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

858 篇 会议

馆藏范围

858 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

853 篇 工学
- 838 篇 计算机科学与技术...
- 27 篇 软件工程
- 15 篇 生物工程
- 10 篇 光学工程
- 9 篇 机械工程
- 8 篇 信息与通信工程
- 5 篇 控制科学与工程
- 3 篇 电气工程
- 3 篇 电子科学与技术（可...
- 3 篇 生物医学工程（可授...
- 2 篇 化学工程与技术
- 1 篇 建筑学
- 1 篇 交通运输工程
31 篇 理学
- 15 篇 生物学
- 10 篇 数学
- 9 篇 物理学
- 5 篇 统计学（可授理学、...
- 3 篇 化学
- 1 篇 地质学
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...
3 篇 医学
- 3 篇 临床医学
- 2 篇 基础医学(可授医学...
- 1 篇 公共卫生与预防医...
- 1 篇 药学(可授医学、理...

主题

362 篇 deep learning
359 篇 recognition: det...
358 篇 categorization
357 篇 retrieval
128 篇 vision applicati...
121 篇 low-level vision
119 篇 representation l...
92 篇 vision + languag...
69 篇 segmentation
68 篇 image and video ...
63 篇 scene analysis a...
60 篇 grouping and sha...
54 篇 face
52 篇 gesture
51 篇 and body pose
51 篇 vision + graphic...
48 篇 computational ph...
45 篇 video analytics
44 篇 action recogniti...
42 篇 datasets and eva...

机构

27 篇 peng cheng lab p...
26 篇 univ chinese aca...
23 篇 chinese univ hon...
17 篇 sensetime res pe...
17 篇 nanyang technol ...
15 篇 univ sci & techn...
15 篇 carnegie mellon ...
15 篇 tsinghua univ pe...
15 篇 sun yat sen univ...
14 篇 johns hopkins un...
12 篇 stanford univ st...
11 篇 peking univ peop...
11 篇 incept inst arti...
11 篇 huawei noahs ark...
10 篇 facebook ai res ...
10 篇 univ maryland co...
10 篇 shanghai jiao to...
10 篇 univ calif berke...
9 篇 georgia inst tec...
9 篇 swiss fed inst t...

作者

10 篇 zhang lei
10 篇 wang xiaogang
10 篇 liu wei
10 篇 shao ling
9 篇 zheng wei-shi
9 篇 loy chen change
8 篇 timofte radu
7 篇 chun se young
7 篇 tao dacheng
7 篇 lin liang
7 篇 lin dahua
7 篇 zuo wangmeng
7 篇 yan junjie
7 篇 cheng ming-ming
6 篇 van gool luc
6 篇 chen xilin
6 篇 tian qi
6 篇 rohrbach marcus
6 篇 ji rongrong
6 篇 khan fahad shahb...

语言

858 篇 英文

检索条件"任意字段=32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019"

共 858 条记录，以下是41-50 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：

Local detection of stereo occlusion boundaries 32

Local detection of stereo occlusion boundaries

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Wang, Jialiang Zickler, Todd Harvard Univ Cambridge MA 02138 USA

ISBN: (纸本)9781728132938

Stereo occlusion boundaries are one-dimensional structures in the visual field that separate foreground regions of a scene that are visible to both eyes (binocular regions) from background regions of a scene that are visible to only one eye (monocular regions). Stereo occlusion boundaries often coincide with object boundaries, and localizing them is useful for tasks like grasping, manipulation, and navigation. This paper describes the local signatures for stereo occlusion boundaries that exist in a stereo cost volume, and it introduces a local detector for them based on a simple feedforward network with relatively small receptive fields. The local detector produces better boundaries than many other stereo methods, even without incorporating explicit stereo matching, top-down contextual cues, or single-image boundary cues based on texture and intensity.

关键词： 3D from Multiview and Sensors Grouping and Sha Low-level vision Physics-based vision and Shape-from-X Segmentation

来源：评论

学校读者我要写书评

暂无评论

Spectral Metric for Dataset Complexity Assessment 32

Spectral Metric for Dataset Complexity Assessment

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Branchaud-Charron, Frederic Achkar, Andrew Jodoin, Pierre-Marc Univ Sherbrooke Sherbrooke PQ Canada Miovision Inc Kitchener ON Canada

ISBN: (纸本)9781728132938

In this paper, we propose a new measure to gauge the complexity of image classification problems. Given an annotated image dataset, our method computes a complexity measure called the cumulative spectral gradient (CSG) which strongly correlates with the test accuracy of convolutional neural networks (CNN). The CSG measure is derived from the probabilistic divergence between classes in a spectral clustering framework. We show that this metric correlates with the overall separability of the dataset and thus its inherent complexity. As will be shown, our metric can be used for dataset reduction, to assess which classes are more difficult to disentangle, and approximate the accuracy one could expect to get with a CNN. Results obtained on 11 datasets and three CNN models reveal that our method is more accurate and faster than previous complexity measures.

关键词： Categorization computer vision Theory Datasets and Evaluation Deep Learning recognition: Detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments 32

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Chen, Howard Suhr, Alane Misra, Dipendra Snavely, Noah Artzi, Yoav ASAPP Inc New York NY 10007 USA Cornell Univ Dept Comp Sci New York NY 10021 USA Cornell Univ Cornell Tech New York NY 10021 USA Cornell Univ New York NY 10021 USA

ISBN: (纸本)9781728132938

We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent must first follow navigation instructions in a Street View environment to a goal position, and then guess a location in its observed environment described in natural language to find a hidden object. The data contains 9326 examples of English instructions and spatial descriptions paired with demonstrations. We perform qualitative linguistic analysis, and show that the data displays a rich use of spatial reasoning. Empirical analysis shows the data presents an open challenge to existing methods.

关键词： Datasets and Evaluation vision + Language Visual Reasoning

来源：评论

学校读者我要写书评

暂无评论

PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval 32

PCAN: 3D Attention Map Learning Using Contextual Information...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Zhang, Wenxiao Xiao, Chunxia Wuhan Univ Sch Comp Sci Wuhan Peoples R China

ISBN: (纸本)9781728132938

Point cloud based retrieval for place recognition is an emerging problem in vision field. The main challenge is how to find an efficient way to encode the local features into a discriminative global descriptor. In this paper, we propose a Point Contextual Attention Network (PCAN), which can predict the significance of each local point feature based on point context. Our network makes it possible to pay more attention to the task-relevent features when aggregating local features. Experiments on various benchmark datasets show that the proposed network can provide outperformance than current state-of-the-art approaches.

关键词： 3D from Multiview and Sensors Categorization recognition: Detection Representation Learning Retrieval

来源：评论

学校读者我要写书评

暂无评论

Timeception for Complex Action recognition 32

Timeception for Complex Action Recognition

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Hussein, Noureldien Gavves, Efstratios Smeulders, Arnold W. M. Univ Amsterdam QUVA Lab Amsterdam Netherlands

ISBN: (纸本)9781728132938

This paper focuses on the temporal aspect for recognizing human activities in videos;an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to "Complex Action": a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.

关键词： Action recognition Video Analytics

来源：评论

学校读者我要写书评

暂无评论

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs 32

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CN...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Singh, Pravendra Verma, Vinay Kumar Rai, Piyush Namboodiri, Vinay P. IIT Kanpur Dept Comp Sci & Engn Kanpur Uttar Pradesh India

ISBN: (纸本)9781728132938

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG[31] and ResNet [8]. We find that after replacing the standard convolutional filters in these architectures with our proposed HetConv filters, we achieve 3X to 8X FLOPs based improvement in speed while still maintaining (and sometimes improving) the accuracy. We also compare our proposed convolutions with group/depth wise convolutions and show that it achieves more FLOPs reduction with significantly higher accuracy.

关键词： Categorization computer vision Theory Deep Learning recognition: Detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors 32

Assisted Excitation of Activations: A Learning Technique to ...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Derakhshani, Mohammad Mahdi Masoudnia, Saeed Shaker, Amir Hossein Mersa, Omid Sadeghi, Mohammad Amin Rastegari, Mohammad Araabi, Babak N. Univ Tehran Dept Elect & Comp Engn MLCM Lab Tehran Iran Allen Inst Artificial Intelligence AI2 Seattle WA USA

ISBN: (纸本)9781728132938

We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize (Figure 2). In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy tradeoff (Figure 1). [GRAPHICS] Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO *** technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors.

关键词： Categorization computer vision Theory Datasets and Evaluation Deep Learning recognition: Detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Revisiting Self-Supervised Visual Representation Learning 32

Revisiting Self-Supervised Visual Representation Learning

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Kolesnikov, Alexander Zhai, Xiaohua Beyer, Lucas Google Brain Zurich Switzerland

ISBN: (纸本)9781728132938

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging benchmarks. A large number of the pretext tasks for self-supervised learning have been studied, but other important aspects, such as the choice of convolutional neural networks (CNN), has not received equal attention. Therefore, we revisit numerous previously proposed self-supervised models, conduct a thorough large scale study and, as a result, uncover multiple crucial insights. We challenge a number of common practices in self-supervised visual representation learning and observe that standard recipes for CNN design do not always translate to self-supervised representation learning. As part of our study, we drastically boost the performance of previously proposed techniques and outperform previously published state-of-the-art results by a large margin.

关键词： Deep Learning Low-level vision Representation Learning

来源：评论

学校读者我要写书评

暂无评论

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks 32

Interpretable and Fine-Grained Visual Explanations for Convo...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Wagner, Joerg Koehler, Jan Mathias Gindele, Tobias Hetzel, Leon Wiedemer, Jakob Thaddaeus Behnke, Sven Bosch Ctr Artificial Intelligence BCAI Renningen Germany Univ Bonn Bonn Germany

ISBN: (纸本)9781728132938

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which highlights the evidence in the input image for a specific prediction. Our approach is based on a novel technique to defend against adversarial evidence (i.e. faulty evidence due to artefacts) by filtering gradients during optimization. The defense does not depend on human-tuned parameters. It enables explanations which are both fine-grained and preserve the characteristics of images, such as edges and colors. The explanations are interpretable, suited for visualizing detailed evidence and can be tested as they are valid model inputs. We qualitatively and quantitatively evaluate our approach on a multitude of models and datasets.

关键词： Categorization Deep Learning Others recognition: Detection Retrieval vision Applications and Systems Visual R

来源：评论

学校读者我要写书评

暂无评论

Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture 32

Texture Mixer: A Network for Controllable Synthesis and Inte...

引用

32nd ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Yu, Ning Barnes, Connelly Shechtman, Eli Amirghodsi, Sohrab Lukac, Michal Univ Maryland College Pk MD 20742 USA Max Planck Inst Informat Saarbrucken Germany Adobe Res San Jose CA USA Univ Virginia Charlottesville VA 22903 USA

ISBN: (纸本)9781728132938

This paper addresses the problem of interpolating visual textures. We formulate this problem by requiring (1) by example controllability and (2) realistic and smooth interpolation among an arbitrary number of texture samples. To solve it we propose a neural network trained simultaneously on a reconstruction task and a generation task, which can project texture examples onto a latent space where they can be linearly interpolated and projected back onto the image domain, thus ensuring both intuitive control and realistic results. We show our method outperforms a number of base-lines according to a comprehensive suite of metrics as well as a user study. We further show several applications based on our technique, which include texture brush, texture dis-solve, and animal hybridization.

关键词： Image and Video Synthesis vision + Graphics

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86页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：