检索结果-内蒙古大学图书馆

Discriminative feature encoding for intrinsic image decomposition

Computational Visual Media 2023年第3期9卷 597-618页

作者： Zongji Wang Yunfei Liu Feng Lu Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518000China

Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image *** work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high *** focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input *** achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding *** define feature distribution divergence to efficiently separate the feature vectors of different intrinsic *** feature distributions are also constrained to fit the real ones through a feature distribution *** addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image *** method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent *** results indicate that our proposed network structure can outperform the existing state-of-the-art.

关键词： intrinsic image decomposition deep learning feature distribution data refinement

来源：评论

学校读者我要写书评

暂无评论

Force modeling for tooth preparation in a dental training system

引用

virtual reality 2008年第3期12卷 125-136页

作者： Liu, Guanyang Zhang, Yuru Townsend, William T. State Key Lab. of Virtual Reality Technology and System Beihang University Beijing China Robotics Institute School of Mechanical Engineering and Automation Beihang University Beijing China Barrett Technology Inc. Boston MA United States

Feedback force is very important for novices to simulate tooth preparation by using the haptic interaction system (dental training system) in a virtual environment. In the process of haptic simulation, the fidelity of generated forces by a haptic device decides whether the simulation is successful. A force model computes feedback force, and we present an analytical force model to compute the force between a tooth and a dental pin during tooth preparation. The force between a tooth and a dental pin is modeled in two parts: (1) force to resist human's operation and (2) friction to resist the rotation of the dental engine. The force to resist the human's operation is divided into three parts in the coordinates that are constructed on the bottom center of the dental pin. In addition, we also consider the effects of dental-pin type, tooth stiffness, and contact geometry in the force model. To determine the parameters of the force model, we construct a measuring system by using machine vision and a force/torque sensor to track the human's operations and measure the forces between the dental pins and teeth. Based on the measuring results, we construct the relation between the force and the human's operation. The force model is implemented in the prototype of a dental training system that uses the Phantom as the haptic interface. Dentists performing virtual operations have confirmed the fidelity of feedback force. © Springer-Verlag London Limited 2008.

关键词： Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

A component-based aircraft instrument rapid modeling tool

A component-based aircraft instrument rapid modeling tool

引用

作者： Li, Fang-Wen Shen, Xu-Kun State Key Lab of Virtual Reality Technology and Systems School of Computer Science Beihang University Beijing 100191 China

Component-based software reuse and development is considered to be the best way to improve the efficiency and quality of development. To meet the demands of aircraft instrument exhibition in an aviation virtual library, we present a modeling and simulation tool for cockpit instruments on component methods, achieving display functionality and providing a visual interaction platform in the aviation virtual library. For the rapid model construction and reuse of virtual library resources, we classify entities in the cockpit into several categories by their behavior, and design a template for each category to describe its attributes. This efficiently reduces the modeling cycle, and thus largely helps users to take advantage of the library resource. © 2010 Zhejiang University and Springer-Verlag Berlin Heidelberg.

关键词： computer software reusability

来源：评论

学校读者我要写书评

暂无评论

Rapid modeling for large scale anhui-styled architectures

Rapid modeling for large scale anhui-styled architectures

引用

2012 International Conference on systems and Informatics, ICSAI 2012

作者： Xue, Feng Wang, Xiaotao School of Computer Science and Information Hefei University of Technology Hefei 230009 China State Key Lab of Virtual Reality Technology and System Beihang University Beijing 100191 China

ISBN: (纸本)9781467301992

To construct Anhui-Styled Architecture (ASA) models rapidly and automatically, we proposed an automatic modeling method by analyzing the basic structure of ASA in-depth. Firstly, we built modules' database, composition rule database and repository database of ASA. Then, we translated each module of architecture into a node of graph and traverse these nodes using Breadth-First Traversal(BFS) algorithm of Graph to get descript document of single building. Finally, large scale scene of ASA were constructed automatically by combine the descript document and large scale ground scenes. Experimental results show that our method is rapid and effective for constructing ASA models. © 2012 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Integrating a weighted-average method into the random walk framework to generate individual friend recommendations

引用

science China(Information sciences) 2017年第11期60卷 43-64页

作者： Jibing GONG Xiaoxia GAO Hong CHENG Jihui LIU Yanqing SONG Mantang ZHANG Yi ZHAO School of Information Science and Engineering Yanshan University The Key Lab for Computer Virtual Technology and System Integration Yanshan University State Key Lab of Mathematical Engineering and Advanced Computing Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong

Friend recommendation is a fundamental service in both social networks and practical applications,and is influenced by user behaviors such as interactions, interests, and activities. In this study, we first conduct in-depth investigations on factors that affect recommendation results. Next, we design Friend++, a hybrid multi-individual recommendation model that integrates a weighted average method(WAM) into the random walk(RW) framework by seamlessly employing social ties, behavior context, and personal information. In Friend++, the first plus signifies recommending a new friend through network features, while the second plus stands for using node features. To verify our method, we conduct experiments on three social datasets crawled from the Sina microblog system(Weibo). Experimental results show that the proposed method significantly outperforms six baseline methods in terms of recall, precision, F1-measure, and MAP. As a final step, we describe a case study that demonstrates the scalab.lity and universality of our method. Through discussion, we reach a meaningful conclusion: although common interests are more important than user activities in making recommendations, user interactions may be the most important factor in finding the most appropriate potential friends.

关键词： multi-individual friend recommendation architecture behavior context analysis Intimacy degree random walk framework social networks

来源：评论

学校读者我要写书评

暂无评论

Internet-wide multi-party tele-immersion framework for remote 3D collab.ration

Internet-wide multi-party tele-immersion framework for remot...

引用

IEEE International Symposium on VR Innovation

作者： Zhou, Zhong Chen, Xiuwen Zhang, Lin Chang, Xuefeng State Key Lab. of Virtual Reality Technology and Systems Beihang University Beijing 100191 China School of Computer Science and Technology Beihang University Beijing 100191 China

ISBN: (纸本)9781457700538

Tele-presence and tele-immersion systems are growing to be more realistic these years. However, few show practical experiences in Internet wide tele-immersion, especially in acceptable end-to-end delay. We present a framework for multi-party tele-immersion applications that allow remote collab.rative 3D interactions. This framework performs real-time stereo modeling based on the bumblebee cameras. It provides an architecture that supports several tele-immersion nodes to communicate in groups. This paper addresses how to reconstruct, compress and establish the system. The system has been set up in China NGI. Preliminary experiment results show that it's possible to have the delay under 100ms with 320*240 depth map and 640*480 texture images. The framework is also expected to be further extended for interaction with full-body reconstruction. © 2011 IEEE.

关键词： Tele-immersion compression real-time modeling tele-immersion Time intervals Frameworks GRAIN PATTERN compression

来源：评论

学校读者我要写书评

暂无评论

Static object tracking in road panoramic videos

Static object tracking in road panoramic videos

引用

IEEE Internaitonal Conference on Multimedia Information Processing and Retrieval

作者： Zhou, Zhong Niu, Ben Ke, Chen Wu, Wei State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9780769542171

In panoramic videos, the object movement between adjacent side images leads to deformation and discontinuity, which makes the traditional video tracking approaches insufficient. An effective static object tracking algorithm is proposed in this paper to resolve the tracking problems from the deformation and discontinuity in cubic panorama. The algorithm extends the relevant side images with boundary consistency, and then conducts a background eliminated mean-shift algorithm to track objects on the extended images. Experiment results show that the algorithm can track static objects correctly in reasonable situations in real-time. © 2010 IEEE.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

引用

2010 International Conference on Educational and Information technology, ICEIT 2010

作者： Hao, Senshen Jiao, Jian Xia, Chunhe Li, Xiaojian Yao, Shan State Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beihang University Beijing China Beijing Key Laboratory of Network Technology School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781424480340

In order to effectively deal with large-scale attacks on computer networks, computer Network Defense (CND) policy refinement based on descriptive language is wildly used. However, it's very difficult to figure out the semantic discrepancies between the measures and the predefined policy after the calculation with symbols by computers. A new method is presented to solve the discordance of semantic between the measures and the predefined policy automatically. Based on the establishment of the ontology of CND policy and measure (CNDPM), the CND policy and measure semantic similarity analysis model (CNDPMSSAM) is established, and then the termination of the two main components of CNDPMSSAM are proofed by the putdown automaton, and the prototype system of CNDPMSSAM is implemented. At last, we validate the validity of this method on analyzing semantic similarity of transferring from computer Network Defense Policy Specification Language (CNDPSL) to Defense Measure Description Language (DMDL) with experiments. © 2010 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Descriptive model of peer-to-peer botnet structures

Descriptive model of peer-to-peer botnet structures

引用

2010 International Conference on Educational and Information technology, ICEIT 2010

作者： Duan, Junfeng Jiao, Jian Xia, Chunhe Yao, Shan Li, Xiaojian State Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beihang University Beijing China Beijing Key Laboratory of Network Technology School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781424480340

Peer-to-peer (P2P) Botnets, which are more resilient and robust than centralized botnets, have emerged as the peer-to-peer technology evolves. Better understanding of this new phenomenon will help researchers develop detection and mitigation methods. Most of existing work is case study of typical P2P botnets. In this paper, we focus on systematically analyzing structures of P2P botnets. We propose a descriptive model of P2P botnet structures, which consists of features of P2P bot, definitions of structures, and structural properties. Firstly, we detail two key functionalities of P2P bot, command-and-control (C&C) functionality and peer-to-peer (P2P) functionality, and give several features of P2P bot. And then, we define two structures of P2P botnets: C&C structure and P2P structure. To characterize these structures, we propose several properties and corresponding quantitative methods. Finally, we conduct experiments to verify our results. © 2010 IEEE.

关键词： Structural properties

来源：评论

学校读者我要写书评

暂无评论

GPU-based time parallel cache simulator

GPU-based time parallel cache simulator

引用

2010 IEEE Youth Conference on Information, Computing and Telecommunications, YC-ICT 2010

作者： Ma, Junjie Wan, Han Gao, Xiaopeng Long, Xiang State Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beihang University Xueyuan Rd. 37 100191 Beijing China

ISBN: (纸本)9781424488841

We present the design of time parallel trace-driven cache simulation for the purpose of evaluating different cache architectures. Due to the long simulation cycles, traditional sequential simulation methods are no longer practical. An obvious way to achieve fast parallel simulation is time parallel. It splits the whole trace into small slices which are assigned to parallel processors for concurrent simulation. In this paper, we introduce a novel time parallel multi-configuration simulation on single pass method. It exploits time partitioning as the main sources of parallelism and takes the full advantage of the computational capability offered by the Compute Unified Device Architecture (CUDA) on the GPU. Our experimental results demonstrate that the cache simulator based on GPU platform gains 1.91x performance improvement compared to traditional serial algorithm. © 2010 IEEE.

关键词： Graphics processing unit

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：