulting subintervals are approximately equal. The integral in each subinterval is then computed by considering the Gaussian function as a weight function and interpolating the smooth factor of the integrand at the Chebyshev points of the first kind. For a finite order differentiable factor, we design a quadrature scheme having accuracy of a polynomial order and for an infinitely differentiable factor of the integrand, we design a quadrature scheme having accuracy of an exponential order. Numerical results are presented to confirm the accuracy of these proposed quadrature schemes. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistics