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

320 篇 会议

馆藏范围

320 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

318 篇 工学
- 318 篇 计算机科学与技术...
- 199 篇 控制科学与工程
- 78 篇 机械工程
- 3 篇 软件工程
- 2 篇 光学工程
- 1 篇 生物工程
200 篇 理学
- 199 篇 系统科学
- 2 篇 物理学
- 1 篇 生物学

主题

135 篇 task analysis
122 篇 computer vision
122 篇 training
90 篇 computer archite...
89 篇 feature extracti...
77 篇 visualization
55 篇 three-dimensiona...
55 篇 computational mo...
45 篇 neural networks
41 篇 semantics
35 篇 cameras
29 篇 image segmentati...
29 篇 convolution
27 篇 face
25 篇 kernel
25 篇 estimation
23 篇 pattern recognit...
23 篇 shape
23 篇 two dimensional ...
22 篇 face recognition

机构

16 篇 univ chinese aca...
10 篇 carnegie mellon ...
8 篇 stanford univ st...
6 篇 cas ctr excellen...
6 篇 univ sci & techn...
6 篇 adobe res san jo...
6 篇 sensetime res pe...
5 篇 univ oxford oxfo...
5 篇 swiss fed inst t...
5 篇 shanghai jiao to...
5 篇 univ calif berke...
5 篇 nvidia santa cla...
5 篇 nanyang technol ...
4 篇 google mountain ...
4 篇 univ edinburgh e...
4 篇 chinese univ hon...
4 篇 microsoft res as...
4 篇 univ tokyo
4 篇 casia cripac peo...
4 篇 univ adelaide ad...

作者

5 篇 kautz jan
4 篇 van gool luc
4 篇 gupta abhinav
4 篇 grauman kristen
4 篇 huang kaiqi
4 篇 belongie serge
4 篇 wang xiaogang
4 篇 hospedales timot...
4 篇 yang ming-hsuan
4 篇 xiang tao
4 篇 wang gang
3 篇 fua pascal
3 篇 girshick ross
3 篇 liu yang
3 篇 darrell trevor
3 篇 feng jiashi
3 篇 borji ali
3 篇 shao jing
3 篇 davis larry s.
3 篇 li fei-fei

语言

320 篇 英文

检索条件"任意字段=31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018"

共 320 条记录，以下是91-100 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：

Multi-Level Factorisation Net for Person Re-Identification 31

Multi-Level Factorisation Net for Person Re-Identification

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Chang, Xiaobin Hospedales, Timothy M. Xiang, Tao Queen Mary Univ London London England Univ Edinburgh Edinburgh Midlothian Scotland

ISBN: (纸本)9781538664209

Key to effective person re-identification (Re-ID) is modelling discriminative and view-invariant factors of person appearance at both high and low semantic levels. Recently developed deep Re-ID models either learn a holistic single semantic level feature representation and/or require laborious human annotation of these factors as attributes. We propose Multi-Level Factorisation Net (MLFN), a novel network architecture that factorises the visual appearance of a person into latent discriminative factors at multiple semantic levels without manual annotation. MLFN is composed of multiple stacked blocks. Each block contains multiple factor modules to model latent factors at a specific level, and factor selection modules that dynamically select the factor modules to interpret the content of each input image. The outputs of the factor selection modules also provide a compact latent factor descriptor that is complementary to the conventional deeply learned features. MLFN achieves state-of-the-art results on three Re-ID datasets, as well as compelling results on the general object categorisation CIFAR-100 dataset.

关键词： Semantics computer architecture Visualization Feature extraction Frequency modulation Task analysis Cameras

来源：评论

学校读者我要写书评

暂无评论

Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation 31

Aligning Infinite-Dimensional Covariance Matrices in Reprodu...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Zhang, Zhen Wang, Mianzhi Huang, Yan Nehorai, Arye Washington Univ St Louis MO 63130 USA

ISBN: (纸本)9781538664209

Domain shift, which occurs when there is a mismatch between the distributions of training (source) and testing (target) datasets, usually results in poor performance of the trained model on the target domain. Existing algorithms typically solve this issue by reducing the distribution discrepancy in the input spaces. However, for kernel-based learning machines, performance highly depends on the statistical properties of data in reproducing kernel Hilbert spaces (RKHS). Motivated by these considerations, we propose a novel strategy for matching distributions in RKHS, which is done by aligning the RKHS covariance matrices (descriptors) across domains. This strategy is a generalization of the correlation alignment problem in Euclidean spaces to (potentially) infinite-dimensional feature spaces. In this paper, we provide two alignment approaches, for both of which we obtain closed-form expressions via kernel matrices. Furthermore, our approaches are scalable to large datasets since they can naturally handle out-of-sample instances. We conduct extensive experiments (248 domain adaptation tasks) to evaluate our approaches. Experiment results show that our approaches outperform other state-of-the-art methods in both accuracy and computationally efficiency.

关键词： Kernel Covariance matrices Correlation Maximum likelihood estimation Hilbert space Testing Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Arbitrary style Transfer with Deep Feature Reshuffle 31

Arbitrary Style Transfer with Deep Feature Reshuffle

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Gu, Shuyang Chen, Congliang Liao, Jing Yuan, Lu Univ Sci & Technol China Hefei Anhui Peoples R China Peking Univ Beijing Peoples R China Microsoft Res Beijing Peoples R China

ISBN: (纸本)9781538664209

This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle connects both global and local style losses respectively used by most parametric and non-parametric neural style transfer methods. This simple idea can effectively address the challenging issues in existing style transfer methods. On one hand, it can avoid distortions in local style patterns, and allow semantic-level transfer, compared with neural parametric methods. On the other hand, it can preserve globally similar appearance to the style image, and avoid wash-out artifacts, compared with neural non-parametric methods. Based on the proposed loss, we also present a progressive feature-domain optimization approach. The experiments show that our method is widely applicable to various styles, and produces better quality than existing methods.

关键词： Optimization Parametric statistics Semantics Rendering (computer graphics) Decoding Correlation Acceleration

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Image Transformation via Scale Space Decomposition 31

Intrinsic Image Transformation via Scale Space Decomposition

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Cheng, Lechao Zhang, Chengyi Liao, Zicheng Zhejiang Univ Coll Comp Sci Hangzhou Zhejiang Peoples R China Alibaba Zhejiang Univ Joint Inst Frontier Technol Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538664209

We introduce a new network structure for decomposing an image into its intrinsic albedo and shading. We treat it as an image-to-image transformation problem and explore the scale space of the input and output. By expanding the output images (albedo and shading) into their Laplacian pyramid components, we develop a multi-channel architecture that learns the image-to-image transformation function in successive frequency bands in parallel, within each channel is a filly convolutional neural network. This network architecture is general and extensible, and has demonstrated excellent performance on the task of intrinsic image decomposition. We evaluate the network on two benchmark datasets: the MPI-Sintel dataset and the MIT Intrinsic Images dataset. Both quantitative and qualitative results show our model delivers a clear progression over state-of-the-art.

关键词： Laplace equations Task analysis Training Space exploration Network architecture computer architecture Transforms

来源：评论

学校读者我要写书评

暂无评论

PIXOR: Real-time 3D Object Detection from Point Clouds 31

PIXOR: Real-time 3D Object Detection from Point Clouds

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Yang, Bin Luo, Wenjie Urtasun, Raquel Univ Toronto Uber Adv Technol Grp Toronto ON Canada

ISBN: (纸本)9781538664209

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Speed is critical as detection is a necessary component for safety. Existing approaches are, however expensive in computation due to high dimensionality of point clouds. We utilize the 3D data more efficiently by representing the scene from the Bird's Eye View (BEV), and propose PIXOR, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions. The input representation, network architecture, and model optimization are specially designed to balance high accuracy and real-time efficiency. We validate PIXOR on two datasets: the KITTI BEV object detection benchmark, and a large-scale 3D vehicle detection benchmark. In both datasets we show that the proposed detector surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS.

关键词： Three-dimensional displays Object detection Detectors Feature extraction Two dimensional displays Real-time systems computer architecture

来源：评论

学校读者我要写书评

暂无评论

PPFNet: Global Context Aware Local Features for Robust 3D Point Matching 31

PPFNet: Global Context Aware Local Features for Robust 3D Po...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Deng, Haowen Birdal, Tolga Ilie, Slobodan Tech Univ Munich Munich Germany Siemens AG Munchen Munich Germany Natl Univ Def Technol Changsha Hunan Peoples R China

ISBN: (纸本)9781538664209

We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds. PPFNet learns local descriptors on pure geometry and is highly aware of the global context, an important cue in deep learning. Our 3D representation is computed as a collection of point-pair-features combined with the points and normals within a local vicinity. Our permutation invariant network design is inspired by PointNet and sets PPFNet to be ordering-free. As opposed to voxelization, our method is able to consume raw point clouds to exploit the full sparsity. PPFNet uses a novel N-tuple loss and architecture injecting the global information naturally into the local descriptor. It shows that context awareness also boosts the local feature representation. Qualitative and quantitative evaluations of our network suggest increased recall, improved robustness and invariance as well as a vital step in the 3D descriptor extraction performance.

关键词： Three-dimensional displays Geometry Task analysis computer architecture Two dimensional displays Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Im2Flow: Motion Hallucination from static Images for Action recognition 31

Im2Flow: Motion Hallucination from Static Images for Action ...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Gao, Ruohan Xiong, Bo Grauman, Kristen UT Austin Austin TX 78712 USA

ISBN: (纸本)9781538664209

Existing methods to recognize actions in static images take the images at their face value, learning the appearances-objects, scenes, and body poses-that distinguish each action class. However, such models are deprived of the rich dynamic structure and motions that also define human activity. We propose an approach that hallucinates the unobserved future motion implied by a single snapshot to help static-image action recognition. The key idea is to learn a prior over short-term dynamics from thousands of unlabeled videos, infer the anticipated optical flow on novel static images, and then train discriminative models that exploit both streams of information. Our main contributions are twofold. First, we devise an encoder-decoder convolutional neural network and a novel optical flow encoding that can translate a static image into an accurate flow map. Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition. On seven datasets, we demonstrate the power of the approach. It not only achieves state-of-the-art accuracy for dense optical flow prediction, but also consistently enhances recognition of actions and dynamic scenes.

关键词： Videos Optical imaging Image recognition Dynamics Visualization Encoding Training

来源：评论

学校读者我要写书评

暂无评论

On the Importance of Label Quality for Semantic Segmentation 31

On the Importance of Label Quality for Semantic Segmentation

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Zlateski, Aleksandar Jaroensri, Ronnachai Sharma, Prafull Durand, Fredo MIT Cambridge MA 02139 USA

ISBN: (纸本)9781538664209

Convolutional networks (ConvNets) have become the dominant approach to semantic image segmentation. Producing accurate, pixel level labels required for this task is a tedious and time consuming process;howevet;producing approximate. coarse labels could take only a fraction of the time and clbrt. We investigate the relationship between the quality of labels and the performance of ConvNets for semantic segmentation. We create a very large synthetic dataset with perfectly labeled street view scenes. From these perfect labels, we synthetically coarsen labels with different qualities and estimate human hours required for producing them. We peiform a series of experiments by training ConvNets with a varying number of training images and label qualify. We found that the performance of ConvNets mostly depends on the time spent creating the training labels. That is, a larger coarsely annotated dataset can yield the same performance as a smaller finely annotated one. Furthermore. fine tuning coarsely pre trained ConvNets with few finely-annotated labels can yield comparable or superior performance to training it with a large amount of finely annotated labels alone, at a fraction of the labeling cost. We demonstrate that our result is also valid for different network architectures, and various object classes in an urban scene.

关键词： computer vision pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Sliced Wasserstein Distance for Learning Gaussian Mixture Models 31

Sliced Wasserstein Distance for Learning Gaussian Mixture Mo...

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Kolouri, Soheil Rohde, Gustavo K. Hoffmann, Heiko HRL Labs LLC Malibu CA 90265 USA Univ Virginia Charlottesville VA 22903 USA

ISBN: (纸本)9781538664209

Gaussian mixture models (GMM) are powerful parametric tools with many applications in machine learning and computer vision. Expectation maximization (EM) is the most popular algorithm for estimating the GMM parameters. However, EM guarantees only convergence to a stationary point of the log-likelihood function, which could be arbitrarily worse than the optimal solution. Inspired by the relationship between the negative log-likelihood function and the Kullback-Leibler (KL) divergence, we propose an alternative formulation for estimating the GMM parameters using the sliced Wasserstein distance, which gives rise to a new algorithm. Specifically, we propose minimizing the sliced-Wasserstein distance between the mixture model and the data distribution with respect to the GMM parameters. In contrast to the KL-divergence, the energy landscape for the sliced-Wasserstein distance is more well-behaved and therefore more suitable for a stochastic gradient descent scheme to obtain the optimal GMM parameters. We show that our formulation results in parameter estimates that are more robust to random initializations and demonstrate that it can estimate high-dimensional data distributions more faithfully than the EM algorithm.

关键词： Radon Transforms Kernel Gaussian mixture model Machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Lean Multiclass Crowdsourcing 31

Lean Multiclass Crowdsourcing

引用

31st ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Van Horn, Grant Branson, steve Loarie, Scott Belongie, Serge Perona, Pietro CALTECH Pasadena CA 91125 USA iNaturalist San Francisco CA USA Cornell Tech New York NY USA

ISBN: (纸本)9781538664209

We introduce a method for efficiently crowdsourcing multiclass annotations in challenging, real world image datasets. Our method is designed to minimize the number of human annotations that are necessary to achieve a desired level of confidence on class labels. It is based on combining models of worker behavior with computer vision. Our method is general: it can handle a large number of classes, worker labels that come from a taxonomy rather than a flat list, and can model the dependence of labels when workers can see a history of previous annotations. Our method may be used as a drop-in replacement for the majority vote algorithms used in online crowdsourcing services that aggregate multiple human annotations into a final consolidated label. In experiments conducted on two real-life applications we find that our method can reduce the number of required annotations by as much as a factor of 5.4 and can reduce the residual annotation error by up to 90% when compared with majority voting. Furthermore, the online risk estimates of the models may be used to sort the annotated collection and minimize subsequent expert review effort.

关键词： Task analysis Computational modeling Crowdsourcing Taxonomy Predictive models computer vision Birds

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32页 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：