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641-650 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：

Unsupervised Learning of Probabilistic Object Models (POMs) for Object Classification, Segmentation and recognition

Unsupervised Learning of Probabilistic Object Models (POMs) ...

引用

26th ieee conference on computer vision and pattern recognition (cvpr 2008), vol.1

作者： Yuanhao Chen Long (Leo) Zhu Alan Yuille Hongjiang Zhang MOE-MS Key Laboratory of MCC University of Science and Technology China Department of Statistics University of California Los Angeles USA Department of Statistics Psychology and Computer Science University of California Los Angeles USA Microsoft Advanced Technology Center USA

We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this as a structure learning task and our strategy is to learn and combine basic POM's that make use of complementary image cues. Each POM has algorithms for inference and parameter learning, but: (i) the structure of each POM is unknown, and (ii) the inference and parameter learning algorithm for a POM may be impractical without additional information. We address these problems by a novel structure induction procedure which uses knowledge propagation to enable POM's to provide information to other POM's and "teach them" (which greatly reduced the amount of supervision required for training). In particular, we learn a POM-IP defined on Interest Points using weak supervision [1, 2] and use this to train a POM-mask, defined on regional features, which yields a combined POM which performs segmentation/localization. this combined model can be used to train POM-edgelets, defined on edgelets, which gives a full POM with improved performance on classification. We give detailed experimental analysis on large datasets which show that the full POM is invariant to scale and rotation of the object (for learning and inference) and performs inference rapidly. In addition, we show that we can apply POM's to learn objects classes (i.e. when there are several objects and the identity of the object in each image is unknown). We emphasize that these models can match between different objects from the same category and hence enable object recognition.

关键词： Unsupervised learning Image segmentation Inference algorithms Shape Object detection Statistics Laboratories Psychology computer science Data analysis

来源：评论

学校读者我要写书评

暂无评论

Matching Vehicles under Large Pose Transformations using Approximate 3D Models and Piecewise MRF Model

Matching Vehicles under Large Pose Transformations using App...

引用

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

作者： Yanlin Guo Cen Rao Supun Samarasekera Janet Kim Rakesh Kumar Harpreet Sawhney Sarnoff Corporation Princeton NJ USA

We propose a robust object recognition method based on approximate 3D models that can effectively match objects under large viewpoint changes and partial occlusion. the specific problem we solve is: given two views of an object, determine if the views are for the same or different object. Our domain of interest is vehicles, but the approach can be generalized to other man-made rigid objects. A key contribution of our approach is the use of approximate models with locally and globally constrained rendering to determine matching objects. We utilize a compact set of 3D models to provide geometry constraints and transfer appearance features for object matching across disparate viewpoints. the closest model from the set, together with its poses with respect to the data, is used to render an object both at pixel (local) level and region/part (global) level. Especially, symmetry and semantic part ownership are used to extrapolate appearance information. A piecewise Markov Random Field (MRF) model is employed to combine observations obtained from local pixel and global region level. Belief Propagation (BP) with reduced memory requirement is employed to solve the MRF model effectively. No training is required, and a realistic object image in a disparate viewpoint can be obtained from as few as just one image. Experimental results on vehicle data from multiple sensor platforms demonstrate the efficacy of our method.

关键词： Vehicles Object recognition Robustness Geometry Solid modeling Markov random fields Belief propagation Surveillance Lighting Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Real-Time Global Localization with A Pre-Built Visual Landmark Database

Real-Time Global Localization with A Pre-Built Visual Landma...

引用

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

作者： Zhiwei Zhu Taragay Oskiper Supun Samarasekera Rakesh Kumar Harpreet S. Sawhney Sarnoff Corporation Princeton NJ USA

In this paper, we study how to build a vision-based system for global localization with accuracies within 10cm. for robots and humans operating both indoors and outdoors over wide areas covering many square kilometers. In particular, we study the parameters of building a landmark database rapidly and utilizing that database online for real-time accurate global localization. Although the accuracy of traditional short-term motion based visual odometry systems has improved significantly in recent years, these systems alone cannot solve the drift problem over large areas. Landmark based localization combined with visual odometry is a viable solution to the large scale localization problem. However, a systematic study of the specification and use of such a landmark database has not been undertaken. We propose techniques to build and optimize a landmark database systematically and efficiently using visual odometry. First, topology inference is utilized to find overlapping images in the database. Second, bundle adjustment is used to refine the accuracy of each 3D landmark. Finally, the database is optimized to balance the size of the database with achievable accuracy. Once the landmark database is obtained, a new real-time global localization methodology that works both indoors and outdoors is proposed. We present results of our study on both synthetic and real data-sets that help us determine critical design parameters for the landmark database and the achievable accuracies of our proposed system.

关键词： Visual databases Image databases Cameras Robot vision systems Humans Large-scale systems Robustness Navigation Sensor systems Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-Fine Low-Rank Structure-from-Motion

Coarse-to-Fine Low-Rank Structure-from-Motion

引用

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

作者： A. Bartoli V. Gay-Bellile U. Castellani J. Peyras S. Olsen P. Sayd Institut Pascal Aubiere Auvergne-RhÃ´ne-Alpes FR CEA/List Saclay France VIP Sensors Inc. Verona Italy LASMEA Clermont Ferrand France DIKU Copenhagen Denmark

We address the problem of deformable shape and motion recovery from point correspondences in multiple perspective images. We use the low-rank shape model, i.e. the 3D shape is represented as a linear combination of unknown shape bases. We propose a new way of looking at the low-rank shape model. Instead of considering it as a whole, we assume a coarse-to-fine ordering of the deformation modes, which can be seen as a model prior. this has several advantages. First, the high level of ambiguity of the original low-rank shape model is drastically reduced since the shape bases can not anymore be arbitrarily re-combined. Second, this allows us to propose a coarse-to-fine reconstruction algorithm which starts by computing the mean shape and iteratively adds deformation modes. It directly gives the sought after metric model, thereby avoiding the difficult upgrading step required by most of the other methods. third, this makes it possible to automatically select the number of deformation modes as the reconstruction algorithm proceeds. We propose to incorporate two other priors, accounting for temporal and spatial smoothness, which are shown to improve the quality of the recovered model parameters. the proposed model and reconstruction algorithm are successfully demonstrated on several videos and are shown to outperform the previously proposed algorithms.

关键词： Shape Reconstruction algorithms Deformable models Videos Cameras computer vision Principal component analysis Terminology Optimization methods

来源：评论

学校读者我要写书评

暂无评论

ANSIG - An Analytic Signature for Permutation-Invariant Two-Dimensional Shape Representation

ANSIG - An Analytic Signature for Permutation-Invariant Two-...

引用

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

作者： Jose J. Rodrigues Pedro M. Q. Aguiar Joao M. F. Xavier Institute of Systems and Robotics IST Lisboa Portugal

Many applications require a computer representation of 2D shape, usually described by a set of 2D points. the challenge of this representation is that it must not only capture the characteristics of the shape but also be invariant to relevant transformations. Invariance to geometric transformations, such as translation, rotation and scale, has received attention in the past, usually under the assumption that the points are previously labeled, i.e., that the shape is characterized by an ordered set of landmarks. However, in many practical scenarios the landmarks are obtained from an automatic process, e.g., edge/corner detection, thus without natural ordering. In this paper, we represent 2D shapes in a way that is invariant to the permutation of the landmarks. Within our framework, a shape is mapped to an analytic function on the complex plane, leading to what we call its analytic signature (ANSIG). We show that different shapes lead to different ANSIGs but that shapes that differ by a permutation of the landmarks lead to the same ANSIG, i.e., that our representation is a maximal invariant with respect to the permutation group. To store an ANSIG, it suffices to sample it along a closed contour in the complex plane. We further show how easy it is to factor out geometric transformations when comparing shapes using the ANSIG representation. We illustrate the ANSIG capabilities in shape-based image classification.

关键词： Shape Iterative algorithms Image edge detection Robots Application software computer applications Image classification Two dimensional displays Registers Iterative closest point algorithm

来源：评论

学校读者我要写书评

暂无评论

Retinal Image Registration from 2D to 3D

Retinal Image Registration from 2D to 3D

引用

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

作者： Yuping Lin Gerard Medioni Computer Science Department University of Southern California Los Angeles CA USA

We propose a 2D registration method for multi-modal image sequences of the retinal fundus, and a 3D metric reconstruction of near planar surface from multiple views. there are two major contributions in our paper. For 2D registration, our method produces high registration rates while accounting for large modality differences. Compared with the state of the art method [5], our approach has higher registration rate (97.2% vs. 82.31%) while the computation time is much less. this is achieved by extracting features from the edge maps of the contrast enhanced images, and performing pairwise registration by matching the features in an iterative manner, maximizing the number of matches and estimating homographies accurately. the pairwise registration result is further globally optimized by an indirect registration process. For 3D registration part, images are registered to the reference frame by transforming points via a reconstructed 3D surface. the challenge is the reconstruction of a near planar surface, in which the shallow depth makes it a quasi-degenerate case for estimating the geometry from images. Our contribution is the proposed 4-pass bundle adjustment method that gives optimal estimation of all camera poses. With accurate camera poses, the 3D surface can be reconstructed using the images associated with the cameras with the largest baseline. Compared with state of the art 3D retinal image registration methods, our approach produces better results in all image sets.

关键词： Retina Image registration Image reconstruction Surface reconstruction Feature extraction Cameras Image sequences Geometry Iterative closest point algorithm Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Environmental information acquisition with deep learning

Environmental information acquisition with deep learning

引用

ieee Signal Processing and Communications Applications (SIU)

作者： Anıl Çetınsoy Yildiz Teknik Universitesi Istanbul TR

In this study, a system which describes the objects in the environment and the positions of these objects with each other has been developed. this system can be used for visually impaired people to learn what is happening in their surroundings and for young children to learn objects in their surroundings. In the study, a very successful environmental information acquisition tool was developed by using the latest image segmentation, object recognition and environment description algorithms.

关键词： computer vision Reactive power conferences Machine learning Image segmentation Object recognition pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Fast, Accurate Detection of 100,000 Object Classes on a Single Machine

Fast, Accurate Detection of 100,000 Object Classes on a Sing...

引用

ieee conference on computer vision and pattern recognition

作者： thomas Dean Mark A. Ruzon Mark Segal Jonathon Shlens Sudheendra Vijayanarasimhan Jay Yagnik Google Mountain View

ISBN: (纸本)9781467364102

Many object detection systems are constrained by the time required to convolve a target image with a bank of filters that code for different aspects of an object's appearance, such as the presence of component parts. We exploit locality-sensitive hashing to replace the dot-product kernel operator in the convolution with a fixed number of hash-table probes that effectively sample all of the filter responses in time independent of the size of the filter bank. To show the effectiveness of the technique, we apply it to evaluate 100,000 deformable-part models requiring over a million (part) filters on multiple scales of a target image in less than 20 seconds using a single multi-core processor with 20GB of RAM. this represents a speed-up of approximately 20,000 times-four orders of magnitude-when compared with performing the convolutions explicitly on the same hardware. While mean average precision over the full set of 100,000 object classes is around 0.16 due in large part to the challenges in gathering training data and collecting ground truth for so many classes, we achieve a mAP of at least 0.20 on a third of the classes and 0.30 or better on about 20% of the classes.

关键词： target image FILTER RESPONSE Filters Banks ground truth Classes CCDC26 gene random access machine FAM103A1 gene SUPPORT FRAME Convolution

来源：评论

学校读者我要写书评

暂无评论

Automatic Non-rigid Registration of 3D Dynamic Data for Facial Expression Synthesis and Transfer

Automatic Non-rigid Registration of 3D Dynamic Data for Faci...

引用

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

作者： Sen Wang Xianfeng David Gu Hong Qin Computer Science Department Stony Brook University-SUNY Stony Brook NY USA

Automatic non-rigid registration of 3D time-varying data is fundamental in many vision and graphics applications such as facial expression analysis, synthesis, and recognition. Despite many research advances in recent years, it still remains to be technically challenging, especially for 3D dynamic, densely-sampled facial data with a large number of degrees of freedom (necessarily used to represent rich and subtle facial expressions). In this paper, we present a new method for automatic non-rigid registration of 3D dynamic facial data using least-squares conformal maps, and based on this registration method, we also develop a new framework of facial expression synthesis and transfer. Nowadays more and more 3D dynamic, densely-sampled data become prevalent with the advancement of novel 3D scanning techniques. To analyze and utilize such huge 3D data, an efficient non-rigid registration algorithm is needed to establish one-to-one inter-frame correspondences. Towards this goal, a non-rigid registration algorithm of 3D dynamic facial data is developed by using least-squares conformal maps with additional feature correspondences detected by employing active appearance models (AAM). the proposed method with additional, interior feature constraints guarantees that the non-rigid data will be accurately registered. the least-squares conformal maps between two 3D surfaces are globally optimized with the least angle distortion and the resulting 2D maps are stable and one-to-one. Furthermore, by using this non-rigid registration method, we develop a new system of facial expression synthesis and transfer. Finally, we perform a series of experiments to evaluate our non-rigid registration method and demonstrate its efficacy and efficiency in the applications of facial expression synthesis and transfer.

关键词： Face detection Facial animation computer vision Graphics Humans Tracking Algorithm design and analysis Heuristic algorithms Active appearance model Deformable models

来源：评论

学校读者我要写书评

暂无评论

Extracting a Fluid Dynamic Texture and the Background from Video

Extracting a Fluid Dynamic Texture and the Background from V...

引用

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

作者： Bernard Ghanem Narendra Ahuja Beckman Institute for Advanced Science and Technology Department of Electrical and Computer E University of Illinois Urbana-Champaign Urbana IL USA

Given the video of a still background occluded by a fluid dynamic texture (FDT), this paper addresses the problem of separating the video sequence into its two constituent layers. One layer corresponds to the video of the unoccluded background, and the other to that of the dynamic texture, as it would appear if viewed against a black background. the model of the dynamic texture is unknown except that it represents fluid flow. We present an approach that uses the image motion information to simultaneously obtain a model of the dynamic texture and separate it from the background which is required to be still. Previous methods have considered occluding layers whose dynamics follows simple motion models (e.g. periodic or 2D parametric motion). FDTs considered in this paper exhibit complex stochastic motion. We consider videos showing an FDT layer (e.g. pummeling smoke or heavy rain) in front of a static background layer (e.g. brick building). We propose a novel method for simultaneously separating these two layers and learning a model for the FDT. Due to the fluid nature of the DT, we are required to learn a model for both the spatial appearance and the temporal variations (due to changes in density) of the FDT, along with a valid estimate of the background. We model the frames of a sequence as being produced by a continuous HMM, characterized by transition probabilities based on the Navier-Stokes equations for fluid dynamics, and by generation probabilities based on the convex matting of the FDT with the background. We learn the FDT appearance, the FDT temporal variations, and the background by maximizing their joint probability using Interactive Conditional Modes (ICM). Since the learned model is generative, it can be used to synthesize new videos with different backgrounds and density variations. Experiments on videos that we compiled demonstrate the performance of our method.

关键词： Fluid dynamics Hidden Markov models Video sequences Rain Navier-Stokes equations Character generation Layout Filters Fluid flow Stochastic processes

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：