检索结果-内蒙古大学图书馆

Adversarial Neural Machine Translation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wu, Lijun Xia, Yingce Zhao, Li Tian, Fei Qin, Tao Lai, Jianhuang Liu, Tie-Yan School of Data and Computer Science Sun Yat-sen University University of Science and Technology of China Microsoft Research Asia Guangdong Key Laboratory of Information Security Technology

In this paper, we study a new learning paradigm for Neural Machine Translation \(NMT\). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of Generative Adversarial Networks \(GANs\), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elab.rately designed Convolutional Neural Network \(CNN\). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English!French and German!English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

A cloud-based taxi trace mining framework for smart city

学校读者我要写书评

暂无评论

A cloud-based taxi trace mining framework for smart city

作者： Liu, Jin Yu, Xiao Xu, Zheng Choo, Kim-Kwang Raymond Hong, Liang Cui, Xiaohui State Key Lab. of Software Engineering Computer School Wuhan University Wuhan China Third Research Institute of Ministry of Public Security Shanghai China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX United States School of Information Technology and Mathematical Science University of South Australia AdelaideSA Australia School of Information Management Wuhan University Wuhan China International School of Software Wuhan University Wuhan China

As a well-known field of big data applications, smart city takes advantage of massive data analysis to achieve efficient management and sustainable development in the current worldwide urbanization process. An important problem in smart city is how to discover frequent trajectory sequence pattern and cluster trajectory. To solve this problem, this paper proposes a cloud-based taxi trajectory pattern mining and trajectory clustering framework for smart city. Our work mainly includes (1) preprocessing raw Global Positioning System trace by calling the Baidu API Geocoding;(2) proposing a distributed trajectory pattern mining (DTPM) algorithm based on Spark;and (3) proposing a distributed trajectory clustering (DTC) algorithm based on Spark. The proposed DTPM algorithm and DTC algorithm can overcome the high input/output overhead and communication overhead by adopting in-memory computation. In addition, the proposed DTPM algorithm can avoid generating redundant local trajectory patterns to significantly improve the overall performance. The proposed DTC algorithm can enhance the performance of trajectory similarity computation by transforming the trajectory similarity calculation into AND and OR operators. Experimental results indicate that DTPM algorithm and DTC algorithm can significantly improve the overall performance and scalab.lity of trajectory pattern mining and trajectory clustering on massive taxi trace data. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

关键词： Clustering algorithms

Deep User Modeling for Content-based Event Recommendation in Event-based Social Networks

学校读者我要写书评

暂无评论

Deep User Modeling for Content-based Event Recommendation in...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Zhibo Wang Yongquan Zhang Honglong Chen Zhetao Li Feng Xia Jiangsu Key Lab. of Big Data Security & Intelligent Processing NJUPT P. R. China School of Cyber Science and Engineering Wuhan University P. R. China College of Information and Control Engineering China University of Petroleum P. R. China College of Information Engineering Xiangtan University P. R. China School of Software Dalian University of Technology P. R. China

ISBN: (纸本)9781538641293

Event-based social networks (EBSNs) are the newly emerging social platforms for users to publish events online and attract others to attend events offline. The content information of events plays an important role in event recommendation. However, the content-based approaches in existing event recommender systems cannot fully represent the preference of each user on events since most of them focus on exploiting the content information from events' perspective, and the bag-of-words model, commonly used by them, can only capture word frequency but ignore word orders and sentence structure. In this paper, we shift the focus from events' perspective to users' perspective, and propose a Deep User Modeling framework for Event Recommendation (DUMER) to characterize the preference of users by exploiting the contextual information of events that users have attended. Specifically, we utilize convolutional neural network (CNN) with word embedding to deeply capture the contextual information of a user's interested events and build up a user latent model for each user. We then incorporate the user latent model into probabilistic matrix factorization (PMF) model to enhance the recommendation accuracy. We conduct experiments on the real-world dataset crawled from a typical EBSN, ***, and the experimental results show that DUMER outperforms the compared benchmarks.

关键词： Recommender systems Machine learning Social network services Feature extraction Context modeling Conferences Probabilistic logic

Advancing image understanding in poor visibility environments: A collective benchmark study

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Wenhan Yuan, Ye Ren, Wenqi Liu, Jiaying Scheirer, Walter J. Wang, Zhangyang Zhang, Taiheng Zhong, Qiaoyong Xie, Di Pu, Shiliang Zheng, Yuqiang Qu, Yanyun Xie, Yuhong Chen, Liang Li, Zhonghao Hong, Chen Jiang, Hao Yang, Siyuan Liu, Yan Qu, Xiaochao Wan, Pengfei Zheng, Shuai Zhong, Minhui Su, Taiyi He, Lingzhi Guo, Yandong Zhao, Yao Zhu, Zhenfeng Liang, Jinxiu Wang, Jingwen Chen, Tianyi Quan, Yuhui Xu, Yong Liu, Bo Liu, Xin Sun, Qi Lin, Tingyu Li, Xiaochuan Lu, Feng Gu, Lin Zhou, Shengdi Cao, Cong Zhang, Shifeng Chi, Cheng Zhuang, Chubin Lei, Zhen Li, Stan Z. Wang, Shizheng Liu, Ruizhe Yi, Dong Zuo, Zheming Chi, Jianning Wang, Huan Wang, Kai Liu, Yixiu Gao, Xingyu Chen, Zhenyu Guo, Chang Li, Yongzhou Zhong, Huicai Huang, Jing Guo, Heng Yang, Jianfei Liao, Wenjuan Yang, Jiangang Zhou, Liguo Feng, Mingyue Qin, Likun Wangxuan Institute of Computer Technology Peking University Beijing100080 China Department of Computer Science and Engineering Texas A&M University TX77843 United States State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Department of Computer Science and Engineering University of Notre Dame Notre DameIN46556 United States Department of Mechanical Engineering Zhejiang University Hangzhou310027 China Hikvision Research Institute Hangzhou310051 China Mtlab Meitu Inc. Beijing100080 China Insitute of Information Science Beijing Jiaotong University Beijing100044 China Department of Computer Science and Technology Tongji University Shanghai201804 China XPENGMOTORS Beijing China School of Computer Science and Engineering at South China University of Technology Guangzhou510006 China Tencent AI Lab Shenzhen518000 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Northeastern University Shenyang110819 China Nanyang Technological University Singapore639798 Big Data Center State Grid Corporation of China Beijing China Winsense Inc. Beijing100080 China University of Chinese Academy of Sciences Beijing100049 China Department of Informatics Technical University of Munich Garching85748 Germany Institute of Microelectronics Chinese Academy of Sciences Beijing100190 China China Electric Power Research Institute Beijing100031 China Westlake University Hangzhou310024 China Department of Computer Science Durham University Durham United Kingdom Australian National University ActonACT0200 Australia Sunway-AI Co. Ltd Zhuhai China Chinese Academy of Sciences R&D Center for Internet of Things Wuxi214200 China

Existing enhancement methods are empirically expected to help the high-level end computer vision task: however, that is observed to not always be the case in practice. We focus on object or face detection in poor visibility enhancements caused by bad weathers (haze, rain) and low light conditions. To provide a more thorough examination and fair comparison, we introduce three benchmark sets collected in real-world hazy, rainy, and lowlight conditions, respectively, with annotated objects/faces. We launched the UG2+challenge Track 2 competition in IEEE CVPR 2019, aiming to evoke a comprehensive discussion and exploration about whether and how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios. To our best knowledge, this is the first and currently largest effort of its kind. Baseline results by cascading existing enhancement and detection models are reported, indicating the highly challenging nature of our new data as well as the large room for further technical innovations. Thanks to a large participation from the research community, we are able to analyze representative team solutions, striving to better identify the strengths and limitations of existing mindsets as well as the future directions. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

Digital image splicing detection based on Markov features in QDCT and QWT domain

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Ruxin Lu, Wei Xiang, Shijun Zhao, Xianfeng Wang, Jinwei School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China College of Information Science and Technology Jinan University Guangzhou510632 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

Image splicing detection is of fundamental importance in digital forensics and therefore has attracted increasing attention recently. In this paper, a color image splicing detection approach is proposed based on Markov transition probability of quaternion component separation in quaternion discrete cosine transform (QDCT) domain and quaternion wavelet transform (QWT) domain. Firstly, Markov features of the intra-block and inter-block between block QDCT coefficients are obtained from the real part and three imaginary parts of QDCT coefficients respectively. Then, additional Markov features are extracted from luminance (Y) channel in quaternion wavelet transform domain to characterize the dependency of position among quaternion wavelet subband coefficients. Finally, ensemble classifier (EC) is exploited to classify the spliced and authentic color images. The experiment results demonstrate that the proposed approach can outperforms some state-of-the-art methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Discrete cosine transforms

Image Processing Operations Identification via Convolutional Neural Network

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Chen, Bolin Li, Haodong Luo, Weiqi School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China College of Information Engineering Shenzhen University Shenzhen518052 China

—In recent years, image forensics has attracted more and more attention, and many forensic methods have been proposed for identifying image processing operations. Up to now, most existing methods are based on hand crafted features, and just one specific operation is considered in their methods. In many forensic scenarios, however, multiple classification for various image processing operations is more practical. Besides, it is difficult to obtain effective features by hand for some image processing operations. In this paper, therefore, we propose a new convolutional neural network (CNN) based method to adaptively learn discriminative features for identifying typical image processing operations. We carefully design the high pass filter bank to get the image residuals of the input image, the channel expansion layer to mix up the resulting residuals, the pooling layers, and the activation functions employed in our method. The extensive results show that the proposed method can outperform the currently best method based on hand crafted features and three related methods based on CNN for image steganalysis and/or forensics, achieving the state-of-the-art results. Furthermore, we provide more supplementary results to show the rationality and robustness of the proposed model. Copyright © 2017, 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

Journal of Communications and information Networks 2017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 UniversityGuangzhou 510006China College of Information Science and Technology Jinan UniversityGuangzhou 510632China School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510006China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen UniversityGuangzhou 510006China

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

Anti-forensics of camera identification and the triangle test by improved fingerprint-copy attack

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Li, Haodong Luo, Weiqi Rao, Quanquan Huang, Jiwu School of Electronics and Information Technology Sun Yatsen University Guangzhou China School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yatsen University Guangzhou China College of Information Engineering Shenzhen University Shenzhen China

The fingerprint-copy attack aims to confuse camera identification based on sensor pattern noise. However, the triangle test shows that the forged images undergone fingerprint-copy attack would share a non-PRNU (Photo-response nonuniformity) component with every stolen image, and thus can detect fingerprint-copy attack. In this paper, we propose an improved fingerprint-copy attack scheme. Our main idea is to superimpose the estimated fingerprint into the target image dispersedly, via employing a block-wise method and using the stolen images randomly and partly. We also develop a practical method to determine the strength of the superimposed fingerprint based on objective image quality. In such a way, the impact of non-PRNU component on the triangle test is reduced, and our improved fingerprint-copy attack is difficultly detected. The experiments evaluated on 2,900 images from 4 cameras show that our scheme can effectively fool camera identification, and significantly degrade the performance of the triangle test simultaneously. Copyright © 2017, The Authors. All rights reserved.

关键词： Cameras

A SVM-based EEG signal analysis: An auxiliary therapy for tinnitus 1

学校读者我要写书评

暂无评论

8th International Conference on Brain Inspired Cognitive Systems, BICS 2016

作者： Li, Pei-Zhen Li, Juan-Hui Wang, Chang-Dong School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

ISBN: (数字)9783319496856

ISBN: (纸本)9783319496849

Tinnitus is a kind of auditory disease characterized by an ongoing conscious perception of a sound in the absence of any external sound source. It is a common symptom for which no effective treatment exists. Though many non-invasive functional imaging modalities have been rapidly developed and applied to this field, yet, whether the EEG signal can be utilized to distinguish tinnitus patients from normal populations has not been investigated. In the present study, we perform a binary classification based on EEG signal to distinguish tinnitus patients from normal populations. In this study, 22 subjects are involved in the experiment with 15 of them being tinnitus patients and the others being normal controls. The collected EEG signals are preprocessed in frequency domain and well represented as features that depict each subject. Then the linear support vector machine is applied to classify the subjects. Satisfactory results have been achieved, where the accuracy of the classification could reach 90.91% in spite of the undeniable fact that the collected EEG signals contain noises. Accordingly, the present study reveals that the EEG signals can be utilized to distinguish tinnitus patients from normal populations, which could be regarded as an auxiliary therapy in tinnitus. © Springer International Publishing AG 2016.

关键词： Support vector machines