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

212 篇 会议

馆藏范围

212 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

209 篇 工学
- 209 篇 计算机科学与技术...
- 186 篇 电气工程
- 169 篇 机械工程
- 3 篇 软件工程
- 2 篇 光学工程
- 2 篇 信息与通信工程
- 1 篇 电子科学与技术（可...
- 1 篇 控制科学与工程
- 1 篇 生物工程
- 1 篇 安全科学与工程
3 篇 理学
- 2 篇 物理学
- 1 篇 生物学
- 1 篇 系统科学

主题

131 篇 computer vision
68 篇 images
45 篇 training
36 篇 visualization
32 篇 computer archite...
25 篇 semantics
24 篇 computational mo...
24 篇 estimation
18 篇 neural networks
18 篇 feature extracti...
16 篇 three-dimensiona...
16 篇 image segmentati...
16 篇 optimization
16 篇 modulation
16 篇 filtration
15 篇 pattern recognit...
15 篇 dataset
15 篇 ofdm
15 篇 signal processin...
15 篇 clocks

机构

9 篇 univ chinese aca...
6 篇 carnegie mellon ...
5 篇 mit cambridge ma...
5 篇 kaust thuwal
5 篇 chinese acad sci...
5 篇 stanford univ st...
4 篇 natl univ singap...
4 篇 univ calif berke...
4 篇 max planck inst ...
3 篇 ist austria klos...
3 篇 chinese acad sci...
3 篇 univ sci & techn...
3 篇 peking univ inst...
3 篇 ist italiano tec...
3 篇 australian natl ...
3 篇 univ sydney nsw
3 篇 tech univ dresde...
3 篇 adobe res san jo...
3 篇 swiss fed inst t...
2 篇 natl res univ hi...

作者

4 篇 ghanem bernard
4 篇 schiele bernt
3 篇 swoboda paul
3 篇 murino vittorio
3 篇 fritz mario
3 篇 feng jiashi
3 篇 pollefeys marc
3 篇 rother carsten
2 篇 xue jia
2 篇 komodakis nikos
2 篇 andres bjoern
2 篇 busch christoph
2 篇 agustsson eiriku...
2 篇 singh vikas
2 篇 beksi william j.
2 篇 wang liang
2 篇 darrell trevor
2 篇 dana kristin
2 篇 huang yan
2 篇 rivadeneira rafa...

语言

211 篇 英文
1 篇 日文

检索条件"任意字段=30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017"

共 212 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：

Gaze Embeddings for Zero-Shot Image Classification 30

Gaze Embeddings for Zero-Shot Image Classification

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Karessli, Nour Akata, Zeynep Schiele, Bernt Bulling, Andreas Max Planck Inst Informat Saarland Informat Campus Saarbrucken Germany Univ Amsterdam Amsterdam Machine Learning Lab Amsterdam Netherlands Eyeem Berlin Germany

ISBN: (纸本)9781538604571

Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as auxiliary information, exploiting that even nonexpert users have a natural ability to judge class membership. We present a data collection paradigm that involves a discrimination task to increase the information content obtained from gaze data. Our method extracts discriminative descriptors from the data and learns a compatibility function between image and gaze using three novel gaze embeddings: Gaze Histograms (GH), Gaze Features with Grid (GFG) and Gaze Features with Sequence (GFS). We introduce two new gaze-annotated datasets for fine-grained image classification and show that human gaze data is indeed class discriminative, provides a competitive alternative to expert-annotated attributes, and outperforms other baselines for zero-shot image classification.

关键词： Histograms Gaze tracking Visualization Data collection Birds computer vision Ocular Fixation images histograms Image classification Data Collection Methods computer vision Gaze tracking Visualization Avifauna

来源：评论

学校读者我要写书评

暂无评论

A clever elimination strategy for efficient minimal solvers 30

A clever elimination strategy for efficient minimal solvers

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kukelova, Zuzana Kileel, Joe Sturmfels, Bernd Pajdla, Tomas Czech Tech Univ Fac Elect Engn Prague Czech Republic Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (纸本)9781538604571

We present a new insight into the systematic generation of minimal solvers in computer vision, which leads to smaller and faster solvers. Many minimal problem formulations are coupled sets of linear and polynomial equations where image measurements enter the linear equations only. We show that it is useful to solve such systems by first eliminating all the unknowns that do not appear in the linear equations and then extending solutions to the rest of unknowns. this can be generalized to fully non-linear systems by linearization via lifting. We demonstrate that this approach leads to more efficient solvers in three problems of partially calibrated relative camera pose computation with unknown focal length and/or radial distortion. Our approach also generates new interesting constraints on the fundamental matrices of partially calibrated cameras, which were not known before.

关键词： computer vision Mathematical model Cameras Generators Systematics Geometry Standards

来源：评论

学校读者我要写书评

暂无评论

Seeing into Darkness: Scotopic Visual recognition 30

Seeing into Darkness: Scotopic Visual Recognition

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Chen, Bo Perona, Pietro CALTECH Pasadena CA 91125 USA

ISBN: (纸本)9781538604571

Images are formed by counting how many photons traveling from a given set of directions hit an image sensor during a given time interval. When photons are few and far in between, the concept of 'image' breaks down and it is best to consider directly the flow of photons. computer vision in this regime, which we call 'scotopic', is radically different from the classical image-based paradigm in that visual computations (classification, control, search) have to take place while the stream of photons is captured and decisions may be taken as soon as enough information is available. the scotopic regime is important for biomedical imaging, security, astronomy and many other fields. Here we develop a framework that allows a machine to classify objects with as few photons as possible, while maintaining the error rate below an acceptable threshold. A dynamic and asymptotically optimal speed-accuracy tradeoff is a key feature of this framework. We propose and study an algorithm to optimize the tradeoff of a convolutional network directly from lowlight images and evaluate on simulated images from standard datasets. Surprisingly, scotopic systems can achieve comparable classification performance as traditional vision systems while using less than 0.1% of the photons in a conventional image. In addition, we demonstrate that our algorithms work even when the illuminance of the environment is unknown and varying. Last, we outline a spiking neural network coupled with photon-counting sensors as a power-efficient hardware realization of scotopic algorithms.

关键词： Night vision Photon images Sensors (image) computer vision Error analysis tradeoffs Time intervals analog image Illuminance Frameworks

来源：评论

学校读者我要写书评

暂无评论

UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level vision using Diverse Datasets and Limited Memory 30

UberNet: Training a Universal Convolutional Neural Network f...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kokkinos, Iasonas UCL London England Facebook Artificial Intelligence Res Menlo Pk CA 94025 USA

ISBN: (纸本)9781538604571

In this work we train in an end-to-end manner a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a network can act like a 'swiss knife' for vision tasks;we call it an "UberNet" to indicate its overarching nature. the main contribution of this work consists in handling challenges that emerge when scaling up to many tasks. We introduce techniques that facilitate (i) training a deep architecture while relying on diverse training sets and (ii) training many (potentially unlimited) tasks with a limited memory budget. this allows us to train in an end-to-end manner a unified CNN architecture that jointly handles (a) boundary detection (b) normal estimation (c) saliency estimation (d) semantic segmentation (e) human part segmentation (f) semantic boundary detection, (g) region proposal generation and object detection. We obtain competitive performance while jointly addressing all tasks in 0.7 seconds on a GPU. Our system will be made publicly available.

关键词： Training Estimation Semantics computer architecture Discrete wavelet transforms Proposals

来源：评论

学校读者我要写书评

暂无评论

Network Sketching: Exploiting Binary Structure in Deep CNNs 30

Network Sketching: Exploiting Binary Structure in Deep CNNs

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Guo, Yiwen Yao, Anbang Zhao, Hao Chen, Yurong Intel Labs China Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (纸本)9781538604571

Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks. However, deep networks are typically resource-intensive and thus difficult to be deployed on mobile devices. Recently, CNNs with binary weights have shown compelling efficiency to the community, whereas the accuracy of such models is usually unsatisfactory in practice. In this paper, we introduce network sketching as a novel technique of pursuing binary-weight CNNs, targeting at more faithful inference and better trade-off for practical applications. Our basic idea is to exploit binary structure directly in pre-trained filter banks and produce binary-weight models via tensor expansion. the whole process can be treated as a coarse-to-fine model approximation, akin to the pencil drawing steps of outlining and shading. To further speedup the generated models, namely the sketches, we also propose an associative implementation of binary tensor convolutions. Experimental results demonstrate that a proper sketch of AlexNet (or ResNet) outperforms the existing binary-weight models by large margins on the ImageNet large scale classification task, while the committed memory for network parameters only exceeds a little.

关键词： Binary network parameters Filter banks Sketches images computer vision artificial shade Tensor Outlines Network

来源：评论

学校读者我要写书评

暂无评论

Transition Forests: Learning Discriminative Temporal Transitions for Action recognition and Detection 30

Transition Forests: Learning Discriminative Temporal Transit...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Garcia-Hernando, Guillermo Kim, Tae-Kyun Imperial Coll London London England

ISBN: (纸本)9781538604571

A human action can be seen as transitions between one's body poses over time, where the transition depicts a temporal relation between two poses. Recognizing actions thus involves learning a classifier sensitive to these pose transitions as well as to static poses. In this paper, we introduce a novel method called transitions forests, an ensemble of decision trees that both learn to discriminate static poses and transitions between pairs of two independent frames. During training, node splitting is driven by alternating two criteria: the standard classification objective that maximizes the discrimination power in individual frames, and the proposed one in pairwise frame transitions. Growing the trees tends to group frames that have similar associated transitions and share same action label incorporating temporal information that was not available otherwise. Unlike conventional decision trees where the best split in a node is determined independently of other nodes, the transition forests try to find the best split of nodes jointly (within a layer) for incorporating distant node transitions. When inferring the class label of a new frame, it is passed down the trees and the prediction is made based on previous frame predictions and the current one in an efficient and online manner. We apply our method on varied skeleton action recognition and online detection datasets showing its suitability over several baselines and state-of-the-art approaches.

关键词： Vegetation Hidden Markov models Training Decision trees computer vision pattern recognition Standards

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action recognition 30

Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for S...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Weng, Junwu Weng, Chaoqun Yuan, Junsong Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

ISBN: (纸本)9781538604571

Motivated by previous success of using non-parametric methods to recognize objects, e.g., NBNN [2], we extend it to recognize actions using skeletons. Each 3D action is presented by a sequence of 3D poses. Similar to NBNN, our proposed Spatio-Temporal-NBNN applies stage-to-class distance to classify actions. However, ST-NBNN takes the spatio-temporal structure of 3D actions into consideration and relaxes the Naive Bayes assumption of NBNN. Specifically, ST-NBNN adopts bilinear classifiers [19] to identify both key temporal stages as well as spatial joints for action classification. Although only using a linear classifier, experiments on three benchmark datasets show that by combining the strength of both non-parametric and parametric models, ST-NBNN can achieve competitive performance compared with state-of-the-art results using sophisticated models such as deep learning. Moreover, by identifying key skeleton joints and temporal stages for each action class, our ST-NBNN can capture the essential spatiotemporal patterns that play key roles of recognizing actions, which is not always achievable by using end-to-end models.

关键词： three-dimensional displays Skeleton pattern recognition Videos computer vision Image recognition Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Deep Mixture of Linear Inverse Regressions Applied to Head-Pose Estimation 30

Deep Mixture of Linear Inverse Regressions Applied to Head-P...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Lathuiliere, Stephane Juge, Remi Mesejo, Pablo Munoz-Salinas, Rafael Horaud, Radu Inria Grenoble Rhone Alpes Montbonnot St Martin France Univ Cordoba Comp & Numer Anal Dept Cordoba Spain

ISBN: (纸本)9781538604571

Convolutional Neural Networks (ConvNets) have become the state-of-the-art for many classification and regression problems in computer vision. When it comes to regression, approaches such as measuring the Euclidean distance of target and predictions are often employed as output layer. In this paper, we propose the coupling of a Gaussian mixture of linear inverse regressions with a ConvNet, and we describe the methodological foundations and the associated algorithm to jointly train the deep network and the regression function. We test our model on the headpose estimation problem. In this particular problem, we show that inverse regression outperforms regression models currently used by state-of-the-art computer vision methods. Our method does not require the incorporation of additional data, as it is often proposed in the literature, thus it is able to work well on relatively small training datasets. Finally, it outperforms state-of-the-art methods in head-pose estimation using a widely used head-pose dataset. To the best of our knowledge, we are the first to incorporate inverse regression into deep learning for computer vision applications.

关键词： images computer vision Inverse regression Regression (Psychology) Dataset Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes 30

Full-Resolution Residual Networks for Semantic Segmentation ...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Pohlen, Tobias Hermans, Alexander Mathias, Markus Leibe, Bastian Rhein Westfal TH Aachen Visual Comp Inst Aachen Germany

ISBN: (纸本)9781538604571

Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. To alleviate this problem we propose a novel ResNet-like architecture that exhibits strong localization and recognition performance. We combine multi-scale context with pixel-level accuracy by using two processing streams within our network: One stream carries information at the full image resolution, enabling precise adherence to segment boundaries. the other stream undergoes a sequence of pooling operations to obtain robust features for recognition. the two streams are coupled at the full image resolution using residuals. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.

关键词： Streaming media Image segmentation Semantics Training Network architecture computer architecture

来源：评论

学校读者我要写书评

暂无评论

On human motion prediction using recurrent neural networks 30

On human motion prediction using recurrent neural networks

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Martinez, Julieta Black, Michael J. Romero, Javier Univ British Columbia Vancouver BC Canada MPI Intelligent Syst Tubingen Germany Body Labs Inc New York NY USA MPI Tubingen Germany

ISBN: (纸本)9781538604571

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.

关键词： Hidden Markov models Predictive models Training Mathematical model Visualization Recurrent neural networks recurrent neural nets Human motion Hidden Markov models Prediction models Mathematical Model Visualization Functional training images computer vision Evaluation Methodology Training

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22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：