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

16 篇 会议
1 篇 期刊文献

馆藏范围

17 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6 篇 工学
- 6 篇 计算机科学与技术...
- 5 篇 软件工程
- 2 篇 生物医学工程（可授...
- 2 篇 生物工程
- 1 篇 光学工程
- 1 篇 信息与通信工程
- 1 篇 控制科学与工程
4 篇 理学
- 3 篇 数学
- 2 篇 生物学
- 1 篇 物理学
2 篇 管理学
- 2 篇 管理科学与工程(可...
- 1 篇 工商管理

主题

3 篇 image edge detec...
3 篇 computational mo...
2 篇 computer science
2 篇 neurons
2 篇 information tech...
2 篇 visualization
2 篇 histograms
2 篇 clustering algor...
2 篇 image color anal...
2 篇 biological syste...
2 篇 computer vision
2 篇 object recogniti...
1 篇 biology computin...
1 篇 prior knowledge
1 篇 receptive fields...
1 篇 pose
1 篇 image matching
1 篇 support vector m...
1 篇 ensemble learnin...
1 篇 information anal...

机构

4 篇 lab of algorithm...
1 篇 inst. of softwar...
1 篇 department of co...
1 篇 brain science re...
1 篇 department of co...
1 篇 lab of algorithm...
1 篇 lab of algorithm...
1 篇 department of co...
1 篇 key laboratory o...
1 篇 fudan university
1 篇 department of co...
1 篇 lab of cognitive...
1 篇 school of inform...
1 篇 algorithm for co...
1 篇 lab. of algorith...
1 篇 lab of algorithm...
1 篇 lab of cognitive...
1 篇 lab. of intellig...
1 篇 inst. of artific...
1 篇 cas

作者

10 篇 hui wei
6 篇 wei hui
4 篇 yuan ren
3 篇 ren yuan
2 篇 hui-lan luo
1 篇 陆汝钤
1 篇 huang di
1 篇 huilan luo
1 篇 bo lang
1 篇 weng dawei
1 篇 fanxing hu
1 篇 hu fanxing
1 篇 xudong guan
1 篇 yan chen
1 篇 qingsong zuo
1 篇 wang yunhong
1 篇 危辉
1 篇 jinwen xiao
1 篇 wen he
1 篇 luan shang-min

语言

16 篇 英文
1 篇 中文

检索条件"机构=Lab of Algorithm for Cognitive Model"

共 17 条记录，以下是1-10 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：

Neural encoding based on frequency states using multi-spike train data

Neural encoding based on frequency states using multi-spike ...

引用

2010 IEEE 5th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2010

作者： Hu, Fanxing Wei, Hui Lab of Algorithm for Cognitive Model School of Computer Science and Technology Fudan University Shanghai China

ISBN: (纸本)9781424464388

Understanding the way how the neural networks encode outer stimulus and inner decision-making process is a key problem in neuroscience as well as in artificial intelligence. Although researchers have proposed several assumptions and related models, the supporting biological evidences are rarely provided. Our task involves finding an encoding method based on neuron firing frequency states and its transformation model under certain stimulus. Besides, a new method to analyze spikes train data is also proposed which is proved effective here. Then, the results by analyzing multi-microelectrodes simultaneous recorded spike train from temporal cortex and hippocampus of mouse experiment is shown, supporting and validating this model. © 2010 IEEE.

关键词： Microelectrodes

来源：评论

学校读者我要写书评

暂无评论

An orientation detection model based on fitting from multiple local hypotheses 1

引用

19th International Conference on Neural Information Processing, ICONIP 2012

作者： Wei, Hui Ren, Yuan Lab. of Cognitive Model and Algorithm School of Computer Science Fudan University Shanghai 200433 China

ISBN: (数字)9783642344817

ISBN: (纸本)9783642344800

Orientation detection is an important step in image understanding. Simple cells in the primary visual cortex are sensitive to stimuli of specific orientation. Hubel and Wiesel's classical theory attributes orientation selection in a simple cell to the aligned receptive fields of the retinal ganglion cells and the lateral geniculate nucleus cells. It is hypothesized that these receptive fields are similar in size and sub-structure. Current anatomical and electrophysiological evidence is not sufficient to support this geometric-arrangement-based model. Additionally, this feedforward model is incomplete in the implementation details of neural computation. The proposed algebraic model satisfies local constraints from afferent neurons and estimates the orientation of the stimulus. This constraint satisfaction based approach achieves desirable results on challenging image dataset, and can also be used to explain visual illusions. © 2012 Springer-Verlag.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

3D information acquisition from rectangles and circles in single images

3D information acquisition from rectangles and circles in si...

引用

2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009

作者： Ren, Yuan Wei, Hui Lab. of Algorithm for Cognitive Model School of Computer Science Fudan University Shanghai 200433 China

ISBN: (纸本)9780769535074

This paper presents a monocular approach of partially recovering three-dimensional information from rectangles and circles with proper prior knowledge. Taking image-formation process as projective transform, we first work out the focal length of an image with a common perspective rectangle and further obtain normal vectors of the supporting planes of rectangles and circles and relative depths of each point on the planes with respect to camera coordinate system. The absolute depths and other information about lengths and distances are also acquirable with reasonable estimation or measurement of side lengths and radius. The experimental results suggest good feasibility and acceptable precision of our approach. © 2008 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Aa wavelet model of ganglion cells array and its application in image representation

Aa wavelet model of ganglion cells array and its application...

引用

14th Pacific-Rim Conference on Multimedia, PCM 2013

作者： Weng, Dawei Wang, Yunhong Wei, Hui Huang, Di IRIP Lab Beihang Univ. Beijing China Department of Computer Science Laboratory of Cognitive Model and Algorithm Fudan Univ. Shanghai China

ISBN: (纸本)9783319037301

In this paper, we explore a new local image descriptor based on the modeling of ganglion cells array at the retina. We first introduce the mathematical model of a single ganglion cell and detailed distribution characteristics of ganglion cells array. From above evidence, we find out that the features of ganglion cells array are similar with wavelets in nature. Hence, a set of novel wavelet basis functions is constructed, which well fit these features. Furthermore, we discover that the modeling wavelets are in possession of tight frame property in its corresponding spatial domain expression, that is, multiple scales, shifts, phases of the spatial wavelet basis functions form a tight frame of the L2 Hilbert space, which is helpful to extract strongly distinctive and slightly redundant information in the image matching task. Finally, we obtain an efficient descriptor, state-of-the-art ones. Additionally, the proposed descriptor is easier to construct and much faster to compute. Evaluated in the image matching task on the Multi-view Stereo Correspondence Data set, the results demonstrate its effectiveness. © Springer International Publishing Switzerland 2013.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

A Shape Recognition Method Based on Graph- and Line-Contexts

A Shape Recognition Method Based on Graph- and Line-Contexts

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Hui Wei Jinwen Xiao Lab of Cognitive Model and Algorithm Fudan University Shanghai China

The shape, or contour, of an object is usually stable and persistent, so it is a good basis for invariant recognition. For this purpose, two problems must be addressed. The first is to obtain clean edges, and the second is to organize those edges into a structured data form upon which the necessary manipulations and analysis may be performed. Simple cells in the primary visual cortex are specialized in orientation detection, so the neural mechanism can be simulated by a computational model, which can produce a fairly clean set of lines, and all of them in vectors rather than in pixels. Then a line-context descriptor was designed to describe geometrical distribution of lines in a local area. All lines were also recorded by a weighted graph, and its minimum spanning tree can be used to describe the topological features of an object. An iterative matching algorithm was developed by combining line-context descriptors and minimum spanning tree, and was shown to match objects of the same type but with different shapes very well. Our results suggest that key to representation efficiency of searchable trees is to apply a mid-level line-context. This once more confirms the crucial role played by simple cells in visual processing path, for its preprocessing can greatly ease the subsequent processing.

关键词： Shape Computational modeling Image segmentation Image color analysis Educational institutions Image edge detection Visualization

来源：评论

学校读者我要写书评

暂无评论

COMBINING DIFFERENT INTERESTING POINT DETECTORS FOR OBJECT CATEGORIZATION

COMBINING DIFFERENT INTERESTING POINT DETECTORS FOR OBJECT C...

引用

2009 International Conference on Machine Learning and Cybernetics(2009机器学习与控制论国际会议)

作者： HUI-LAN LUO YUAN REN HUI WEI Lab of Algorithm for Cognitive Model School of Computer Science Fudan University Shanghai 200433 Lab of Algorithm for Cognitive Model School of Computer Science Fudan University Shanghai 200433

Many interesting point detectors have been proposed in the literature. It is unclear which detectors are more appropriate and how their performance depends on the task. We propose to use different detectors to gain different cues of images. Then an ensemble of classifications can be obtained, each based on one cue. The use of classification ensemble to categorize new images can lead to improved performance. Detailed experimental analyses on several datasets show that our ensemble approaches are well resistant to the variations in view, lighting, occlusion and the intra-class variations and achieve state-of-the-art performance in categorization.

关键词： Interesting point Object categorization Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Object Identification and Recognition Using Multiple Contours Based Moment Invariants

Object Identification and Recognition Using Multiple Contour...

引用

International Symposium on Information Science and Engineering, ISISE

作者： Ren Yuan Wei Hui Lab of Algorithm for Cognitive Model School of Computer Science Fudan University Shanghai China

A particular kind of invariants known as moment invariants have been used for object recognition and identification due to its invariabilities under translation, rotation and similitude transformation and approximate invariability even under small-scale perspective transformation, while contours representing shapes and structures play key role in people's tasks of reorganization and identification. A combining approach incorporating contours into moment invariant is proposed in this paper such that advantages of both are employed. Redefined on contours of both the whole objects and their inners, not just are moment invariants related to geometric information but they are less sensitive to non-essential changes and less complex for computations. Vectors formed by invariants act as features of objects and are classified by Nearest Neighborhood. If common features of kinds of objects are defined in advance, this algorithm can be used for objects belonging to those kinds. Time and space complex are rather low and experimental results show desirable accuracy.

关键词： Object recognition Computer science Pattern analysis Shape measurement Information science Machine vision Stability Character recognition Physics Mirrors

来源：评论

学校读者我要写书评

暂无评论

Object Recognition Using Words model of Optimal Size in Histograms of Oriented Gradients

Object Recognition Using Words Model of Optimal Size in Hist...

引用

International Symposium on Intelligent Information Technology Application, IITA

作者： Yuan Ren Hui Wei Huilan Luo Lab of Algorithm for Cognitive Model School of Computer Science Fudan University Shanghai China

This paper presents a new bag-of-words based algorithm for object recognition. Our algorithm also includes five steps: feature detection and representation, codebook generation, learning and recognition. All features are extracted as dense grids of images instead of interest point for computationally efficiency and effectiveness. While features are described by histograms of oriented gradients (HOG) rather than widely used scale invariant feature transform (SIFT). Different from previous work that randomly determine codebook size, the influence of the codebook size on the performance is also explored as another key problem. Then optimum sizes are chosen for further operation. In the training part, linear support vector machine (SVM) as well as support vector regression (SVR) is adopted due to their sati. Experiment are done on various cars from one of the most challenging databases Gaze; and the results show that our algorithm achieves desirable effect while the computational cost hardly increases.

关键词： Object recognition Histograms Image edge detection Support vector machines Computer vision Detectors Support vector machine classification Feature extraction Clustering algorithms Information technology

来源：评论

学校读者我要写书评

暂无评论

A Bio-inspired model for Image Representation and Image Analysis

A Bio-inspired Model for Image Representation and Image Anal...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Hui Wei Qingsong Zuo Bo Lang Lab of Cognitive Model and Algorithm School of Computer Science Fudan University Shanghai China

This paper proposes a model for image representation and image analysis using a multi-layer neural network, which is rooted in the human vision system. Having complex neural layers to represent and process information, the biological vision system is far more efficient than machine vision system. The neural model simulate non-classical receptive field of ganglion cell and its local feedback control circuit, and can represent images, beyond pixel level, self-adaptively and regularly. The results of experiments, rebuilding, distribution and contour detection, prove this method can represent image faithfully with low cost, and can produce a compact and abstract approximation to facilitate successive image segmentation and integration. This representation schema is good at extracting spatial relationships from different components of images and highlighting foreground objects from background, especially for nature images with complicated scenes. Further it can be applied to object recognition or image classification tasks in future.

关键词： Image representation Computational modeling Image color analysis Biological system modeling Neurons Wavelet transforms Radio frequency

来源：评论

学校读者我要写书评

暂无评论

UML-BASED REPRESENTATIONAL RE-DESCRIPTION OF CONCEPT DEVELOPMENT

UML-BASED REPRESENTATIONAL RE-DESCRIPTION OF CONCEPT DEVELOP...

引用

2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

作者： HUI WEI WEN HE YAN CHEN Department of Computer Science Lab of Algorithm for Cognitive Model Fudan University Shanghai 200433 China

Knowledge-based problem solving requires a conceptual system that is comparatively rich and complete, especially when the problem is domain *** methods about knowledge acquisition, representation and usage in classical Knowledge Engineering can only adapt themselves to domain restricted *** is because it doesn't take a developmental view to construct conceptual system and consequently it is confronted with Framework *** cognitive Psychology, the study of conceptual system has an in-depth cognitive investigate on issues of development and ***, there lack investigations on the details of system construction and *** on the theory of Developmental Psychology, this paper proposes an object-based representation method for conceptual system, focusing on the representation and development of concepts on four levels: Implicit (I), Explicit 1 (E1), Explicit 2 (E2) and Explicit 3 (E3) *** will contribute well to the adaptability and flexibility in the reasoning and problem solving of knowledge-based systems.

关键词： Concept acquisition Representational re-description Learning Artificial intelligence

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2页 << < 1 2 > >>

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：