检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wang, Guojun Wu, Jian Tian, Bin Teng, Siyu Chen, Long Cao, Dongpu The State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Data and Computer Science Sun Yat-Sen University Guangdong Guangzhou510275 China The Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point-the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://***/wangguojun2018/CenterNet3d. Copyright © 2020, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Snap and find: Deep discrete cross-domain garment image retrieval

arXiv

引用

arXiv 2019年

作者： Luo, Yadan Wang, Ziwei Huang, Zi Yang, Yang Lu, Huimin School of Information Technology and Electrical Engineering University of Queensland BrisbaneQLD4072 Australia School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Department of Mechanical and Control Engineering Kyushu Institute of Technology Japan

With the increasing number of online stores, there is a pressing need for intelligent search systems to understand the item photos snapped by customers and search against largescale product databases to find their desired items. However, it is challenging for conventional retrieval systems to match up the item photos captured by customers and the ones officially released by stores, especially for garment images. To bridge the customer- and store- provided garment photos, existing studies have been widely exploiting the clothing attributes (e.g., black) and landmarks (e.g., collar) to learn a common embedding space for garment representations. Unfortunately they omit the sequential correlation of attributes and consume large quantity of human labors to label the landmarks. In this paper, we propose a deep multi-task cross-domain hashing termed DMCH, in which cross-domain embedding and sequential attribute learning are modeled simultaneously. Sequential attribute learning not only provides the semantic guidance for embedding, but also generates rich attention on discriminative local details (e.g., black buttons) of clothing items without requiring extra landmark labels. This leads to promising performance and 306× boost on efficiency when compared with the state-of-the-art models, which is demonstrated through rigorous experiments on two public fashion datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

A TextCNN Based Approach for Multi-label Text Classification of Power Fault Data

A TextCNN Based Approach for Multi-label Text Classification...

引用

IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)

作者： Qiang Zhang Rongrong Zheng Ziyan Zhao Bo Chai Jiangui Li Artificial Intelligence on Electric Power System State Grid Corporation Joint Laboratory (GEIRI) Global Energy Interconnection Research Institute Co. Ltd Beijing China State Grid Information & Telecommunication Co. Ltd School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (数字)9781728160245

ISBN: (纸本)9781728160252

With the increasing number of power terminal devices in power systems, fault diagnosis based on textual fault data has become a challenging task. Classification technology plays an important role in power system fault diagnosis. In this paper, we propose a TextCNN based approach to multi-label text classification for analyzing fault text data of power terminal devices. First, the main category labels of faults and failure were constructed. The dataset was preprocessed for feature representation. Next, we adopted the TextCNN based model for multi-label classification of power fault texts. The experimental results show that the proposed method is better than the typical multi-label classification models for power fault text multi-label classification. The constructed label categories were also experimentally evaluated, and these labels reflect the main types of power faults and failure.

关键词： Text categorization Internet of Things Power system faults Feature extraction Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Face Anti-Spoofing Using Handcrafted and Deep Network Features

A New Approach for Face Anti-Spoofing Using Handcrafted and ...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Das, Polash Kumar Hu, Bin Liu, Chang Cui, Kaixin Ranjan, Prabhat Xiong, Gang School of Electronic and Information Engineering South China University of Technology Guangzhou China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China College of Computer Science Sichuan University Chengdu China Cloud Computing Center Chinese Academy of Science Dongguan China

ISBN: (纸本)9781728128535

In biometrics, face recognition methods are achieving momentum with recent progress in the computer vision(CV). Face recognition is widely used in the identification of an individual's identity. Unfortunately, in recent research work has revealed this face biometrics system is unprotected to spoofing attacks using by very low price instrument such as printed 2D photos attack, 3D masking attack and taking videos using smart devices (reply attack). Therefore, a Liveness Attack Detection (LAD) approach is needed to improve the high-quality security of face recognition system. Most of the earlier worked LAD methods for face anti-spoofing methods have highlight on using the handcrafted features, which are developed by expert knowledge of researcher. As example Gabor filter, Histogram of Oriented Gradients, local ternary pattern, and the Local Binary Pattern. Because of that, the extracted features consider limited factors of the problem, yielding a capture accuracy that is very low and changes with the point of presentation in attack face images. The deep learning method has developed in the computer vision research community, which is proven to be suitable for automatically training. In this article, we approach to mix or combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection. The handcrafted features were based on LBP analysis. We examine the features information from the brightness and the chrominance channels using LBP descriptor. In deep features, we present an approach based on pre-trained convolutional neural network VGG-16 model using static features to recognize video and printed(2D) photo attacks. By attaching this two types of image features on our dataset and public databases, we get good results to identify real and attack images feature, called hybrid features, which has better discrimination ability to understand spoofing image feature. © 2019 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Kernel-Induced label propagation by mapping for semi-supervised classification

arXiv

引用

arXiv 2019年

作者： Zhang, Zhao Jia, Lei Zhao, Mingbo Liu, Guangcan Wang, Meng Yan, Shuicheng School of Computer Science and Technology Soochow University Suzhou215006 China Department of Electronic Engineering City University of Hong Kong Kowloon Hong Kong School of Information and Control Nanjing University of Information Science and Technology Nanjing China School of Computer and Information Hefei University of Technology Hefei China Department of Electrical and Computer Engineering National University of Singapore Singapore

— Kernel methods have been successfully applied to the areas of pattern recognition and data mining. In this paper, we mainly discuss the issue of propagating labels in kernel space. A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space. The essence of Kernel-LP is to perform joint label propagation and adaptive weight learning in a transformed kernel space. That is, our Kernel-LP changes the task of label propagation from the commonly-used Euclidean space in most existing work to kernel space. The motivation of our Kernel-LP to propagate labels and learn the adaptive weights jointly by the assumption of an inner product space of inputs, i.e., the original linearly inseparable inputs may be mapped to be separable in kernel space. Kernel-LP is based on existing positive and negative LP model, i.e. the effects of negative label information are integrated to improve the label prediction power. Also, Kernel-LP performs adaptive weight construction over the same kernel space, so it can avoid the tricky process of choosing the optimal neighborhood size suffered in traditional criteria. Two novel and efficient out-of-sample approaches for our Kernel-LP to involve new test data are also presented, i.e., (1) direct kernel mapping and (2) kernel mapping-induced label reconstruction, both of which purely depend on the kernel matrix between training set and testing set. Owing to the kernel trick, our algorithms will be applicable to handle the high-dimensional real data. Extensive results on real datasets demonstrate the effectiveness of our approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Opacity of Nondeterministic Transition Systems: A (Bi)Simulation Relation Approach

Opacity of Nondeterministic Transition Systems: A (Bi)Simula...

引用

作者： Zhang, Kuize Yin, Xiang Zamani, Majid ACCESS Linnaeus Center School of Electrical Engineering KTH Royal Institute of Technology Stockholm10044 Sweden Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China Computer Science Department University of Colorado Boulder BoulderCO80309 United States

In this paper, we propose several opacity-preserving (bi)simulation relations for nondeterministic transition systems (NTSs) in terms of initial-state opacity, current-state opacity, K-step opacity, and infinite-step opacity. We also show how one can leverage quotient constructions to compute such relations. As a result, although the opacity verification problem for infinite NTSs is generally undecidable, if one can find such an opacity-preserving relation from an infinite NTS to a finite one, the (lack of) opacity of the infinite NTS can be easily verified over the finite one, which is decidable. © 1963-2012 IEEE.

关键词： Opacity

来源：评论

学校读者我要写书评

暂无评论

Multi-person remote heart-rate measurement from human faces - a CNN based approach

Multi-person remote heart-rate measurement from human faces ...

引用

IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin)

作者： Thomas Pursche Marcel Walz Roland Clauß Robert Roth Bernd Tibken Reinhard Möller School of Electrical Information and Media Engineering Automatic Control University of Wuppertal Wuppertal Germany Faculty of Electrical Information and Media Engineering Automatic Control University of Wuppertal Wuppertal Germany Faculty of Electrical Information and Media Engineering Automation/Computer Science University of Wuppertal Wuppertal Germany

The conventional heart rate measurement techniques using electrocardiogram, wrist belts and so on, are attached with some disadvantages like discomfort, irritation of the skin and even more. From this starting point various video based heart rate measurement techniques were developed in the last years. All of these techniques use video data of the human faces to extract information to estimate the heart rate of the person in front of the camera. Most of them work with the detection of minimal changes in the color spectrum of the recorded video data. With these extracted information and multiple concluding steps, they are able to estimate the heart rate of the person sitting in front of the camera. All of these approaches have some big disadvantages, they are only able to measure the heart rate of one person - and in a small number of cases up to three persons. So the main objective of this work is to adapt and enhance existing research approaches of processing visual biological signals. The focus is set on the design and deployment of a new system, which is able to process visual data as well as detect and localize human faces by using artificial neural networks and calculate each individuals heart rate from the processed data's information. For the first time in this research area, different scenarios with more than three observed participants are being analyzed to calculate the heart rate for each of them separately. It will be shown that by using the applied technical architecture and technologies, it is possible to deploy a comparable and qualitatively competitive system. In addition, the implemented system proves the feasibility of processing various faces' signals and calculating the respective heart rates simultaneously within an acceptable range of tolerance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

swMD: Performance Optimizations for Molecular Dynamics Simulation on Sunway Taihulight

swMD: Performance Optimizations for Molecular Dynamics Simul...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Kun Li Shigang Li Bei Wang Yifeng Chen Yunquan Zhang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing Department of Computer Science ETH Zurich HCST Key Lab at School of EECS Peking University Beijing

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Molecular dynamics is an extensively utilized computational tool for solids, liquids and molecules simulation. Currently, much research on molecular dynamics simulation focuses on simplifying forces or parallelizing tasks to reduce the overheads of forces computation. However, the molecular dynamics simulation still remains challenging since the communication and neighbor list construction are time-consuming in the existing algorithm. In this paper, we propose a swMD optimization strategy including a new communication mode called ghost communication to reduce superfluous communication overheads and an innovative neighbor list algorithm to improve the construction efficiency of it. Moreover, we accelerate computation by utilizing many-core resources on Sunway Taihulight and present an auto-tuning Producer-Consumer pairing algorithm to make neighbor list construction happen in fast register communication. Compared to traditional methods, swMD optimization strategy obtains a maximal 82.2% and an average of 79.4% performance improvement. We also evaluate the scalability up to 266,240 cores and the results demonstrate the high efficiency of swMD optimization strategy on communication, computation and neighbor list construction respectively.

关键词： Heuristic algorithms computer architecture Computational modeling Microprocessors Program processors Registers Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Poster: Tancreator: A tangible tool for children to create augmented reality games

Poster: Tancreator: A tangible tool for children to create a...

引用

2018 Joint ACM International Conference on Pervasive and Ubiquitous Computing, UbiComp 2018 and 2018 ACM International Symposium on Wearable computers, ISWC 2018

作者： Jin, Qiao Wang, Danli Sun, Fang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China School of Computer and Information Technology Liaoning Normal University Dalian China

ISBN: (纸本)9781450359665

In this paper, we present TanCreator, a tangible authoring tool which facilitates children to create games based on Augmented Reality (AR) and sensor technologies. Combining AR elements and sensors in games bridges virtual world with realistic surroundings closely together, providing more joyful and intuitive creating experiment for children. Children could boost their creativity via creating their own maze games in daily life with paper tokens and sensors. It is also great training for children's motor skills such as hand-eye coordination. © 2018 Copyright is held by the owner/author(s).

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Fuzzy control for maximum power-point tracking of a photovoltaic system 7

Fuzzy control for maximum power-point tracking of a photovol...

引用

7th International Conference on Systems and control, ICSC 2018

作者： Safia, Z. Ben Allouch, M. Harrabi, N. Bahloul, M. Chaabane, M. Aitouche, A. National Engineering School of SFAX Tunisia CRIStAL Research Center in Computer Science Signal and Automatic Control of Lille University of Lille France

ISBN: (纸本)9781538685372

This paper proposes a new T-S fuzzy method to deal with the power tracking problem of the power generating systems. First, a dynamic model of the PV system is developed which is subsequently converted into a Takagi-Sugeno (TS) model. Then, after leading to this exact model, a fuzzy controller is designed to obtain the MPP even during the variation of the climatic conditions. Based on the T-S fuzzy model, the fuzzy maximum power point tracking controller is designed by constructing fuzzy gain state feedback controller and an optimal reference model for the optimal PV output voltage, which corresponds actually to maximum power point (MPP).The controller gains are obtained by solving a set of linear matrix inequalities (LMIs). Finally, simulation results are given to illustrate the optimal tracking performance of the proposed fuzzy controller even in the case of abrupt changing climatic conditions. © 2018 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：