检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Cong Liang Shangfei Wang Xiaoping Chen Key Lab of Computing and Communication Software of Anhui Province University of Science and Technology of China Hefei China Anhui Robot Technology Standard Innovation Base University of Science and Technology of China Hefei China

Cloud-based expression recognition from high-resolution facial images may put the subjects’ privacy at risk. We identify two kinds of privacy leakage, the appearance leakage in which the visual appearances of subjects are disclosed and the identity-pattern leakage in which the identity information of subjects is dug out. To address both leakages, we propose privacy-protected facial expression recognition from low-resolution facial images with the help of high-resolution facial images. Specifically, to prevent appearance leakage, we propose to extract identity-invariant representations from downsampled images, from which the visually distinguishable appearances cannot be recovered. To prevent identity-pattern leakage, we propose to eliminate the identity information from the extracted representations by leveraging the disentangled representations of high-resolution images as privileged information. After training, our method can fully capture identity-invariant representations from downsampled images for expression recognition without the requirement of high-resolution samples. These privacy-protected representations can be safely transmitted through the Internet. Experimental results in different scenarios demonstrate that the proposed method protects privacy without significantly inhibiting facial expression recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network Security Evaluation Algorithm Based on Access Level Vectors

Network Security Evaluation Algorithm Based on Access Level ...

引用

The 9th International Conference for Young Computer Scientists(第九届国际青年计算机大会)

作者： Kai Li Naijie Gu Kun Bi Hongzhu Ji Department of Computer Science and Technology University of Science and Technology of China Hefei China 230027 Anhui Province Key Lab. of Computing and Communication Software Hefei China 230027

The attack graph, a typical model-based method, is widely used in the field of network security evaluation. The biggest disadvantage of attack graph method is its exponential growth of the state space. This paper presents an efficient algorithm based on the malefactor's access level vector in every host of the network to generate a reduced attack graph in polynomial compute complexity. In this algorithm, the state space is reduced to O(nm) , where n is the number of nodes and m is the whole number of vulnerabilities in the network. We also present a standard method to generate attack templates from the vulnerabilities.

关键词： Network security evaluation attack graph access level vector attack template.

来源：评论

学校读者我要写书评

暂无评论

An emotional harmony generation system

An emotional harmony generation system

引用

Congress on Evolutionary Computation

作者： Bin Xu Shangfei Wang Xian Li Key Laboratory of Computing Software of Anhui Province School of Computer Science and Technology University of Science and Technology China Department of Automation University of Science and Technology China

This paper proposes an emotional harmony composition system using a series of predefined rules and interactive genetic algorithm. Two kinds of rules are defined: One is harmony composition rules used for composing harmony and the other is harmony emotion rules which may indicate the mapping between harmonic elements and a specific emotion of either happiness or sadness. Interactive genetic algorithm is applied to incorporate users' subjective perception in the generated harmony. Both subjective and objective experiments are conducted to prove the effectiveness of our approach.

关键词： User interfaces Humans Harmonic analysis Converters Music Genetics Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Implicit curves and surfaces based on BP neural network

引用

Journal of Information and Computational Science 2005年第2期2卷 259-271页

作者： Li, Daolun Lu, Detang Kong, Xiangyang Wu, Gang Laboratory of Software in Computing and Communication of Anhui Province University of Science and Technology of China Hefei 230026 China Institute of Engineering and Science Software University of Science and Technology of China Hefei 230026 China Nanjing University of Finance and Economics Nanjing 210012 China

Neural networks, combined with implicit polynomials, can be employed to represent 2D curves as well as 3D surfaces. The zero-set of a neural network can be used to describe data points constituting a 2D curve or 3D surface. The neural network fitting algorithms developed in this paper aim to reduce the learning time of neural network by selecting the exterior and interior constraint points simultaneously and improve the fitting performance by using the linear transfer function at the output layers. The neural network adopted so far is a multilayer feed-forward type. Simulation results show that the proposed algorithms provide a significant reduction in learning time, and good fitting results. This paper lays the bases of the neural network modeling approach.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Design methods for polymorphic combinational logic circuits based on the Bi-Decomposition approach

arXiv

引用

arXiv 2017年

作者： Li, Zhifang Luo, Wenjian Yue, Lihua Wang, Xufa School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China Anhui Key Laboratory of Software in Computing and Communication University of Science and Technology of China Hefei Anhui230027 China

Polymorphic circuits are a special kind of digital logic components, which possess multiple build-in functions. In different environments, a polymorphic circuit would perform different functions. Evolutionary Algorithms, Binary Decision Diagrams (BDD) and the multiplex method have been adopted to design polymorphic circuits. However, the evolutionary methods face the scalable problem. The BDD method consumes too much gate resource. The polymorphic circuit built by the multiplex method rarely contains polymorphic gates. In this paper, based on the traditional Bi-Decomposition circuit design approach, two methods, *** Poly-Bi-Decomposition method and the TransformationBi-Decomposition method, are proposed for designing polymorphic circuits. The Poly_Bi-Decomposition method can design relatively large and gate-efficient polymorphic circuits with a higher percentage of polymorphic gates. The TransformationBi-Decomposition method can use the traditional circuit design approaches and tools, e.g. Bi-Decomposition, to design polymorphic circuits directly. The experimental results show the good performance of the proposed methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

FACIAL ACTION UNIT RECOGNITION BY RELATION MODELING FROM BOTH QUALITATIVE KNOWLEDGE AND QUANTITATIVE DATA

FACIAL ACTION UNIT RECOGNITION BY RELATION MODELING FROM BOT...

引用

IEEE International Conference on Multimedia and Expo Workshops

作者： Zhen Gao Shangfei Wang Chongliang Wu Jun Wang Qiang Ji Key Lab of Computing and Communication Software of Anhui Province School of Computer Science and Technology University of Science and Technology of China Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute

ISBN: (纸本)9781479947164

In this paper, we propose to capture Action Unit (AU) relations existing in both qualitative knowledge and quantitative data through Credal Networks (CN). Each node of the CN represents an AU label, and the links and probability intervals capture the probabilistic dependencies among multiple AUs. The structure of CN is designed based on prior knowledge. The parameters of CN are learned from both knowledge and ground-truth AU labels. The AU preliminary estimations are obtained by an existing image-driven recognition method. With the learned credal network, we infer the true AU labels by combining the relationships among labels with the previous obtained estimations. Experimental results on the CK+ database and MMI database demonstrate that with complete AU labels, our CN model is slightly better than the Bayesian Network (BN) model, demonstrating that credal sets learned from data can capture uncertainty more reliably;With incomplete and error-prone AU annotations, our CN model outperforms the BN model, indicating that credal sets can successfully capture qualitative knowledge.

关键词： Prior knowledge Credal network AU recognition

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

A low-cost pedestrian-detection system with a single optical camera

A low-cost pedestrian-detection system with a single optical...

引用

作者： Cao, Xian-Bin Qiao, Hong Keane, John IEEE Department of Computer Science and Technology University of Science and Technology of China Hefei 230026 China Anhui Province Key Laboratory of Software in Computing and Communication Hefei 230026 China Laboratory of Complex Systems and Intelligent Science Institute of Automation Chinese Academy of Sciences Beijing 100080 China School of Informatics University of Manchester M60 1QD Manchester United Kingdom University of Manchester M13 9PL Manchester United Kingdom

The ultimate purpose of a pedestrian-detection system (PDS) is to reduce pedestrian-vehicle-related injury. Most such systems tend to adopt expensive sensors, such as infrared devices, in expectation of better performance. In comparison, a low-cost optical-camera-based system has much potential practical value, including a greater detection range, and can easily be trained to detect other objects. However, such low-cost systems are difficult to design (e.g., little original information can be collected, and the scene is very complex). To address these problems, an effective and reliable classifier is needed. The classifier should have a proper structure, its features need to be well selected, and a large number of high-quality samples are necessary for training. In this paper, we present a low-cost PDS which only uses a single optical camera. We design a cascade classifier to achieve an effective and reliable detection. First, our system scans two sequential frames at each zoom scale with a sliding window. Second, with each window, both appearance and motion features are extracted. A well-trained cascade classifier, combining statistical learning with a decomposed support-vector-machine classifier, then determines whether the window contains a human body. At the same time, to provide as much information as possible about the pedestrian, a small-scale weighted template tree trained by a coevolutionary algorithm is adopted to identify each pedestrian's direction, and the distance of each from the vehicle is also provided using an estimation algorithm. During the training procedure, we select key features by using the AdaBoost algorithm and a large number of high-quality samples. Experimental results demonstrate that the system is suitable for pedestrian detection in city traffic: The detection speed is more than 10 ft/s, the detection rate reaches 80%, and the false positive rate is no more than 0.3‰. © 2008 IEEE.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

IPRAR: A DFG-based approach to instruction clustering for multicluster VLIW DSP processor with SIMD structure

引用

Journal of Computational Information Systems 2014年第3期10卷 1257-1269页

作者： Yang, Yangzhao Gu, Naijie Zhao, Zeng Ren, Kaixin School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Anhui Province Key Laboratory of Computing and Communication Software Hefei 230027 China USTC and Loongson Technology Associated Laboratory Institute of Advanced Technology University of Science and Technology of China Hefei 230027 China

Modern Very Long Instruction (VLIW) DSP can improve performance by using instruction-level parallelism (ILP) and obtain better parallelism through instruction clustering. The essence of clustering is resource allocation. Traditional clustering method assumes that one instruction can only be assigned to a certain cluster, which is inapplicable to the architecture with SIMD structure. To address this issue, this paper presents IPRAR, a novel instruction clustering algorithm for the features of SIMD structure based on DFG. Due to considering the features of SIMD structure, IPRAR can be implemented on BWDSP100 with satisfactory. Besides, IPRAR can make the load of cluster more balanced and minimize the intercluster communication overload. Finally, numerous experiment results show that the IPRAR has an average of 7-10% performance improvement compared to the traditional methods. © 2014 Binary Information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing BLAS2 for a decoupled access/execute architecture processor

引用

Journal of Computational Information Systems 2014年第3期10卷 1231-1241页

作者： Zhao, Zeng Gu, Naijie Yang, Yangzhao Ren, Kaixin School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China USTC and Loongson Technology Associated Laboratory Institute of Advanced Technology University of Science and Technology of China Hefei 230027 China Anhui Province Key Laboratory of Computing and Communication Software Hefei 230027 China

Basic Linear Algebra Subroutines (BLAS) is a widely used basic mathematical library for high-performance computing. It has a great impact on the performance of supercomputers. This paper focuses on memory accessing optimization for the level-2 library of BLAS (BLAS2) based on Godson-3B chips. The key contribution of this work is proposing several methods to make full use of the Godson-3B's hardware features, as well as to improve the performance of memory access. GEMV, the kernel function of BLAS2, is selected to demonstrate the optimization methods for Godson-3B. Using Single Instruction Multiple Data (SIMD) instructions, Direct Register Access (DRA) and Direct Cache Access (DCA) of Godson-3B, two optimization algorithms for GEMV are introduced in this paper. Experiments show that the best computing performance of the optimized GEMVs on Godson-3B is more than 1.8Gops, which is far superior to that of other versions. While the test scale of GEMVs is greater than the size of L2-cache, its average performance exceeds UBLAS and OpenBlas, the two most famous optimized BLAS libraries for GODSON, by more than 60% and 20% respectively. © 2014 Binary Information Press.

关键词： Supercomputers

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：