检索结果-内蒙古大学图书馆

2011 International Conference on Computer Science and Education, CSE 2011

作者： Yuan, Yuan Fanping, Zeng Guanmiao, Zhu Chaoqiang, Deng Neng, Xiong Department of Computer University of Science and Technology of China China Anhui Province Key Lab. of Software in Computing and Communication Hefei Anhui China

ISBN: (纸本)9783642224171

Testing is a critical activity to find software errors. And choosing an effective test suite is the key problem in software testing area. Program invariant, as an attribute of program, can record the implementation state of test case very well and reveal the coverage of program data. In this paper, we integrate adaptive random testing and invariant technology, and present a new method which makes full use of the feedback information of program invariant and invalid case suite to generate the next case. Experiment results show that, compared with other similar methods, running for the same time, our method can achieve higher coverage and faster convergence speed. © 2011 Springer-Verlag.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

A new boundary treatment method for SPH and application in fluid simulation

A new boundary treatment method for SPH and application in f...

引用

3rd International Conference on Information and computing, ICIC 2010

作者： Song, Bo Dong, Lanfang School of Computer Science and Technology USTC Hefei China Anhui Province Key Lab. of Software in Computing and Communication China

ISBN: (纸本)9780769540474

Appropriate dealing with boundary conditions is very important for SPH. Current boundary treatment methods like boundary force method, ghost particle method and virtual boundary layer method, when dealing with complex boundaries, they will have to compute much on putting external particles. For resolving this problem, we propose a new method assuming part of boundary surface instead of external particles, called effective force surface, directly repels the internal particles which approach sufficiently close. We call this new method EFS method. It is implemented in the SPH model for simulating fluid in rabbit-type cup and dam-breaking. In the former case, liquid flows vividly and no internal particles penetrate boundaries. In the latter case, the result is similar to existing result. The experimental results show that EFS method can effectively and precisely deal with complex boundary conditions. © 2010 IEEE.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Eye localization from infrared thermal images

Eye localization from infrared thermal images

引用

1st IAPR TC3 Workshop on Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Wang, Shangfei Shen, Peijia Liu, Zhilei Key Lab. of Computing and Communication Software of Anhui Province School of Computer Science and Technology University of Science and Technology of China HeFei AnHui 230027 China

ISBN: (纸本)9783642370809

By using the knowledge of facial structure and temperature distribution, this paper proposes an automatic eye localization method from infrared thermal images. A facial structure consisting of 15 sub-regions is proposed to extract Haar-like features. Eight classifiers are learned from the features selected by Adaboost algorithm for left and right eye, respectively. A vote strategy is used to find the most likely eyes. Experimental results on the NVIE and Equinox databases show the effectiveness of our approach. © 2013 Springer-Verlag.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Models of parallel computation :a survey and classification

引用

中国高等学校学术文摘·计算机科学 2007年第2期1卷 156-165页

作者： ZHANG Yunquan CHEN Guoliang SUN Guangzhong MIAO Qiankun Laboratory of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100080China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100080China Anhui Province-MOST Key Co-Lab of High Performance Computing and Its Applications Department of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230027China

In this paper,the state-of-the-art parallel computational model research is *** will introduce various models that were developed during the past *** to their targeting architecture features,especially memory organization,we classify these parallel computational models into three *** models and their characteristics are discussed based on three generations *** believe that with the ever increasing speed gap between the CPU and memory systems,incorporating non-uniform memory hierarchy into computational models will become *** the emergence of multi-core CPUs,the parallelism hierarchy of current computing platforms becomes more and more *** this complicated parallelism hierarchy in future computational models becomes more and more important.A semi-automatic toolkit that can extract model parameters and their values on real computers can reduce the model analysis complexity,thus allowing more complicated models with more parameters to be *** memory and hierarchical parallelism will be two very important features that should be considered in future model design and research.

关键词： parallel computational models hierarchicalmemory hierarchical parallelism three generations memorymodel

来源：评论

学校读者我要写书评

暂无评论

Precisely reconstruct porous media model based on synchrotron radiation slice images

Precisely reconstruct porous media model based on synchrotro...

引用

2009 International Conference on Computational Intelligence and software Engineering, CiSE 2009

作者： Song, Bo Dong, Lanfang Lu, Detang Anhui Province Key Lab of Software in Computing and Communication School of Computer Science and Technology USTC Hefei China Institute of Engineering and Science Software USTC Hefei China

ISBN: (纸本)9781424445073

In this paper a method for precisely reconstructing porous media three-dimensional model based on slice images is proposed. It first processes the original slice images, then uses 3D seed filling algorithm to find all pores based on the constructed spatial data, finally uses the modified marching cubes algorithm based on bounding box technology to render material skeletons and pores. Associating with the porous media flow specific application, a novel invalid pore removing method is proposed. The final reconstructed model shows that our method can precisely reconstruct the pore network and recover the pore shape. It also can identify the pores which meet spatial scale threshold conditions. Comparison of running time between the original marching cubes algorithm and the modified marching cubes algorithm is given. It shows that due to the bounding box technology the running time of modified marching cubes algorithm is shorten greatly when the pores are far away from each other. ©2009 IEEE.

关键词： Porous materials

来源：评论

学校读者我要写书评

暂无评论

software Backdoor Analysis Based on Sensitive Flow Tracking and Concolic Execution

引用

Wuhan University Journal of Natural Sciences 2016年第5期21卷 421-427页

作者： XU Xin WANG Jiajie CHENG Shaoyin ZHANG Tao JIANG Fan School of Computer Science and Technology University of Science and Technology of China Hefei 230027 Anhui China China Information Technology Security Evaluation Center Beijing 100085 China Anhui Province Key Lab of Software in Computing and Communication Hefei 230026 Anhui China

In order to effectively detect and analyze the backdoors this paper introduces a method named Backdoor Analysis based on Sensitive flow tracking and Concolic Execution（BASEC）.BASEC uses sensitive flow tracking to effectively discover backdoor behaviors, such as stealing secret information and injecting evil data into system, with less false negatives. With concolic execution on predetermined path, the backdoor trigger condition can be extracted and analyzed to achieve high accuracy. BASEC has been implemented and experimented on several software backdoor samples widespread on the Internet, and over 90% of them can be detected. Compared with behavior-based and system-call-based detection methods, BASEC relies less on the historical sample collections, and is more effective in detecting software backdoors, especially those injected into software by modifying and recompiling source codes.

关键词： software backdoor detection data flow tracking concolic execution malware detection

来源：评论

学校读者我要写书评

暂无评论

Low-Resolution Face Recognition Enhanced by High-Resolution Facial Images 17

Low-Resolution Face Recognition Enhanced by High-Resolution ...

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Wang, Haihan Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province China University of Science and Technology of China Anhui Robot Technology Standard Innovation Base China

ISBN: (纸本)9798350345445

Despite recent advances in high-resolution (HR) face recognition, recognizing identities from low-resolution (LR) facial images remains challenging due to the absence of facial shape and detail. Current research focuses solely on reducing the distribution discrepancy between the HR and LR embeddings from the output layer, rather than thoroughly investigating the superiority of HR facial images for improved performance. In this paper, we propose a novel low-resolution face recognition method enhanced by the guidance of high-resolution facial images in both feature map space and embedding space. Specifically, in feature map space, the similarity constraint across the multilayer feature maps is adopted to align the intermediate features of facial images. Then we introduce multiple generators to recover HR images from extracted feature maps and utilize the reconstructed loss to supplement the missing facial details in LR images. In embedding space, we propose a supervised auxiliary contrastive loss to encourage the paired HR and LR embedding from the same class to be pulled together, whereas those from different classes are pushed apart. The one-to-many matching strategy and the adaptive weight adjustment strategy are applied to make the network adapt to the inputs of different resolutions. Experiments on four benchmark datasets with both synthesized and realistic LR facial images demonstrate the superiority of the proposed method to state-of-the-art. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation with Shape Aware Loss 17

Human Pose Estimation with Shape Aware Loss

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Fang, Lin Wang, Shangfei University of Science and Technology of China Key Lab of Computing and Communication Software of Anhui Province China University of Science and Technology of China Anhui Robot Technology Standard Innovation Base China

ISBN: (纸本)9798350345445

Although the mean square error (mse) of heatmap is an intuitive loss for heatmap-based human pose estimation, the joints localization accuracy may not be improved when heatmap mse reduces. In this paper, we show that a great cause for such misalignment is the unnecessary requirement from heatmap mse on the irrelevant Gaussian parameter, i.e. maximum. The coordinate prediction is precise as long as the probability distribution held by the predicted heatmap is a well-shaped Gaussian distribution and has the same center as the ground truth. However, heatmap mse unnecessarily requires the Gaussian distribution to hold the same maximum as the ground truth. Correspondingly, we introduce mse on the image gradients of the target and predicted heatmap (referred to as gradmap mse) to focus on the shape of the heatmap. Combining heatmap and gradmap mse, we propose a simple yet effective Shape Aware Loss (SAL) method. Being model-agnostic, our method can benefit various existing models. We apply SAL to the three latest network architectures and obtain performance improvements for all of them. Comparisons of the visualized predicted heatmaps further prove the effectiveness of the proposed method. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Three dimensional stratum modeling and a fast algorithm for arbitrary cutting based on half-edge structure

Three dimensional stratum modeling and a fast algorithm for ...

引用

2009 International Conference on Computational Intelligence and software Engineering, CiSE 2009

作者： Xi, Liu Dong, Lanfang Lu, Detang Hefei China Anhui Province Key Lab of Software in Computing and Communication School of Computer Science and Technology USTC Hefei China Institute of Engineering and Science Software USTC Hefei China

ISBN: (纸本)9781424445073

The three dimensional stratum modeling provides important basis of analysis and policy-making in areas such as Geophysics, Petroleum, Minerals, Urban construction and so on. In this paper, we firstly propose a general flow of three dimensional stratum modeling, then research stratum partition algorithm and reconstruct the surface of three dimensional stratum model (3DSM), finally program the module of the simulation and visualization of 3DSM, and propose a fast algorithm for arbitrary cutting based on half-edge structure. The result shows that the algorithm performs real-time, and the reconstructed model of it is perfect. The algorithm has general applicability in entity cutting, it can be used in 3DSM, medical treatment, city planning and other similar areas. ©2009 IEEE.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Unpaired Multimodal Facial Expression Recognition 15th

Unpaired Multimodal Facial Expression Recognition

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Xia, Bin Wang, Shangfei Key Lab of Computing and Communication Software of Anhui Province School of Computer Science and Technology University of Science and Technology of China Hefei China Anhui Robot Technology Standard Innovation Base Hefei China

ISBN: (纸本)9783030695408

Current works on multimodal facial expression recognition typically require paired visible and thermal facial images. Although visible cameras are readily available in our daily life, thermal cameras are expensive and less prevalent. It is costly to collect a large quantity of synchronous visible and thermal facial images. To tackle this paired training data bottleneck, we propose an unpaired multimodal facial expression recognition method, which makes full use of the massive number of unpaired visible and thermal images by utilizing thermal images to construct better image representations and classifiers for visible images during training. Specifically, two deep neural networks are trained from visible and thermal images to learn image representations and expression classifiers for two modalities. Then, an adversarial strategy is adopted to force statistical similarity between the learned visible and thermal representations, and to minimize the distribution mismatch between the predictions of the visible and thermal images. Through adversarial learning, the proposed method leverages thermal images to construct better image representations and classifiers for visible images during training, without the requirement of paired data. A decoder network is built upon the visible hidden features in order to preserve some inherent features of the visible view. We also take the variability of the different images’ transferability into account via adaptive classification loss. During testing, only visible images are required and the visible network is used. Thus, the proposed method is appropriate for real-world scenarios, since thermal imaging is rare in these instances. Experiments on two benchmark multimodal expression databases and three visible facial expression databases demonstrate the superiority of the proposed method compared to state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： Infrared imaging

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：