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

220 篇 会议
5 篇 期刊文献
2 册 图书

馆藏范围

227 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

217 篇 工学
- 203 篇 计算机科学与技术...
- 25 篇 电气工程
- 20 篇 机械工程
- 4 篇 信息与通信工程
- 4 篇 控制科学与工程
- 4 篇 软件工程
- 1 篇 光学工程
- 1 篇 冶金工程
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 生物医学工程（可授...
- 1 篇 生物工程
7 篇 理学
- 2 篇 数学
- 2 篇 物理学
- 1 篇 大气科学
- 1 篇 海洋科学
- 1 篇 生物学
- 1 篇 系统科学
- 1 篇 统计学（可授理学、...
3 篇 医学
- 3 篇 临床医学
2 篇 管理学
- 2 篇 管理科学与工程(可...

主题

44 篇 computer vision
24 篇 pattern recognit...
23 篇 object recogniti...
20 篇 images
15 篇 face recognition
11 篇 object detection
9 篇 action recogniti...
9 篇 training
8 篇 image segmentati...
8 篇 feature extracti...
7 篇 image classifica...
6 篇 cameras
6 篇 gesture recognit...
6 篇 dataset
6 篇 machine learning
6 篇 recognition
5 篇 deep learning
5 篇 visualization
5 篇 image recognitio...
5 篇 shape

机构

6 篇 chinese acad sci...
4 篇 chinese univ hon...
4 篇 mpi intelligent ...
4 篇 carnegie mellon ...
4 篇 univ washington ...
3 篇 univ oxford oxfo...
3 篇 hong kong univ s...
3 篇 mit cambridge ma...
3 篇 univ calif berke...
2 篇 inria
2 篇 stevens inst tec...
2 篇 univ calif river...
2 篇 univ toronto on
2 篇 rensselaer polyt...
2 篇 georgia inst tec...
2 篇 swiss fed inst t...
2 篇 chinese acad sci...
2 篇 chinese acad sci...
2 篇 natl univ singap...
2 篇 swiss fed inst t...

作者

4 篇 hu weiming
3 篇 yuan chunfeng
3 篇 li stan z.
3 篇 lu cewu
3 篇 wen longyin
3 篇 jia jiaya
3 篇 murala subrahman...
3 篇 ji qiang
3 篇 salzmann mathieu
3 篇 shao ling
3 篇 vedaldi andrea
3 篇 yan shuicheng
3 篇 vipparthi santos...
3 篇 brandt jonathan
3 篇 hua gang
2 篇 kannala juho
2 篇 cucchiara rita
2 篇 ling haibin
2 篇 wang limin
2 篇 maji subhransu

语言

227 篇 英文

检索条件"任意字段=27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014"

共 227 条记录，以下是101-110 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：

Human Action recognition across Datasets by Foreground-weighted Histogram Decomposition 27

Human Action Recognition across Datasets by Foreground-weigh...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Sultani, Waqas Saleemi, Imran Univ Cent Florida Ctr Comp Vis Res Orlando FL 32816 USA

ISBN: (纸本)9781479951178

this paper attempts to address the problem of recognizing human actions while training and testing on distinct datasets, when test videos are neither labeled nor available during training. In this scenario, learning of a joint vocabulary, or domain transfer techniques are not applicable. We first explore reasons for poor classifier performance when tested on novel datasets, and quantify the effect of scene backgrounds on action representations and recognition. Using only the background features and partitioning of gist feature space, we show that the background scenes in recent datasets are quite discriminative and can be used classify an action with reasonable accuracy. We then propose a new process to obtain a measure of confidence in each pixel of the video being a foreground region, using motion, appearance, and saliency together in a 3D MRF based framework. We also propose multiple ways to exploit the foreground confidence: to improve bag-of-words vocabulary, histogram representation of a video, and a novel histogram decomposition based representation and kernel. We used these foreground confidences to recognize actions trained on one data set and test on a different data set. We have performed extensive experiments on several datasets that improve cross dataset recognition accuracy as compared to baseline methods.

关键词： action recognition cross dataset dataset bias foreground weighted representation

来源：评论

学校读者我要写书评

暂无评论

Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech recognition 27

Rate-Invariant Analysis of Trajectories on Riemannian Manifo...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Su, Jingyong Srivastava, Anuj de Souza, Fillipe D. M. Sarkar, Sudeep Texas Tech Univ Dept Math & Stat Lubbock TX 79409 USA Florida State Univ Dept Stat Tallahassee FL 32306 USA Univ S Florida Dept Comp Sci & Engn Tampa FL 33620 USA

ISBN: (纸本)9781479951178

In statistical analysis of video sequences for speech recognition, and more generally activity recognition, it is natural to treat temporal evolutions of features as trajectories on Riemannian manifolds. However, different evolution patterns result in arbitrary parameterizations of these trajectories. We investigate a recent framework from statistics literature [15] that handles this nuisance variability using a cost function/distance for temporal registration and statistical summarization & modeling of trajectories. It is based on a mathematical representation of trajectories, termed transported square-root vector field (TSRVF), and the L-2 norm on the space of TSRVFs. We apply this framework to the problem of speech recognition using both audio and visual components. In each case, we extract features, form trajectories on corresponding manifolds, and compute parametrization-invariant distances using TSRVFs for speech classification. On the OuluVS database the classification performance under metric increases significantly, by nearly 100% under both modalities and for all choices of features. We obtained speaker-dependent classification rate of 70% and 96% for visual and audio components, respectively.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Birdsnap: Large-scale Fine-grained Visual Categorization of Birds 27

Birdsnap: Large-scale Fine-grained Visual Categorization of ...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Berg, thomas Liu, Jiongxin Lee, Seung Woo Alexander, Michelle L. Jacobs, David W. Belhumeur, Peter N. Columbia Univ New York NY 10027 USA Univ Maryland College Pk MD USA

ISBN: (纸本)9781479951178

We address the problem of large-scale fine-grained visual categorization, describing new methods we have used to produce an online field guide to 500 North American bird species. We focus on the challenges raised when such a system is asked to distinguish between highly similar species of birds. First, we introduce one-vs-most classifiers. By eliminating highly similar species during training, these classifiers achieve more accurate and intuitive results than common one-vs-all classifiers. Second, we show how to estimate spatio-temporal class priors from observations that are sampled at irregular and biased locations. We show how these priors can be used to significantly improve performance. We then show state-of-the-art recognition performance on a new, large dataset that we make publicly available. these recognition methods are integrated into the online field guide, which is also publicly available.

关键词： Fine-grained visual categorization birds large-scale classification recognition species identification

来源：评论

学校读者我要写书评

暂无评论

Gait recognition under Speed Transition 27

Gait Recognition under Speed Transition

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Mansur, Al Makihara, Yasushi Aqmar, Rasyid Yagi, Yasushi Osaka Univ Inst Sci & Ind Res Ibaraki Osaka 5670047 Japan

ISBN: (纸本)9781479951178

this paper describes a method of gait recognition from image sequences wherein a subject is accelerating or decelerating. As a speed change occurs due to a change of pitch (the first-order derivative of a phase, namely, a gait stance) and/or stride, we model this speed change using a cylindrical manifold whose azimuth and height corresponds to the phase and the stride, respectively. A radial basis function (RBF) interpolation framework is used to learn subject specific mapping matrices for mapping from manifold to image space. Given an input image sequence of speed transited gait of a test subject, we estimate the mapping matrix of the test subject as well as the phase and stride sequence using an energy minimization framework considering the following three points: (1) fitness of the synthesized images to the input image sequence as well as to an eigenspace constructed by exemplars of training subjects;(2) smoothness of the phase and the stride sequence;and (3) pitch and stride fitness to the pitch-stride preference model. Using the estimated mapping matrix, we synthesize a constant-speed gait image sequence, and extract a conventional period-based gait feature from it for matching. We conducted experiments using real speed transited gait image sequences with 179 subjects and demonstrated the effectiveness of the proposed method.

关键词： image sequences Variable speed Locomotion Gait recognition Gait Phase MAPPING(MAthEMATICAL) Manifolds azimuth ENERGY MINIMISATION

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Visual Font recognition 27

Large-Scale Visual Font Recognition

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Chen, Guang Yang, Jianchao Jin, Hailin Brandt, Jonathan Shechtman, Eli Agarwala, Aseem Han, Tony X. Adobe Res San Jose CA USA Univ Missouri Columbia MO 65211 USA

ISBN: (纸本)9781479951178

this paper addresses the large-scale visual font recognition (VFR) problem, which aims at automatic identification of the typeface, weight, and slope of the text in an image or photo without any knowledge of content. Although visual font recognition has many practical applications, it has largely been neglected by the vision community. To address the VFR problem, we construct a large-scale dataset containing 2,420 font classes, which easily exceeds the scale of most image categorization datasets in computer vision. As font recognition is inherently dynamic and open-ended, i.e., new classes and data for existing categories are constantly added to the database over time, we propose a scalable solution based on the nearest class mean classifier (NCM). the core algorithm is built on local feature embedding, local feature metric learning and max-margin template selection, which is naturally amenable to NCM and thus to such open-ended classification problems. the new algorithm can generalize to new classes and new data at little added cost. Extensive experiments demonstrate that our approach is very effective on our synthetic test images, and achieves promising results on real world test images.

关键词： character recognition fine-grained recognition font recognition large-scale recognition font recognition Character recognition images New classes CWC22 gene VFR flight rule Automatic identification

来源：评论

学校读者我要写书评

暂无评论

Depth and Skeleton Associated Action recognition without Online Accessible RGB-D Cameras 27

Depth and Skeleton Associated Action Recognition without Onl...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Lin, Yen-Yu Hua, Ju-Hsuan Tang, Nick C. Chen, Min-Hung Liao, Hong-Yuan Mark Acad Sinica Taipei Taiwan Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781479951178

the recent advances in RGB-D cameras have allowed us to better solve increasingly complex computer vision tasks. However, modern RGB-D cameras are still restricted by the short effective distances. the limitation may make RGB-D cameras not online accessible in practice, and degrade their applicability. We propose an alternative scenario to address this problem, and illustrate it with the application to action recognition. We use Kinect to offline collect an auxiliary, multi-modal database, in which not only the RGB videos but also the depth maps and skeleton structures of actions of interest are available. Our approach aims to enhance action recognition in RGB videos by leveraging the extra database. Specifically, it optimizes a feature transformation, by which the actions to be recognized can be concisely reconstructed by entries in the auxiliary database. In this way, the inter-database variations are adapted. More importantly, each action can be augmented with additional depth and skeleton images retrieved from the auxiliary database. the proposed approach has been evaluated on three benchmarks of action recognition. the promising results manifest that the augmented depth and skeleton features can lead to remarkable boost in recognition accuracy.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Cause and Effect Analysis of Motion Trajectories for Modeling Actions 27

A Cause and Effect Analysis of Motion Trajectories for Model...

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Narayan, Sanath Ramakrishnan, Kalpathi R. Indian Inst Sci Dept Elect Engn Bangalore 560012 Karnataka India

ISBN: (纸本)9781479951178

An action is typically composed of different parts of the object moving in particular sequences. the presence of different motions (represented as a 1D histogram) has been used in the traditional bag-of-words (BoW) approach for recognizing actions. However the interactions among the motions also form a crucial part of an action. Different object-parts have varying degrees of interactions with the other parts during an action cycle. It is these interactions we want to quantify in order to bring in additional information about the actions. In this paper we propose a causality based approach for quantifying the interactions to aid action classification. Granger causality is used to compute the cause and effect relationships for pairs of motion trajectories of a video. A 2D histogram descriptor for the video is constructed using these pairwise measures. Our proposed method of obtaining pairwise measures for videos is also applicable for large datasets. We have conducted experiments on challenging action recognition databases such as HMDB51 and UCF50 and shown that our causality descriptor helps in encoding additional information regarding the actions and performs on par with the state-of-the art approaches. Due to the complementary nature, a further increase in performance can be observed by combining our approach with state-of-the-art approaches.

关键词： Action recognition Granger Causality Interaction

来源：评论

学校读者我要写书评

暂无评论

Multi-View Super Vector for Action recognition 27

Multi-View Super Vector for Action Recognition

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Cai, Zhuowei Wang, Limin Peng, Xiaojiang Qiao, Yu Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Comp Vis & Pattern Recognit Beijing Peoples R China Chinese Univ Hong Kong Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781479951178

Images and videos are often characterized by multiple types of local descriptors such as SIFT, HOG and HOF, each of which describes certain aspects of object feature. recognition systems benefit from fusing multiple types of these descriptors. Two widely applied fusion pipelines are descriptor concatenation and kernel average. the first one is effective when different descriptors are strongly correlated, while the second one is probably better when descriptors are relatively independent. In practice, however, different descriptors are neither fully independent nor fully correlated, and previous fusion methods may not be satisfying. In this paper, we propose a new global representation, Multi-View Super Vector (MVSV), which is composed of relatively independent components derived from a pair of descriptors. Kernel average is then applied on these components to produce recognition result. To obtain MVSV, we develop a generative mixture model of probabilistic canonical correlation analyzers (M-PCCA), and utilize the hidden factors and gradient vectors of M-PCCA to construct MVSV for video representation. Experiments on video based action recognition tasks show that MVSV achieves promising results, and outperforms FV and VLAD with descriptor concatenation or kernel average fusion strategy.

关键词： action recognition canonical correlation analysis mixture model multi-view

来源：评论

学校读者我要写书评

暂无评论

An Attention-based Activity recognition for Egocentric Video

An Attention-based Activity Recognition for Egocentric Video

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Matsuo, Kenji Yamada, Kentaro Ueno, Satoshi Naito, Sei KDDI R&D Labs Inc Fujimino Saitama Japan

ISBN: (纸本)9781479943098

In this paper, we propose a human activity recognition method from first-person videos, which provides a supplementary method to improve the recognition accuracy. Conventional methods detect objects and derive a user's behavior based on their taxonomy. One of the recent works has achieved accuracy improvement by determining key objects based on hand manipulation. However, such manipulation-based approach has a restriction on applicable scenes and object types because the user's hands don't always present significant information. In contrast, our proposed attention-based approach provides a solution to detect visually salient objects as key objects in a non-contact manner. Experimental results show that the proposed method classifies first-person actions more accurately than the previous method by 6.4 percentage points and its average accuracy reaches 43.3%.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Pulling things out of Perspective 27

Pulling Things out of Perspective

引用

27th ieee conference on computer vision and pattern recognition (cvpr)

作者： Ladicky, L'ubor Shi, Jianbo Pollefeys, Marc Swiss Fed Inst Technol Zurich Switzerland Univ Penn Philadelphia PA 19104 USA

ISBN: (纸本)9781479951178

the limitations of current state-of-the-art methods for single-view depth estimation and semantic segmentations are closely tied to the property of perspective geometry, that the perceived size of the objects scales inversely with the distance. In this paper, we show that we can use this property to reduce the learning of a pixel-wise depth classifier to a much simpler classifier predicting only the likelihood of a pixel being at an arbitrarily fixed canonical depth. the likelihoods for any other depths can be obtained by applying the same classifier after appropriate image manipulations. Such transformation of the problem to the canonical depth removes the training data bias towards certain depths and the effect of perspective. the approach can be straight-forwardly generalized to multiple semantic classes, improving both depth estimation and semantic segmentation performance by directly targeting the weaknesses of independent approaches. Conditioning the semantic label on the depth provides a way to align the data to their physical scale, allowing to learn a more discriminative classifier. Conditioning depth on the semantic class helps the classifier to distinguish between ambiguities of the otherwise ill-posed problem. We tested our algorithm on the KITTI road scene dataset and NYU2 indoor dataset and obtained obtained results that significantly outperform current state-of-the-art in both single-view depth and semantic segmentation domain.

关键词： Depth Estimation Object recognition Semantic 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23页 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：