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

654 篇 会议
2 册 图书

馆藏范围

656 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

648 篇 工学
- 406 篇 机械工程
- 298 篇 计算机科学与技术...
- 17 篇 电气工程
- 14 篇 软件工程
- 11 篇 光学工程
- 4 篇 信息与通信工程
- 2 篇 控制科学与工程
- 2 篇 生物医学工程（可授...
- 2 篇 生物工程
- 1 篇 仪器科学与技术
- 1 篇 电子科学与技术（可...
- 1 篇 土木工程
- 1 篇 化学工程与技术
14 篇 理学
- 11 篇 物理学
- 5 篇 数学
- 3 篇 生物学
- 2 篇 系统科学
- 2 篇 统计学（可授理学、...
- 1 篇 化学
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...
- 1 篇 工商管理
1 篇 法学
- 1 篇 社会学
1 篇 教育学
- 1 篇 教育学
1 篇 医学
- 1 篇 基础医学(可授医学...
- 1 篇 临床医学
- 1 篇 药学(可授医学、理...

主题

252 篇 computer vision
94 篇 image segmentati...
90 篇 cameras
86 篇 layout
84 篇 feature extracti...
83 篇 face recognition
82 篇 object recogniti...
76 篇 object detection
74 篇 image recognitio...
71 篇 humans
70 篇 shape
68 篇 robustness
66 篇 computer science
63 篇 image reconstruc...
54 篇 image classifica...
54 篇 learning (artifi...
49 篇 application soft...
49 篇 image motion ana...
41 篇 image representa...
40 篇 testing

机构

8 篇 microsoft resear...
6 篇 microsoft res as...
4 篇 robotics institu...
4 篇 carnegie mellon ...
4 篇 department of co...
4 篇 univ illinois ur...
4 篇 microsoft res re...
4 篇 department of co...
4 篇 mit cambridge ma...
4 篇 carnegie mellon ...
4 篇 cornell univ ith...
4 篇 department of co...
4 篇 stanford univ st...
4 篇 carnegie mellon ...
3 篇 penn state univ ...
3 篇 nanyang technol ...
3 篇 univ michigan an...
3 篇 univ adelaide sc...
3 篇 school of comput...
3 篇 georgia institut...

作者

6 篇 mubarak shah
6 篇 tsuhan chen
5 篇 shiguang shan
5 篇 daniel cremers
5 篇 xilin chen
5 篇 nikos paragios
5 篇 wen gao
5 篇 yanxi liu
4 篇 nassir navab
4 篇 zhang lei
4 篇 jan-michael frah...
4 篇 li stan z.
4 篇 thomas huang
4 篇 vincent lepetit
4 篇 tieniu tan
4 篇 svetha venkatesh
4 篇 narendra ahuja
4 篇 alan yuille
4 篇 de la torre fern...
4 篇 liang wang

语言

653 篇 英文
2 篇 土耳其文
1 篇 其他

检索条件"任意字段=26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013"

共 656 条记录，以下是601-610 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：

Max Margin AND/OR Graph Learning for Parsing the Human Body

Max Margin AND/OR Graph Learning for Parsing the Human Body

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.11

作者： Long (Leo) Zhu Yuanhao Chen Yifei Lu Chenxi Lin Alan Yuille Department of Statistics University of California Los Angeles USA University of Science and Technology China Shanghai Jiaotong University China Microsoft Research Asia China Department of Statistics Psychology and Computer Science University of California Los Angeles USA

We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human body and its parts by an AND/OR graph, which is a multi-level mixture of Markov Random Fields (MRFs). Max-margin learning, which is a generalization of the training algorithm for support vector machines (SVMs), is used to learn the parameters of the AND/OR graph model discriminatively. there are four advantages from this combination of AND/OR graphs and max-margin learning. Firstly, the AND/OR graph allows us to handle enormous articulated poses with a compact graphical model. Secondly, max-margin learning has more discriminative power than the traditional maximum likelihood approach. thirdly, the parameters of the AND/OR graph model are optimized globally. In particular, the weights of the appearance model for individual nodes and the relative importance of spatial relationships between nodes are learnt simultaneously. Finally, the kernel trick can be used to handle high dimensional features and to enable complex similarity measure of shapes. We perform comparison experiments on the baseball datasets, showing significant improvements over state of the art methods.

关键词： Humans Biological system modeling Machine learning Tree graphs Statistics Maximum likelihood estimation Kernel Shape measurement Performance analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

Visual Tracking Via Incremental Log-Euclidean Riemannian Subspace Learning

Visual Tracking Via Incremental Log-Euclidean Riemannian Sub...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.5

作者： Xi Li Weiming Hu Zhongfei Zhang Xiaoqin Zhang Mingliang Zhu Jian Cheng National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China State University of New York Binghamton NY USA

Recently, a novel Log-Euclidean Riemannian metric [28] is proposed for statistics on symmetric positive definite (SPD) matrices. Under this metric, distances and Riemannian means take a much simpler form than the widely used affine-invariant Riemannian metric. Based on the Log-Euclidean Riemannian metric, we develop a tracking framework in this paper. In the framework, the covariance matrices of image features in the five modes are used to represent object appearance. Since a nonsingular covariance matrix is a SPD matrix lying on a connected Riemannian manifold, the Log-Euclidean Riemannian metric is used for statistics on the covariance matrices of image features. Further, we present an effective online Log-Euclidean Riemannian subspace learning algorithm which models the appearance changes of an object by incrementally learning a low-order Log-Euclidean eigenspace representation through adaptively updating the sample mean and eigen-basis. Tracking is then led by the Bayesian state inference framework in which a particle filter is used for propagating sample distributions over the time. theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the proposed framework.

关键词： Covariance matrix Robustness Lighting Statistics Inference algorithms Particle tracking Particle filters Kernel Principal component analysis Cameras

来源：评论

学校读者我要写书评

暂无评论

Dynamic scene shape reconstruction using a single structured light pattern

Dynamic scene shape reconstruction using a single structured...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.9

作者： Hiroshi Kawasaki Ryo Furukawa Ryusuke Sagawa Yasushi Yagi Saitama University Japan Faculty of Information Sciences Hiroshima City University Japan Institute of Scientific and Industrial Research Osaka University Japan

3D acquisition techniques to measure dynamic scenes and deformable objects with little texture are extensively researched for applications like the motion capturing of human facial expression. To allow such measurement, several techniques using structured light have been proposed. these techniques can be largely categorized into two types. the first involves techniques to temporally encode positional information of a projector's pixels using multiple projected patterns, and the second involves techniques to spatially encode positional information into areas or color spaces. Although the former allows dense reconstruction with a sufficient number of patterns, it has difficulty in scanning objects in rapid motion. the latter technique uses only a single pattern, so this problem can be resolved, however, it often uses complex patterns or color intensities, which are weak to noise, shape distortions, or textures. thus, it remains an open problem to achieve dense and stable 3D acquisition in real cases. In this paper, we propose a technique to achieve dense shape reconstruction that requires only a single-frame image of a grid pattern. the proposed technique also has the advantage of being robust in terms of image processing.

关键词： Layout Image reconstruction Colored noise Shape measurement Motion measurement Humans Spatial resolution Noise shaping Robustness Image processing

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC FACE recognition FROM VIDEO SEQUENCES USING A TEMPLATE BASED CROSS CORRELATION MEthOD

AUTOMATIC FACE RECOGNITION FROM VIDEO SEQUENCES USING A TEMP...

引用

ieee Canadian conference on Electrical and computer Engineering

作者： Edward Rosales Yun Tie Anastasios Venetsanopoulos Ling Guan Electrical Engineering Ryerson University Toronto ON Canada

ISBN: (纸本)9781479900312

Face recognition in videos has been an active topic in the field of object recognition and computer vision. In this paper we propose an automatic face recognition algorithm from video sequences using a template based cross correlation (TBCC) method. It utilizes random selection of frames to form the training template for the discriminant feature representation of a face. the proposed method was tested by randomly selecting a subject from the RML and Cohn-Kanade (CK) databases with non-overlapping sequences between test and training sequences. From the experiments on several datasets, the system performance achieved an average recognition rate of 88%.

关键词： Facial recognition Video sequences jigs(templates) Videotapes Cross correlation training sequence Randomisation object recognition images computer vision AUTOMATIC System performance face recognition algorithm

来源：评论

学校读者我要写书评

暂无评论

Principled Fusion of High-level Model and Low-level Cues for Motion Segmentation

Principled Fusion of High-level Model and Low-level Cues for...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.3

作者： Arasanathan thayananthan Masahiro Iwasaki Roberto Cipolla Department of Engineering University of Cambridge Cambridge UK Panasonic Europe Limited Cambridge UK

High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, approximate inference in these models often require ad-hoc initialization to avoid local minima issues. Low-level cues, obtained independently from the high-level model, can constrain the search space and reduce the chance of inference algorithms falling into a local minima. this paper introduces a novel principled fusion framework where, local hierarchical superpixels segmentation of images are used to capture local motion. the low-level cues such as local motion, on their own, not adequate to obtain full motion segmentation as occlusion needs to be handled globally. We fuse the low-level motion cues with the high-level model in a principled manner to surmount the shortcomings of using only the high-level model or low-level cues to perform motion segmentation. the fused model contains both continuous and discrete variables which forms a number of Markov Random fields. Variational approximation or belief propagation algorithms cannot be applied due to the complex interactions between the variables. Hence, approximate inference is performed using expectation propagation (EP) algorithm. the scheme is demonstrated by performing motion segmentation in two video sequences.

关键词： Motion segmentation computer vision Inference algorithms Fusion power generation Videos Image segmentation Fuses Markov random fields Belief propagation Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Biologically Inspired Model

Enhanced Biologically Inspired Model

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.7

作者： Yongzhen Huang Kaiqi Huang Liangsheng Wang Dacheng Tao Tieniu Tan Xuelong Li National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China Biometrics Research Centre Department of Computing Hong Kong Polytechnic University Hong Kong China School of Computer Science and Information Systems Birkbeck University of London London UK

It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feedforward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 × 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.

关键词： Biological system modeling Spatial databases Image databases Brain modeling Object recognition Visual databases Computational efficiency Feedforward systems Feedback Layout

来源：评论

学校读者我要写书评

暂无评论

3D Model Matching with Viewpoint-Invariant Patches (VIP)

3D Model Matching with Viewpoint-Invariant Patches (VIP)

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.4

作者： Changchang Wu Brian Clipp Xiaowei Li Jan-Michael Frahm Marc Pollefeys Department of Computer Science North Carolina State University Chapel Hill NC USA Department of Computer Science ETH Zurich Switzerland

the robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. this paper introduces a novel class of viewpoint independent local features for robust registration and novel algorithms to use the rich information of the new features for 3D scene alignment and large scale scene reconstruction. the key point of our approach consists of leveraging local shape information for the extraction of an invariant feature descriptor. the advantages of the novel viewpoint invariant patch (VIP) are: that the novel features are invariant to 3D camera motion and that a single VIP correspondence uniquely defines the 3D similarity transformation between two scenes. In the paper we demonstrate how to use the properties of the VIPs in an efficient matching scheme for 3D scene alignment. the algorithm is based on a hierarchical matching method which tests the components of the similarity transformation sequentially to allow efficient matching and 3D scene alignment. We evaluate the novel features on real data with known ground truth information and show that the features can be used to reconstruct large scale urban scenes.

关键词： Layout Image reconstruction Robustness Cameras Large-scale systems Geometry computer science Shape Data mining Sequential analysis

来源：评论

学校读者我要写书评

暂无评论

Fast Algorithms for Large Scale Conditional 3D Prediction

Fast Algorithms for Large Scale Conditional 3D Prediction

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.6

作者： Liefeng Bo Cristian Sminchisescu Atul Kanaujia Dimitris Metaxas TTI-C University of Bonn Germany Rutgers University USA

the potential success of discriminative learning approaches to 3D reconstruction relies on the ability to efficiently train predictive algorithms using sufficiently many examples that are representative of the typical configurations encountered in the application domain. Recent research indicates that sparse conditional Bayesian Mixture of Experts (cMoE) models (e.g. BME [21]) are adequate modeling tools that not only provide contextual 3D predictions for problems like human pose reconstruction, but can also represent multiple interpretations that result from depth ambiguities or occlusion. However, training conditional predictors requires sophisticated double-loop algorithms that scale unfavorably with the input dimension and the training set size, thus limiting their usage to 10,000 examples of less, so far. In this paper we present large-scale algorithms, referred to as fBME, that combine forward feature selection and bound optimization in order to train probabilistic, BME models, with one order of magnitude more data (100,000 examples and up) and more than one order of magnitude faster. We present several large scale experiments, including monocular evaluation on the HumanEva dataset [19], demonstrating how the proposed methods overcome the scaling limitations of existing ones.

关键词： Large-scale systems Bayesian methods Humans Predictive models Iterative algorithms Image reconstruction Context modeling Boosting Optimization methods computer vision

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform

Spatio-temporal Saliency Detection Using Phase Spectrum of Q...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.9

作者： Chenlei Guo Qi Ma Liming Zhang Department of Electronic Engineering Fudan University Shanghai China

Salient areas in natural scenes are generally regarded as the candidates of attention focus in human eyes, which is the key stage in object detection. In computer vision, many models have been proposed to simulate the behavior of eyes such as SaliencyToolBox (STB), Neuromorphic vision Toolkit (NVT) and etc., but they demand high computational cost and their remarkable results mostly rely on the choice of parameters. Recently a simple and fast approach based on Fourier transform called spectral residual (SR) was proposed, which used SR of the amplitude spectrum to obtain the saliency map. the results are good, but the reason is questionable. In this paper, we propose it is the phase spectrum, not the amplitude spectrum, of the Fourier transform that is the key in obtaining the location of salient areas. We provide some examples to show that PFT can get better results in comparison with SR and requires less computational complexity as well. Furthermore, PFT can be easily extended from a two-dimensional Fourier transform to a Quaternion Fourier Transform (QFT) if the value of each pixel is represented as a quaternion composed of intensity, color and motion feature. the added motion dimension allows the phase spectrum to represent spatio-temporal saliency in order to engage in attention selection for videos as well as images. Extensive tests of videos, natural images and psychological patterns show that the proposed method is more effective than other models. Moreover, it is very robust against white-colored noise and meets the real-time requirements, which has great potentials in engineering applications.

关键词： Phase detection Quaternions Fourier transforms Eyes Strontium Layout Humans Object detection computer vision Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Exact Inference in Multi-label CRFs with Higher Order Cliques

Exact Inference in Multi-label CRFs with Higher Order Clique...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.2

作者： Srikumar Ramalingam Pushmeet Kohli Karteek Alahari Philip H. S. Torr Oxford Brookes University UK Microsoft Research Limited Cambridge UK

this paper addresses the problem of exactly inferring the maximum a posteriori solutions of discrete multi-label MRFs or CRFs with higher order cliques. We present a framework to transform special classes of multi-label higher order functions to submodular second order boolean functions (referred to as (F{sub}s){sup}2), which can be minimized exactly using graph cuts and we characterize those classes. the basic idea is to use two or more boolean variables to encode the states of a single multi-label variable. there are many ways in which this can be done and much interesting research lies in finding ways which are optimal or minimal in some sense. We study the space of possible encodings and find the ones that can transform the most general class of functions to (F{sub}s){sup}2. Our main contributions are two-fold. First, we extend the subclass of submodular energy functions that can be minimized exactly using graph cuts. Second, we show how higher order potentials can be used to improve single view 3D reconstruction results. We believe that our work on exact minimization of higher order energy functions will lead to similar improvements in solutions of other labelling problems.

关键词： Labeling Boolean functions computer vision Polynomials Cost function Encoding Minimization methods Discrete transforms Image reconstruction Image segmentation

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66页 << < 57 58 59 60 61 62 63 64 65 66 > >>

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：