检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Jin, Xin Wu, Le Zhao, Geng Li, Xiaodong Zhang, Xiaokun Ge, Shiming Zou, Dongqing Zhou, Bin Zhou, Xinghui Department of Cyber Security Beijing Electronic Science and Technology Institute Beijing100070 China Cetc Big Data Research Institute Co. Ltd. Guiyang Guizhou550018 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China SenseTime Research Beijing100084 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Peng Cheng Laboratory Beijing100191 China

Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a newformula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named DPC-Captions which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MemNetAR: Memory Network with Adversative Relation for Target-Level Sentiment Classification

MemNetAR: Memory Network with Adversative Relation for Targe...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Yiwei Gao Jianwei Niu Xuefeng Liu Kaili Mao Shui Yu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Hangzhou Innovation Research Institute Beihang University School of Computer Science and Cyber Engineering Guangzhou University Guangdong China

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Target-level sentiment classification aims to identify the sentiment of multiple targets in a sentence. Although existing approaches based on neural network have achieved good performance in this task, we find that many approaches tend to give the same predictions for instances that have multiple targets, and this tendency can make a low accuracy for those instances that have different classes for different targets. Based on this observation, we propose MemNetAR, a memory network which can explicitly leverage the adversative relation among multiple targets in a sentence. Specifically, we add an adversative loss to the cross-entropy loss when there are adversative words between targets. The experimental results on public laptop and restaurant datasets prove that our model can improve 0.84% and 0.8% on total test dataset, and improve 2.97% and 2.68% on the dataset consisting of those instances with multiple targets but different classes by leveraging this new adversative information.

关键词： Task analysis Feature extraction Sentiment analysis Portable computers Machine learning Training Predictive models

来源：评论

学校读者我要写书评

暂无评论

keyframe-Based Texture Mapping for RGBD Human Reconstruction

Keyframe-Based Texture Mapping for RGBD Human Reconstruction

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Yishu Heng Chen Wang Yue Qi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beihang University Qingdao Research Institute Qingdao China

ISBN: (纸本)9781538684986;9781538684979

Realistic human model has a wide range of requirements in 3D content creation. A model with high-quality texture map can display human body surface details in low facets which could be toughly represented by geometric mesh. Image-based texture mapping suffers from discontinuities due to geometry inaccuracy, camera pose drifts, and illumination changes. In this paper, we propose a keyframe-based texture map generation method to obtain more desired texture mapping results. Our method firstly acquire the keyframes by performing a spatio-temporal sampling strategy, rather than just sampling keyframes according to time interval. Then, we apply an efficient patch-based optimization to the keyframes to make the texture data in different views alinged with each other. Finally, we generate a texture atlas from the aligned texture and the simplified mesh. Experimental results demonstrate that our method can get realistic human models with low facets and competitive details within short minutes.

关键词： Image reconstruction Cameras Optimization Geometry Solid modeling Image color analysis Face

来源：评论

学校读者我要写书评

暂无评论

A Robust Method for Hands Gesture Recognition from Egocentric Depth Sensor

A Robust Method for Hands Gesture Recognition from Egocentri...

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Ye Bai Yue Qi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beihang University Qingdao Research Institute Qingdao China

ISBN: (纸本)9781538684986;9781538684979

We present a method for robust and accurate hand pose recognition from egocentric depth cameras. Our method combines CNN based hand pose estimation and joint locations based hand gesture recognition. In pose estimation stage, we use a hand geometry prior network to estimate the hand pose. In gesture recognition stage, we defined a hand language which based on a set of pre-define basic propositions, obtained by applying four predicate types to the fingers and palm states. The hand language is used to convert the estimated joint location to hand gesture. Our experimental results indicate that the method enables robust and accurate gesture recognition in self-occlusion environment.

关键词： Bones Thumb Gesture recognition Pose estimation Geometry Joints Kinematics

来源：评论

学校读者我要写书评

暂无评论

Distributed Refinement of Large-Scale 3D Mesh for Accurate Multi-View Reconstruction

Distributed Refinement of Large-Scale 3D Mesh for Accurate M...

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Qing Luo Yao Li Yue Qi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beihang University Qingdao Research Institute Qingdao China

ISBN: (纸本)9781538684986;9781538684979

As the scene of multi-view reconstruction becomes larger, a single machine can no longer satisfy the refinement of 3D mesh in large scenes including mesh simplification, subdivision, smoothness and recovering meaningful details. In this paper, We propose a distributed method to refine a large-scale 3D mesh for accurate multiview reconstruction. First, we divide the initial mesh into blocks directly, which can utilize computing power of each computer. And then we make simplification and subdivision on those blocks, which can reduce mesh's noise and remove redundant vertices, so as to generate a high quality mesh where the difference of the size of each edge is not too large. Next, we propose to split a graph consisting of multiple images in order to minimize the overlapped image data in each block. Finally, we use distributed variational surface refinement algorithm to capture meaningful details of mesh. The experiments on both public large scale data-sets and our very large scale aerial photo sets demonstrate that the proposed distributed method is fast and robust, and is suitable for all kinds of large scene areas.

关键词： Image reconstruction Three-dimensional displays Partitioning algorithms Distributed databases Sparks Image edge detection virtual reality

来源：评论

学校读者我要写书评

暂无评论

Recent advances on HEVC inter-frame coding: From optimization to implementation and beyond

arXiv

引用

arXiv 2019年

作者： Zhang, Yongfei Zhang, Chao Fan, Rui Ma, Siwei Chen, Zhibo Kuo, C.-C. Jay Beijing Key Laboratory of Digital Media School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China China Academy of Electronic and Information Technology Beijing100041 China Institute of Digital Media School of Electronics Engineering and Computer Science Peking University Beijing100871 China University of Science and Technology of China Hefei Anhui230026 China University of Southern California Los AngelesCA90089 United States

High Efficiency Video Coding (HEVC) has doubled the video compression ratio with equivalent subjective quality as compared to its predecessor H.264/AVC. The significant coding efficiency improvement is attributed to many new techniques. Inter-frame coding is one of the most powerful yet complicated techniques therein and has posed high computational burden thus main obstacle in HEVC-based real-time applications. Recently, plenty of research has been done to optimize the inter-frame coding, either to reduce the complexity for real-time applications, or to further enhance the encoding efficiency. In this paper, we provide a comprehensive review of the state-of-the-art techniques for HEVC inter-frame coding from three aspects, namely fast inter coding solutions, implementation on different hardware platforms as well as advanced inter coding techniques. More specifically, different algorithms in each aspect are further subdivided into sub-categories and compared in terms of pros, cons, coding efficiency and coding complexity. To the best of our knowledge, this is the first such comprehensive review of the recent advances of the inter-frame coding for HEVC and hopefully it would help the improvement, implementation and applications of HEVC as well as the ongoing development of the next generation video coding standard. Copyright © 2019, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

WEB3D-Based APP Generator for VR Exhibition

WEB3D-Based APP Generator for VR Exhibition

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Xueguang Xie Xuehao Wang Min Zhao Jian Su Shuai Li Guojun Chen China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Qingdao China Qingdao Research Institute Beihang University Qingdao China

ISBN: (纸本)9781538684986;9781538684979

We design a WEB3D-based application generator for VR exhibition, which provides management and edit functions for VR scenes and models. Because our work is based on WEB3D and B/S architecture, user can make VR application instantly and easily. We develop the web editor by UE4, so it can get an excellent rendering performance and preview and modify model in real time. In this development process, we solve many problems caused by packaging UE4 to HTML5, such as loading local files, web page jumping problems. In order to help users creating VR scenes quickly, we provide some common templates. Therefore, this work is considered as an efficient tool for nontechnical users to create applications of VR exhibition.

关键词： Conferences virtual reality Visualization

来源：评论

学校读者我要写书评

暂无评论

Evaluate concurrent state machine of SysML model with Petri net

Evaluate concurrent state machine of SysML model with Petri ...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jieshi Shen Lei Liu Xiaoguang Hu Guofeng Zhang Jin Xiao State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing P R China Beijing Electro-Mechanical Engineering Institute Beijing PR China

systems Modeling Language (SysML) is the extension and development of Unified Modeling Language (UML) in the field of system engineering. It is gradually applied to the architecture analysis and design of complex hardware and software systems. SysML provides a visual modeling approach in the field of systems engineering that enables a clear explanation of the system's design. However, SysML uses a semi-formal description method [1], which uses natural language to describe the constraints and detailed semantics of systems. This leads to the fact that SysML itself lacks the accurate semantics and it is difficult to conduct rigorous semantic analysis and model quality verification directly. This paper provides a method that transforms SysML state machine into Petri net in propose of overcoming the difficulty of analysis and verification under the dynamic behavior of the state machine. This method also can avoid the formal verification of SysML directly.

关键词： Petri nets Unified modeling language Solid modeling Semantics Analytical models virtual reality

来源：评论

学校读者我要写书评

暂无评论

Word2Cluster: A New Multi-Label Text Clustering Algorithm with an Adaptive Clusters Number

Word2Cluster: A New Multi-Label Text Clustering Algorithm wi...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Kaili Mao Jianwei Niu Xuefeng Liu Shui Yu Longbo Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Hangzhou Innovation Research Institute Beihang University School of Computer Science and Cyber Engineering Guangzhou University Guangdong China China aerospace science and industry corporation China

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Text clustering has been widely used in many Natural Language Processing (NLP) applications such as text summarization and news recommendation. However, most of the current algorithms need to predefine a clustering number, which is difficult to obtain. Moreover, the mutli-label clustering is useful in multiple clustering tasks in many applications, but related works are rarely available. Although several studies have attempted to solve above two problems, there is a need for methods that can solve the two issues simultaneously. Therefore, we propose a new text clustering algorithm called Word2Cluster. Word2Cluster can automatically generate an adaptive number of clusters and support multi-label clustering. To test the performance of Wrod2Cluster, we build a Chinese text dataset, Hotline, according to real world applications. To evaluate the clustering results better, we propose an improved evaluation method based on basic accuracy, precision and recall for multi-label text clustering. Experimental results on a Chinese text dataset (Hotline) and a public English text dataset (Reuters) demonstrate that our algorithm can achieve better F1-measure and runs faster than the state-of- the-art baselines.

关键词： Clustering algorithms Biological system modeling Merging Task analysis Computer science Technological innovation Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Load Sharing Behavior of Star Gearing Reducer for Geared Turbofan Engine

引用

Chinese Journal of Mechanical Engineering 2017年第4期30卷 796-803页

作者： Shuai MO Yidu ZHANG Qiong WU Feiming WANG Shigeki MATSUMURA Haruo HOUJOH State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China School of Mechanical Engineering & Automation Beihang University Beijing 100191 China AVIC Shenyang Engine Design & Research Institute Shenyang 100015 China Precision and Intelligence Laboratory Tokyo Institute of Technology Yokohama 226-8503 Japan

Load sharing behavior is very important for power-split gearing system, star gearing reducer as a new type and special transmission system can be used in many industry fields. However, there is few literature regarding the key multiple-split load sharing issue in main gearbox used in new type geared turbofan engine. Further mechanism anal- ysis are made on load sharing behavior among star gears of star gearing reducer for geared turbofan engine. Compre- hensive meshing error analysis are conducted on eccentricity error, gear thickness error, base pitch error, assembly error, and bearing error of star gearing reducer respectively. Floating meshing error resulting from meshing clearance variation caused by the simultaneous floating of sun gear and annular gear are taken into account. A refined mathematical model for load sharing coefficient calculation is established in consideration of different meshing stiffness and support- ing stiffness for components. The regular curves of load sharing coefficient under the influence of interactions, single action and single variation of various component errors are obtained. The accurate sensitivity of load sharing coefficienttoward different errors is mastered. The load sharing coef- ficient of star gearing reducer is 1.033 and the maximum meshing force in gear tooth is about 3010 N. This paper provides scientific theory evidences for optimal parameter design and proper tolerance distribution in advanced devel- opment and manufacturing process, so as to achieve optimal effects in economy and technology.

关键词： Geared turbofan engine GTF engineAero-turbofan engine Star gearing reducer Load sharing behavior

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：