检索结果-内蒙古大学图书馆

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Li, Yuhui Xu, Jiucheng Zhang, Yifan Zhang, Chunjie Yin, Hongsheng Lu, Hanqing School of Computer and Information Engineering Henan Normal University Xinxiang China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Science Beijing China School of Computer and Control Engineering University of China Academy of Sciences Beijing China China University of Mining and Technology Xuzhou China

ISBN: (纸本)9783319276700

Spatial pyramid matching (SPM) model is an extension of the bagof-visual words (BoW) model for local feature encoding. It firstly partitions the image into increasingly fine sub-regions, and then concatenates the histograms within each sub-region. However, the SPM model does not consider the spatial information differences between sub-regions explicitly. To make use of this information, we exploit a novel descriptor called spatial difference. In the process of promoting the performance of image classification, this descriptor is mainly used to concatenate the histograms of bag-of-visual words model under spatial pyramid matching framework. Finally, we conduct image classification experiments on several public datasets to demonstrate the effectiveness of the proposed scheme. © Springer International Publishing Switzerland 2016.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Face alignment across large poses: A 3D solution

Face alignment across large poses: A 3D solution

引用

2016 IEEE Conference on computer Vision and Pattern Recognition, CVPR 2016

作者： Zhu, Xiangyu Lei, Zhen Liu, Xiaoming Shi, Hailin Li, Stan Z. Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China Department of Computer Science and Engineering Michigan State University United States

ISBN: (纸本)9781467388511

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45°), lacking the ability to align faces in large poses up to 90°. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

引用

23rd International Conference on Pattern Recognition, ICPR 2016

作者： Wang, Jin Zhu, Junkang Wang, Zheng Gao, Changxin Sang, Nong Rui, Huang National Key Laboratory of Science and Technology on Multispectral Information Processing School of Automation Huazhong University of Science and Technology China School of Physics Nanjing University China School of Computer Wuhan University China School of Science and Engineering Chinese University of Hong Kong Shenzhen China

ISBN: (纸本)9781509048472

Person re-identification, aiming to match a specific person among non-overlapping cameras, has attracted plenty of attention in recent years. It can be regarded as a visual retrieval task, namely given a query person image, ranking all gallery images according to their similarities to the query. Conventionally, this similarity function is learnt by forcing intra-distances to be small while inter-distances to be large, which are referred to as individual similarity constraints. In this paper, we propose to learn the similarity function by taking into account of both individual similarity constraints and contextual similarity constraints. The context of a query is defined as its k-nearest neighbors in the gallery. We argue that if two images are from the same person, apart from the visual likeness between them, denoted as the individual similarity, they should also possess similar k-nearest neighbors in the gallery, denoted as the contextual similarity. Motivated by this assumption, we propose a new Contextual Similarity Regularized Metric Learning (CSRML) method for person re-identification. The contextual similarity regularization term forces two images of the same person to share similar context. Both individual and contextual similarity constraints are encoded by a large margin logistic loss function and the final problem is solved by the stochastic gradient descent algorithm. Experiments on the challenging VIPeR and CUHK01 datasets show that our approach achieves very competitive performance. © 2016 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A hierarchical urban network control with integration of demand balance and traffic signal coordination

引用

IFAC-PapersOnLine 2016年第3期49卷 31-36页

作者： Zhou, Zhao Lin, Shu Xi, Yugeng Li, Dewei Zhang, Jun Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control Information Processing Ministry of Education of China Shanghai200240 China School of Computer and Control Engineering University of Chinese Academy of Science Beijing100049 China Joint Institute of UM-SJTU Shanghai Jiao Tong University Shanghai200240 China

This paper concerns the integration of demand balance control and traffic flow coordination control in a hierarchical framework for complex urban traffic networks. At the first level, a complex traffic network is first partitioned into several subnetworks. The traffic dynamics in each subnetwork is modeled by utilizing the concept of Macroscopic Fundamental Diagram (MFD), which relates the network-wide space-mean flow and the number of vehicles at the aggregated level. This model aims at designing a demand balance model predictive controller (MPC), which can improve the internal flow inside the subnetwork by regulating the input flows from outside. At the second level, based on a more detailed traffic flow model, the signal timings of all intersections for each subnetwork are determined by a flow coordination MPC controller, which aims at distributing the number of vehicles in each subnetwork as homogeneously as possible. The effectiveness of the proposed approach is investigated via simulation under different scenarios on a hypothetical urban traffic network, and the performance is compared with other control strategies. © 2016

关键词： Street traffic control

来源：评论

学校读者我要写书评

暂无评论

Learning with only multiple instance positive bags

Learning with only multiple instance positive bags

引用

2016 International Joint Conference on Neural Networks, IJCNN 2016

作者： Wang, Zhigang Zhao, Zengshun Zhang, Changshui Computer and Communication Engineering School Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology China Key Laboratory of Computer Vision and System Tianjin University of Technology Ministry of Education China College of Electronics Communication and Physics Shandong University of Science and Technology China Automation Department Tsinghua University State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology China

ISBN: (纸本)9781509006199

In traditional multiple instance learning (MIL), both positive and negative bags are required to learn a prediction function. However, a high human cost is needed to know the label of each bag - positive or negative. Only positive bags contain our focus (positive instances) while negative bags consist of noise or background (negative instances). So we do not expect to spend too much to label the negative bags. Contrary to our expectation, nearly all existing MIL methods require enough negative bags besides positive ones. In this paper we propose an algorithm called 'Positive Multiple Instance' (PMI), which learns a classifier given only a set of positive bags. So the annotation of negative bags becomes unnecessary in our method. PMI is constructed based on the assumption that the unknown positive instances in positive bags be similar each other and constitute one compact cluster in feature space and the negative instances locate outside this cluster. The experimental results demonstrate that PMI achieves the performances close to or a little worse than those of the traditional MIL algorithms on benchmark and real data sets. However, the number of training bags in PMI is reduced significantly compared with traditional MIL algorithms. © 2016 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Manifold Constrained Low-Rank Decomposition

Manifold Constrained Low-Rank Decomposition

引用

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Chen Chen Baochang Zhang Alessio Del Bue Vittorio Murino Center for Research in Computer Vision (CRCV) University of Central Florida (UCF) State Key Laboratory of Satellite Navigation System and Equipment Technology Shijiazhuang China School of Automation Science and Electrical Engineering Beihang University Beijing China Istituto Italiano di Tecnologia Genova Liguria IT Istituto Italiano di Tecnologia Genova Italy

Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling. However, it is a very challenging problem when the image data contains significant occlusion, noise, illumination variation, and misalignment from rotation or viewpoint changes. We leverage the specific structure of data in order to improve the performance of LRD when the data are not ideal. To this end, we propose a new framework that embeds manifold priors into LRD. To implement the framework, we design an alternating direction method of multipliers (ADMM) method which efficiently integrates the manifold constraints during the optimization process. The proposed approach is successfully used to calculate low-rank models from face images, hand-written digits and planar surface images. The results show a consistent increase of performance when compared to the state-of-the-art over a wide range of realistic image misalignments and corruptions.

关键词： Manifolds Optimization Data models Videos computer vision Matrix decomposition Transmission line matrix methods

来源：评论

学校读者我要写书评

暂无评论

Strategic Air Traffic Flow Management under Uncertainties using Scalable Sampling-based Dynamic Programming and Q-Learning Approaches

Strategic Air Traffic Flow Management under Uncertainties us...

引用

Asian Control Conference

作者： Junfei Xie Yan Wan F. L. Lewis Department of Computer Science Texas A&M University at Corpus Christi Corpus Christi TX Department of Electrical Engineering University of Texas at Arlington Arlington TX State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China UTA Research Institute University of Texas at Arlington Fort Worth Texas USA

ISBN: (纸本)9781509015740;9781509015733

Many Cyber-Physical Systems (CPSs) demonstrate high-dimensional environmental uncertainties that modulate the physical system dynamics and complicate the computational decision-making tasks. As an example, strategic air traffic flow management (ATFM) aims to resolve air traffic congestion through managing traffic flows at a long look-ahead time. The convective weather, a dominant factor of traffic congestion, is very uncertain and significantly complicates the decision-making process. Other uncertainties such as traffic demands further expand the uncertainty space and complicate the design of optimal control solutions that are robust to uncertainties. In this paper, we formulate the strategic ATFM as a stochastic optimal control problem, and use scalable sampling based dynamic programming and Q-learning approaches to address high-dimensional uncertainties. Simulation studies demonstrate the effectiveness of these approaches. These approaches generally apply to CPSs that operate under high-dimensional environmental uncertainties.

关键词： Uncertainty Mathematical model Meteorology Optimal control Dynamic programming Atmospheric modeling Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

Correction to: Predicting drug response of tumors from integrated genomic profiles by deep neural networks

引用

BMC medical genomics 2019年第1期12卷 119页

作者： Yu-Chiao Chiu Hung-I Harry Chen Tinghe Zhang Songyao Zhang Aparna Gorthi Li-Ju Wang Yufei Huang Yidong Chen Greehey Children's Cancer Research Institute University of Texas Health Science Center at San Antonio San Antonio TX 78229 USA. Department of Electrical and Computer Engineering The University of Texas at San Antonio San Antonio TX 78249 USA. Laboratory of Information Fusion Technology of Ministry of Education School of Automation Northwestern Polytechnical University Xi'an 710072 Shaanxi China. Department of Electrical and Computer Engineering The University of Texas at San Antonio San Antonio TX 78249 USA. Yufei.Huang@utsa.edu. Department of Epidemiology and Biostatistics University of Texas Health Science Center at San Antonio San Antonio TX 78229 USA. Yufei.Huang@utsa.edu. Greehey Children's Cancer Research Institute University of Texas Health Science Center at San Antonio San Antonio TX 78229 USA. ChenY8@uthscsa.edu. Department of Epidemiology and Biostatistics University of Texas Health Science Center at San Antonio San Antonio TX 78229 USA. ChenY8@uthscsa.edu.

Following publication of the original article [1], the authors provided an updated funding statement to the article. The updated statement is as follows.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weighted ADMM for Fast Decentralized Network Optimization

Weighted ADMM for Fast Decentralized Network Optimization

引用

作者： Ling, Qing Liu, Yaohua Shi, Wei Tian, Zhi Department of Automation University of Science and Technology of China Hefei230026 China Coordinated Science Laboratory University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Electrical and Computer Engineering George Mason University FairfaxVA22030 United States

In this paper, we propose a weighted alternating direction method of multipliers (ADMM) to solve the consensus optimization problem over a decentralized network. In the proposed algorithm, every node holds its local objective function, exchanges its current iterate with a subset of neighbors, carries on local computation, and eventually reaches an optimal and consensual solution that minimizes the summation of the local objective functions. Compared with the conventional ADMM that is popular in decentralized network optimization, the weighted ADMM is able to reduce the communication cost spent in the optimization process through tuning the weight matrices, which assign beliefs on the neighboring iterates. We first prove convergence and establish linear convergence rate of the weighted ADMM. Second, we maximize the derived convergence speed and obtain the best weight matrices on a given topology. Third, observing that exchanging information with all the neighbors is expensive, we maximize the convergence speed while limit the number of communication arcs. This strategy finds a subset of arcs within the underlying topology to fulfill the optimization task while leads to a favorable tradeoff between the number of iterations and the communication cost per iteration. Numerical experiments demonstrate advantages of the weighted ADMM over its conventional counterpart in expediting the convergence speed and reducing the communication cost. © 1991-2012 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

7.3: Compare Variation of User's EEG Owing to Parallax Cue

引用

SID Symposium Digest of Technical Papers 2018年第S1期49卷

作者： Haichen Hu Danli Wang Kang Yue Xinpan Yang Steve C. Chiu Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China College of Science and Engineering Idaho State University Pocatello America

3D display has become increasingly popular in many fields. It can provide incredible immersion compared with 2D display. There are many researches referring to the change of user about no matter subjective experience or objective physiology signal while watching 3D content. Similarly, in this paper, we study the variation of user’s EEG when the user watched 3D content. However, we only focus on parallax cue and avoid other cues of 3D content by using Random Dot Stereogram(RDS) as visual stimulus. We designed an experiment which asked the subject to watch RDS with nine kinds of parallaxes(0,±0.5,±1.1,±1.3,±1.7). The users watched one RDS for 1 minute and then closed eyes and rest for 1 minute every time. During watching, EEG signal with 30-channel was recorded. The result suggests that significant variation of the user’s EEG data occurred in the Alpha (8–13Hz) and Beta(14–30Hz) frequency band by different parallax’s comparison. And we found not only parallax but also electrode position can impact the user’s EEG data significantly. Accurately, the EEG data has a significant change in six electrodes position in both frequency bands including CZ, PZ, OZ, O2 in international 10–20 system. It means those electrode positions we detect can be regarded as typical positions where we record EEG signal. It will simplify the process of EEG signal acquisition when we need to study the relationship between parallax cue of 3D display and the user further.

关键词： EEG Parallax RDS 3D

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：