检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

63 篇 会议
15 册 图书
2 篇 期刊文献

馆藏范围

80 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

36 篇 工学
- 26 篇 计算机科学与技术...
- 20 篇 软件工程
- 9 篇 电气工程
- 4 篇 光学工程
- 3 篇 机械工程
- 3 篇 生物医学工程（可授...
- 3 篇 生物工程
- 2 篇 建筑学
- 2 篇 土木工程
- 1 篇 材料科学与工程（可...
- 1 篇 冶金工程
- 1 篇 电子科学与技术（可...
- 1 篇 信息与通信工程
- 1 篇 控制科学与工程
- 1 篇 交通运输工程
- 1 篇 城乡规划学
- 1 篇 安全科学与工程
9 篇 医学
- 9 篇 临床医学
- 3 篇 基础医学(可授医学...
- 2 篇 药学(可授医学、理...
8 篇 理学
- 5 篇 数学
- 3 篇 物理学
- 1 篇 生物学
- 1 篇 系统科学
- 1 篇 统计学（可授理学、...
5 篇 管理学
- 3 篇 图书情报与档案管...
- 2 篇 管理科学与工程(可...
2 篇 农学
- 2 篇 作物学
1 篇 法学
- 1 篇 社会学
1 篇 教育学
- 1 篇 教育学

主题

17 篇 computer vision
14 篇 computer imaging...
8 篇 computer archite...
7 篇 signal, image an...
7 篇 graphics process...
6 篇 computer applica...
6 篇 computer graphic...
6 篇 artificial intel...
5 篇 image segmentati...
5 篇 machine learning
5 篇 field programmab...
5 篇 training
4 篇 three-dimensiona...
4 篇 pattern recognit...
3 篇 rendering (compu...
3 篇 three dimensiona...
3 篇 human computer i...
3 篇 neural networks
3 篇 computer aided d...
3 篇 hardware

机构

6 篇 university of vi...
6 篇 rochester instit...
6 篇 national center ...
6 篇 case western res...
6 篇 chinese universi...
2 篇 kiit group of co...
2 篇 wentworth instit...
2 篇 institute for co...
2 篇 st. petersburg f...
2 篇 indian institute...
2 篇 koneru lakshmaia...
2 篇 indian institute...
1 篇 st thomas hosp e...
1 篇 school of scienc...
1 篇 acc innovations ...
1 篇 university of ge...
1 篇 univ tecnol mixt...
1 篇 western universi...
1 篇 intel r&d irelan...
1 篇 keldysh institut...

作者

6 篇 qi dou
6 篇 shuo li
6 篇 linwei wang
6 篇 stefanie speidel
6 篇 p. thomas fletch...
3 篇 friedrich fraund...
2 篇 leonidas deligia...
2 篇 rajesh m. hegde
2 篇 k. t. deepak
2 篇 hamid r. arabnia
2 篇 k. samudravijaya
2 篇 s. r. mahadeva p...
2 篇 shyam s. agrawal
2 篇 alexey karpov
1 篇 wang ting-xuan
1 篇 vavpotič damjan
1 篇 galaktionov v.a.
1 篇 khalili ali
1 篇 rastegar raha m.
1 篇 soheyla amirian

语言

73 篇 英文
7 篇 俄文

检索条件"任意字段=25th International Conference on Computer Graphics and Vision, GraphiCon 2015"

共 80 条记录，以下是61-70 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Machine-learned Regularization and Polygonization of Building Segmentation Masks

Machine-learned Regularization and Polygonization of Buildin...

引用

international conference on Pattern Recognition

作者： Stefano Zorzi Ksenia Bittner Friedrich Fraundorfer Institute of Computer Graphics and Vision Graz University of Technology Remote Sensing Technology Institute German Aerospace Center (DLR)

ISBN: (纸本)9781728188089;9781728188096

We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. Taking an image as input, we first predict building segmentation maps exploiting generic fullyconvolutionalnetwork(FCN). A generativeadversarialnetwork(GAN) is then involved to perform a regularization of building boundaries to make them more realistic, i.e., having more rectilinear outlines which construct right angles if required. this is achieved through the interplay between the discriminator which gives a probability of input image being true and generator that learns from discriminator's response to create more realistic images. Finally, we train the backbone convolutionalneuralnetwork(CNN) which is adapted to predict sparse outcomes corresponding to building corners out of regularized building s

关键词： Geometry Image segmentation Buildings Neural networks Machine learning Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Anomaly Detection Algorithms for the Real-World Applications

Evaluation of Anomaly Detection Algorithms for the Real-Worl...

引用

international conference on Pattern Recognition

作者： Marija Ivanovska Janez Perš Domen Tabernik Danijel Skočaj Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia

Anomaly detection in complex data structures is one of the most challenging problems in computer vision. In many real-world problems, for example in the quality control in modern manufacturing, the anomalous samples are usually rare, resulting in (highly) imbalanced datasets. However, in current research practice, these scenarios are rarely modeled, and as a consequence, evaluation of anomaly detection algorithms often do not reproduce results that are useful for practical applications. First, even in case of highly unbalanced input data, anomaly detection algorithms are expected to significantly reduce the proportion of anomalous samples, detecting “almost all” anomalous samples (with exact specifications depending on the target customer). this places high importance on only the small part of the ROC curve, possibly rendering the standard metrics such as AUC (Area Under Curve) and AP (Average Precision) useless. Second, the target of automatic anomaly detection in practical applications is significant reduction in manual work required, and standard metrics are poor predictor of this feature. Finally, the evaluation may produce erratic results for different randomly initialized training runs of the neural network, producing evaluation results that may not reproduce well in practice. In this paper, we present an evaluation methodology that avoids these pitfalls.

关键词： Measurement Training computer vision Satellites Computational modeling Manuals Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

UHRSNet: A Semantic Segmentation Network Specifically for Ultra-High-Resolution Images

UHRSNet: A Semantic Segmentation Network Specifically for Ul...

引用

international conference on Pattern Recognition

作者： Lianlei Shan Minglong Li Xiaobin Li Yang Bai Ke Lv Bin Luo Si-Bao Chen Weiqiang Wang University of Chinese Academy of Sciences Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Semantic segmentation is a basic task in computer vision, but only limited attention has been devoted to the ultra-high-resolution (UHR) image segmentation. Since UHR images occupy too much memory, they cannot be directly put into GPU for training. Previous methods are cropping images to small patches or downsampling the whole images. Cropping and downsampling cause the loss of contexts and details, which is essential for segmentation accuracy. To solve this problem, we improve and simplify the local and global feature fusion method in previous works. Local features are extracted from patches and global features are from downsampled images. Meanwhile, we propose one new fusion called local feature fusion for the first time, which can make patches get information from surrounding patches. We call the network with these two fusions ultra-high-resolution segmentation network (UHRSNet). these two fusions can effectively and efficiently solve the problem caused by cropping and downsampling. Experiments show a remarkable improvement on Deepglobe dataset [1].

关键词： Training Image segmentation computer vision Semantics graphics processing units Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Robust Visual Object Tracking with Top-down Reasoning 17

Robust Visual Object Tracking with Top-down Reasoning

引用

25th ACM international conference on Multimedia (MM)

作者： Zhang, Mengdan Feng, Jiashi Hu, Weiming Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Natl Univ Singapore Singapore Singapore

ISBN: (纸本)9781450349062

In generic visual tracking, traditional appearance based trackers suffer from distracting factors like bad lighting or major target deformation, etc., as well as insufficiency of training data. In this work, we propose to exploit the category-specific semantics to boost visual object tracking, and develop a new visual tracking model that augments the appearance based tracker with a top-down reasoning component. the continuous feedback from this reasoning component guides the tracker to reliably identify candidate regions with consistent semantics across frames and localize the target object instance more robustly and accurately. Specifically, a generic object recognition model and a semantic activation map method are deployed to provide effective top-down reasoning about object locations for the tracker. In addition, we develop a voting based scheme for the reasoning component to infer the object semantics. therefore, even without sufficient training data, the tracker can still obtain reliable top-down clues about the objects. Together with the appearance clues, the tracker can localize objects accurately even in presence of various major distracting factors. Extensive evaluations on two large-scale benchmark datasets, OTB2013 and OTB2015, clearly demonstrate that the top-down reasoning substantially enhances the robustness of the tracker and provides state-of-the-art performance.

关键词： Visual tracking Deep learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Deep supervised qantization by self-organizing map 25

Deep supervised qantization by self-organizing map

引用

25th ACM international conference on Multimedia, MM 2017

作者： Wang, Min Zhou, Wengang Tian, Qi Pu, Junfu Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China China Computer Science Department University of Texas San Antonio United States

ISBN: (纸本)9781450349062

Approximate Nearest Neighbour (ANN) search is an important research topic in multimedia and computer vision fields. In this paper, we propose a new deep supervised quantization method by Self-Organizing Map (SOM) to address this problem. Our method integrates the Convolutional Neural Networks (CNN) and Self-Organizing Map into a unified deep architecture. the overall training objective includes supervised quantization loss and classification loss. With the supervised quantization loss, we minimize the differences on the maps between similar image pairs, and maximize the differences on the maps between dissimilar image pairs. By optimization, the deep architecture can simultaneously extract deep features and quantize the features into the suitable nodes in the Self-Organizing Map. the experiments on several public standard datasets prove the superiority of our approach over the existing ANN search methods. Besides, as a byproduct, our deep architecture can be directly applied to classification task and visualization with little modification, and promising performances are demonstrated on these tasks in the experiments. © 2017 ACM.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Generating FPGA accelerators for chemical similarity assessment

Generating FPGA accelerators for chemical similarity assessm...

引用

international conference on Field Programmable Logic and Applications

作者： Nikolaos Alachiotis Dept. of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA

Numerical measures of similarity/distance between objects represented by binary vectors are common in a wide range of disciplines. Searching in large-scale chemical databases requires billions of comparisons between molecules that are represented by binary fingerprints to capture the atomic structure. the performance bottleneck here is the enumeration of set bits in vectors (population count). Due to the discrete representation, similarity measures between binary fingerprints should fit well to FPGAs. We present an architecture to accelerate binary similarity assessment, evaluate various design points, and compare performance to highly optimized CPU and GPU implementations. We implement an RTL generation software, SimGenRTL, to generate accelerators of various sizes based on the proposed architecture. We find that accelerators with fewer and wider population counters allow better distribution of the hardware resources, outperforming significantly accelerators with more and narrower bit-enumeration components. SimGenRTL is available for download to allow rapid design space exploration of the computational core ahead of a full custom system implementation.

关键词： Sociology Statistics computer architecture Field programmable gate arrays Databases Chemicals graphics processing units

来源：评论

学校读者我要写书评

暂无评论

Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks

Novel View Synthesis from only a 6-DoF Camera Pose by Two-st...

引用

international conference on Pattern Recognition

作者： Xiang Guo Bo Li Yuchao Dai Tongxin Zhang Hui Deng School of Electronics and Information Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781728188089;9781728188096

Novel view synthesis is a challenging problem in computer vision and robotics. Different from the existing works, which need the reference images or 3D models of the scene to generate images under novel views, we propose a novel paradigm to this problem. that is, we synthesize the novel view from only a 6-DoF camera pose directly. Although this setting is the most straightforward way, there are few works addressing it. While, our experiments demonstrate that, with a concise CNN, we could get a meaningful parametric model that could reconstruct the correct scenery images only from the 6-DoF pose. To this end, we propose a two-stage learning strategy, which consists of two consecutive CNNs: GenNet and RefineNet. GenNet generates a coarse image from a camera pose. RefineNet is a generative adversarial network that refines the coarse image. In this way, we decouple the geometric relationship between mapping and texture detail rendering. Extensive experiments conducted on the public datasets prove the effectiveness of our method. We believe this paradigm is of high research and application value and could be an important direction in novel view synthesis.

关键词： Location awareness Solid modeling Visualization three-dimensional displays Robot vision systems Cameras Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

An innovative Charge Pump design and its properties optimization

An innovative Charge Pump design and its properties optimiza...

引用

international conference on Radioelektronika

作者： David Matoušek Ondřej Šubrt Department of Electrical Engineering University of Pardubice Pardubice Czech Republic ASICentrum a company of the Swatch Group Prague FEE CTU Prague Prague

Trend of maximum reduction of the power consumption of electronic devices is still at forefront of interest. For portable electronic appliances Charge Pumps are usually used. Indeed Charge Pumps have particularly small size, easy integrability and higher working frequency than conventional DC/DC converters. the integration of Charge Pumps directly into the system allows manufacturers to feed a complex system with many specific power requirements from a single source. But Charge Pump efficiency is reduced by many phenomena. Relatively strong effect has threshold voltage of used transistors or diodes. this paper is concentrated on optimizing of properties of proposed variant of Charge Pump. So output voltage, drawn current and resulted efficiency of proposed Charge Pump were optimized based on simulations executed by Mentor graphics.

关键词： Charge pumps Clocks threshold voltage Transistors Inverters Capacitors computer architecture

来源：评论

学校读者我要写书评

暂无评论

Towards heterogeneous solvers for large-scale linear systems

Towards heterogeneous solvers for large-scale linear systems

引用

international conference on Field Programmable Logic and Applications

作者： Stylianos I. Venieris Grigorios Mingas Christos-Savvas Bouganis Department of Electrical and Electronic Engineering Imperial College London London UK

Applying Linear Regression to systems with a massive amount of observations, a scenario which is becoming increasingly common in the era of Big Data, poses major algorithmic and computational challenges. this paper proposes a novel high-performance FPGA-based architecture for large-scale Linear Regression problems as well as a heterogeneous system comprising the custom FPGA architecture, an enhanced GPU module and a multi-core CPU for addressing the aforementioned problem. the system adaptively assigns Linear Regression workloads to the three computing devices to minimise runtime. the device with the highest performance is chosen based on an analytical framework, as well as the workload's size and structure. A quantitative comparison with existing FPGA, GPU and multi-core CPU designs yields speed-ups of up to 18.07×, 32.67× and 25.84× respectively.

关键词： graphics processing units Field programmable gate arrays computer architecture Digital signal processing Matrix decomposition Performance evaluation Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Fast hierarchical implementation of sequential tree-reweighted belief propagation for probabilistic inference

Fast hierarchical implementation of sequential tree-reweight...

引用

international conference on Field Programmable Logic and Applications

作者： Skand Hurkat Jungwook Choi Eriko Nurvitadhi José F. Martínez Rob A. Rutenbar Computer Systems Laboratory Cornell University Ithaca NY USA Dept. of Electrical and Computer Engineering Intel Labs Hillsboro OR USA Dept. of Computer Science University of Illinois at Urbana-Champaign Urbana IL USA

Maximum a posteriori probability (MAP) inference on Markov random fields (MRF) is the basis of many computer vision applications. Sequential tree-reweighted belief propagation (TRW-S) has been shown to provide very good inference quality and strong convergence properties. However, software TRW-S solvers are slow due to the algorithm's high computational requirements. A state-of-the-art FPGA implementation has been developed recently, which delivers substantial speedup over software. In this paper, we improve upon the TRW-S algorithm by using a multi-level hierarchical MRF formulation. We demonstrate the benefits of Hierarchical-TRW-S over TRW-S, and incorporate the proposed improvements on a Convey HC-1 CPU-FPGA hybrid platform. Results using four Middlebury stereo vision benchmarks show a 21% to 53% reduction in inference time compared with the state-of-the-art TRW-S FPGA implementation. To the best of our knowledge, this is the fastest hardware implementation of TRW-S reported so far.

关键词： Convergence Benchmark testing Belief propagation Hardware Software algorithms Field programmable gate arrays Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共8页 << < 1 2 3 4 5 6 7 8 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：