检索结果-内蒙古大学图书馆

An Iterative Co-Saliency Framework for RGBD Images

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cong, Runmin Lei, Jianjun Fu, Huazhu Lin, Weisi Huang, Qingming Cao, Xiaochun Hou, Chunping School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Computer Engineering Nanyang Technological University Singapore639798 Singapore Institute for Infocomm Research Ocular Imaging Department Agency for Science Technology and Research Singapore138632 Singapore School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China University of Chinese Academy of Sciences

As a newly emerging and significant topic in computer vision community, co-saliency detection aims at discovering the common salient objects in multiple related images. The existing methods often generate the co-saliency map through a direct forward pipeline which is based on the designed cues or initialization, but lack the refinement-cycle scheme. Moreover, they mainly focus on RGB image and ignore the depth information for RGBD images. In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model. Three schemes are employed in the proposed RGBD co-saliency framework, which include the addition scheme, deletion scheme, and iteration scheme. The addition scheme is used to highlight the salient regions based on intra-image depth propagation and saliency propagation, while the deletion scheme filters the saliency regions and removes the non-common salient regions based on interimage constraint. The iteration scheme is proposed to obtain more homogeneous and consistent co-saliency map. Furthermore, a novel descriptor, named depth shape prior, is proposed in the addition scheme to introduce the depth information to enhance identification of co-salient objects. The proposed method can effectively exploit any existing 2D saliency model to work well in RGBD co-saliency scenarios. The experiments on two RGBD cosaliency datasets demonstrate the effectiveness of our proposed framework. Copyright © 2017, The Authors. All rights reserved.

关键词： Iterative methods

Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cong, Runmin Lei, Jianjun Fu, Huazhu Huang, Qingming Cao, Xiaochun Hou, Chunping School of Electrical and Information Engineering Tianjin University Tianjin300072 China Ocular Imaging Department Institute for Infocomm Research Agency for Science Technology and Research Singapore School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100093 China

Co-saliency detection aims at extracting the common salient regions from an image group containing two or more relevant images. It is a newly emerging topic in computer vision community. Different from the most existing co-saliency methods focusing on RGB images, this paper proposes a novel co-saliency detection model for RGBD images, which utilizes the depth information to enhance identification of co-saliency. First, the intra saliency map for each image is generated by the single image saliency model, while the inter saliency map is calculated based on the multi-constraint feature matching, which represents the constraint relationship among multiple images. Then, the optimization scheme, namely Cross Label Propagation (CLP), is used to refine the intra and inter saliency maps in a cross way. Finally, all the original and optimized saliency maps are integrated to generate the final co-saliency result. The proposed method introduces the depth information and multi-constraint feature matching to improve the performance of co-saliency detection. Moreover, the proposed method can effectively exploit any existing single image saliency model to work well in co-saliency scenarios. Experiments on two RGBD co-saliency datasets demonstrate the effectiveness of our proposed model. Copyright © 2017, The Authors. All rights reserved.

关键词： Image enhancement

Modularity based community detection with deep learning 25

学校读者我要写书评

暂无评论

Modularity based community detection with deep learning

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Liang, Yang Cao, Xiaochun He, Dongxiao Chuan, Wang Xiao, Wang Weixiong, Zhang State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences China School of Information Engineering Tianjin University of Commerce China School of Computer Science and Technology Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University China Department of Computer Science and Technology Tsinghua University China College of Math and Computer Science Institute for Systems Biology Jianghan University China Department of Computer Science and Engineering Washington University St. Louis United States

Identification of module or community structures is important for characterizing and understanding complex systems. While designed with different objectives, i.e., stochastic models for regeneration and modularity maximization models for discrimination, both these two types of model look for low-rank embedding to best represent and reconstruct network topology. However, the mapping through such embedding is linear, whereas real networks have various nonlinear features, making these models less effective in practice. Inspired by the strong representation power of deep neural networks, we propose a novel nonlinear reconstruction method by adopting deep neural networks for representation. We then extend the method to a semi-supervised community detection algorithm by incorporating pairwise constraints among graph nodes. Extensive experimental results on synthetic and real networks show that the new methods are effective, outperforming most state-of-the-art methods for community detection.

关键词： Deep neural networks

Person re-identification by camera correlation aware feature augmentation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Chen, Ying-Cong Zhu, Xiatian Zheng, Wei-Shi Lai, Jian-Huang School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China Collaborative Innovation Center of High Performance Computing National University of Defense Technology Changsha410073 China Department of Computer Science and Engineering Chinese University of Hong Kong School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Key Laboratory of Machine Intelligence and Advanced Computing Sun Yatsen University Ministry of Education China Guangdong Province Key Laboratory of Information Security China

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coRrelation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state-of

关键词： Cameras

Distributed multi-robot coordination for dynamic perimeter surveillance in uncertain environments

学校读者我要写书评

暂无评论

Distributed multi-robot coordination for dynamic perimeter s...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Alexander Jahn Reza Javanmard Alitappeh David Saldaña Luciano C. A. Pimenta Andre G. Santos Mario F. M. Campos Graduate Program in Electrical Engineering (PPGEE) National Institute of Science and Technology for Cooperative Autonomous Systems Applied to Security and Environment Departamento de Informatica Universidade Federal de Vicosa Computer Science Department Universidade Federal de Minas Gerais Universidade Federal de Minas Gerais Belo Horizonte MG BR

In this work, multiple robots circulate around the boundary of a desired region in order to create a virtual fence. The aim of the this fence is to avoid internal or external agents crossing through the delimited area. In this paper, we propose a distributed technique that allows a team of robots to plan the deformation of the boundary shape in order to escort the safe region from one place to a goal. Our proposal is composed of two parts. First, we present a distributed planning method for the dynamic boundary. We model the resulting plan as a twice differentiable function. Second, we use the obtained function to guide the robot team, where every member uses only local information for the controller. The robots distribute themselves along the time-varying perimeter and patrol around it. We show in simulation how the robots behave in partially/totally unknown environments with static obstacles.

关键词： Shape Robot kinematics Trajectory Planning Robot sensing systems Dynamics

Fast shortest-path queries on large-scale graphs

学校读者我要写书评

暂无评论

Fast shortest-path queries on large-scale graphs

International Conference on Network Protocols

作者： Qiongwen Xu Xu Zhang Jin Zhao Xin Wang Tilman Wolf School of Computer Science Fudan University China Ministry of Education Engineering Research Center of Cyber Security Auditing and Monitoring China Department of Electrical and Computer Engineering University of Massachusetts Amherst USA

ISBN: (纸本)9781509032822

Shortest-path queries on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks (SDN), since SDN controllers need to perform a shortest-path query for every flow. Unlike classic solutions (e.g., Dijkstra's algorithm), high-performance shortest-path query algorithms include two stages: preprocessing and query answering. Despite the improved query answering time, existing two-stage algorithms are still extremely time-consuming in preprocessing large-scale graphs. In this paper, we propose an efficient shortest-path query algorithm, called BBQ, which reduces the running time of both stages via tree decomposition. BBQ constructs a distance oracle in a bottom-top-bottom manner, which significantly reduces preprocessing time over existing algorithms. In addition, BBQ can answer batch queries in bulk by traversing the decomposed tree instead of executing separate queries. Our experimental results show that BBQ outperforms state-of-the-art approaches by orders of magnitude for the running time of the preprocessing stage. Meanwhile, BBQ also offers remarkable acceleration for answering batches of queries. As a result, SDN controllers that use BBQ can sustain 1.1-27.9 times higher connection request rates.

关键词： Phase locked loops Conferences Protocols Acceleration Runtime Time complexity

Provable multiple replication data possession with full dynamics for secure cloud storage

学校读者我要写书评

暂无评论

Provable multiple replication data possession with full dyna...

作者： Zhang, Yafang Ni, Jianbing Tao, Xiaoling Wang, Yong Yu, Yong Big Data Research Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada College of Information and Communication Guilin University of Electronic Technology Guilin541004 China Guangxi Cloud Security and Cloud Service Engineering Research Center Guilin University of Electronic Technology Guilin541004 China

Cloud storage has been gaining tremendous popularity among individuals and corporations because of its low maintenance cost and on-demand services for the clients. To improve the availability and the reliability of critical data, storing multiple replicas on multiple servers is a commonly used strategy. Currently, several provable data possession (PDP) protocols for multiple replicas of dynamic data have been proposed to ensure the integrity of outsourced multi-copy data, but the efficiency of these protocols on verifying multiple replicas one by one is not satisfactory. In this paper, we propose a provable multiple replication data possession protocol with full dynamics, named MR-DPDP. In MR-DPDP, we utilize a novel authenticated data structure called Merkle hash tree with rank to support both full dynamic data updates and efficient integrity verification. In addition, our construction with RSA signature can support both variable-sized file blocks and public verification. Through security proof and performance evaluation, we demonstrate that MR-DPDP not only is sound but also incurs less communication overhead when updating data blocks as well as verifying a proof of the integrity of multiple replicas. Copyright © 2015 John Wiley & Sons, Ltd.

关键词： Cloud storage

Toward Optimal Secure Distributed Storage Systems with Exact Repair

学校读者我要写书评

暂无评论

Toward Optimal Secure Distributed Storage Systems with Exact...

作者： Tandon, Ravi Amuru, Saidhiraj Clancy, Thomas Charles Buehrer, Richard Michael Department of Electrical and Computer Engineering University of Arizona TucsonAZ24061 United States Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States Samsung R and D Institute Bangalore560037 India Hume Center for National Security and Technology Virginia Tech BlacksburgVA24061 United States

Distributed storage systems (DSSs) in the presence of an external wiretapper are considered. A DSS is parameterized by (n, k, d), in which the data are stored across n nodes (each with storage capacity α), and must be recoverable by accessing the contents stored on any k out of n nodes. If a node fails, any d ≥ k out of (n-1) nodes help in the repair (regeneration) of the failed node (by sending dβ units of repair data, where β≤ α), so that the data can still be recovered from the DSS. For such a (n, k, d)-DSS, security from the two types of wiretappers is investigated: 1) Type-I (node data) wiretapper, which can read the data stored on any © 2016 IEEE.

关键词： Network coding

On the quantification of the dissolved hydroxyl radicals in the plasma-liquid system using the molecular probe method

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Ma, Yupengxue Gong, Xinning He, Bangbang Li, Xiaofei Cao, Dianyu Li, Junshuai Xiong, Qing Chen, Qiang Chen, Bing Hui Liu, Qing Huo Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Institute of Electromagnetics and Acoustics Department of Electronic Science Xiamen University Xiamen361005 China Department of Chemical and Biochemical Engineering National Engineering Laboratory for Green Productions of Alcohols-Ethers-Esters College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China School of Physical Science and Technology Lanzhou University Lanzhou730000 China State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing400044 China Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States

Hydroxyl (OH) radical is the most important reactive species produced by the plasmaliquid interactions, and the OH in the liquid phase (dissolved OH radical, OHdis) takes effect in many plasma-based applications due to its high reactivity. Therefore, the quantification of the OHdisin the plasma-liquid system is of great importance, and a molecular probe method usually used for the OHdisdetection might be applied. Herein we investigate the validity of using the molecular probe method to estimate the [OHdis] in the plasma-liquid system. Dimethyl sulfoxide is used as the molecular probe to estimate the [OHdis] in an air plasma-liquid system, and the partial OHdisis related to the formed formaldehyde (HCHO) which is the OHdis-induced derivative. The analysis indicates that the true concentration of the OHdisshould be estimated from the sum of three terms: the formed HCHO, the existing OH scavengers, and the OHdisgenerated H2O2. The results show that the measured [HCHO] needs to be corrected since the HCHO destruction is not negligible in the plasma-liquid system. We conclude from the results and the analysis that the molecular probe method generally underestimates the [OHdis] in the plasma-liquid system. If one wants to obtain the true concentration of the OHdisin the plasma-liquid system, one needs to know the destruction behavior of the OHdis-induced derivatives, the information of the OH scavengers (such as hydrated electron, atomic hydrogen besides the molecular probe), and also the knowledge of the OHdisgenerated H2O2. Copyright © 2017, The Authors. All rights reserved.

关键词： Free radicals