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

3,854 篇 会议
1 篇 期刊文献

馆藏范围

3,855 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,938 篇 工学
- 2,846 篇 计算机科学与技术...
- 210 篇 软件工程
- 141 篇 机械工程
- 134 篇 光学工程
- 43 篇 生物工程
- 28 篇 信息与通信工程
- 10 篇 控制科学与工程
- 10 篇 交通运输工程
- 9 篇 电气工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 7 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
1,540 篇 医学
- 1,540 篇 临床医学
176 篇 理学
- 137 篇 物理学
- 44 篇 生物学
- 30 篇 数学
- 17 篇 统计学（可授理学、...
- 10 篇 化学
- 2 篇 大气科学
15 篇 管理学
- 8 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 4 篇 工商管理
6 篇 法学
- 4 篇 社会学
- 2 篇 法学
2 篇 教育学
- 2 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,497 篇 computer vision
1,153 篇 pattern recognit...
1,102 篇 training
834 篇 conferences
688 篇 computational mo...
531 篇 visualization
465 篇 computer archite...
429 篇 benchmark testin...
398 篇 semantics
377 篇 three-dimensiona...
362 篇 codes
307 篇 feature extracti...
297 篇 task analysis
296 篇 deep learning
262 篇 neural networks
226 篇 image segmentati...
221 篇 estimation
218 篇 object detection
212 篇 cameras
205 篇 measurement

机构

50 篇 univ sci & techn...
47 篇 peng cheng lab p...
46 篇 tsinghua univ pe...
42 篇 zhejiang univ pe...
41 篇 chinese univ hon...
39 篇 sensetime res pe...
39 篇 stanford univ st...
38 篇 swiss fed inst t...
37 篇 carnegie mellon ...
36 篇 swiss fed inst t...
33 篇 natl univ singap...
32 篇 yonsei univ
32 篇 shanghai jiao to...
30 篇 korea adv inst s...
29 篇 univ chinese aca...
28 篇 megvii technol p...
28 篇 univ hong kong p...
27 篇 alibaba grp peop...
27 篇 tech univ munich...
27 篇 adobe res san jo...

作者

68 篇 timofte radu
25 篇 van gool luc
23 篇 zhang lei
21 篇 sun jian
17 篇 yang yi
16 篇 tao dacheng
16 篇 radu timofte
15 篇 loy chen change
15 篇 lee kyoung mu
14 篇 fan haoqiang
14 篇 wang xinchao
14 篇 liu shuaicheng
14 篇 pan jinshan
14 篇 ji rongrong
14 篇 zhang wei
12 篇 li xin
12 篇 liu yang
12 篇 wang kai
12 篇 chen wei-ting
12 篇 khan fahad shahb...

语言

3,855 篇 英文

检索条件"任意字段=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021"

共 3855 条记录，以下是3731-3740 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：

Efficient Semantic Segmentation using Gradual Grouping 31

Efficient Semantic Segmentation using Gradual Grouping

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Vallurupalli, Nikitha Annamaneni, Sriharsha Varma, Girish Jawahar, C., V Mathew, Manu Nagori, Soyeb IIIT Hyderabad Kohli Ctr Intelligent Syst Ctr Visual Informat Technol Hyderabad Telangana India Texas Instruments Inc Bangalore Karnataka India

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Deep CNNs for semantic segmentation have high memory and run time requirements. Various approaches have been proposed to make CNNs efficient like grouped, shuffled, depth-wise separable convolutions. We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving run-time by over 5X. We apply these techniques to CNN layers partially or fully and evaluate the testing accuracies on Cityscapes dataset. We obtain accuracy vs parameters/FLOPs trade offs, giving accuracy scores for models that can run under specified runtime budgets. We further propose a novel training procedure which starts out with a dense convolution but gradually evolves towards a grouped convolution. We show that our proposed training method and efficient architecture design can improve accuracies by over 8% with depthwise separable convolutions applied on the encoder of ERFNet and attaching a light weight decoder. This results in a model which has a 5X improvement in FLOPs while only suffering a 4% degradation in accuracy with respect to ERFNet.

关键词： Training Semantics computer architecture Computational modeling Sparse matrices Predictive models Decoding

来源：评论

学校读者我要写书评

暂无评论

Pose-Guided R-CNN for Jersey Number recognition in Sports

Pose-Guided R-CNN for Jersey Number Recognition in Sports

引用

ieee/cvf conference on computer vision and pattern recognition workshops

作者： Hengyue Liu Bir Bhanu Center for Research in Intelligent Systems University of California

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Recognizing player jersey number in sports match video streams is a challenging computer vision task. The human pose and view-point variations displayed in frames lead to many difficulties in recognizing the digits on jerseys. These challenges are addressed here using an approach that exploits human body part cues with a Region-based Convolutional Neural Network (R-CNN) variant for digit level localization and classification. The paper first adopts the Region Proposal Network (RPN) to perform anchor classification and bounding-box regression over three classes: background, person and digit. The person and digit proposals are geometrically related and fed to a network classifier. Subsequently, it introduces a human body key-point prediction branch and a pose-guided regressor to get better bounding-box offsets for generating digit proposals. A novel dataset of soccer-match video frames with corresponding multi-digit class labels, player and jersey number bounding boxes, and single digit segmentation masks is collected. Our framework outperforms all existing models on jersey number recognition task. This work will be essential to the automation of player identification across multiple sports, and releasing the dataset will ease future research on sports video analysis.

关键词： Sports Digit bounding boxes Persons Digital HUMAN BODY PARTS images computer vision VIDEO ANALYSIS Automation FRAMES

来源：评论

学校读者我要写书评

暂无评论

A Fully Progressive Approach to Single-Image Super-Resolution 31

A Fully Progressive Approach to Single-Image Super-Resolutio...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Wang, Yifan Perazzi, Federico McWilliams, Brian Sorkine-Hornung, Alexander Sorkine-Hornung, Olga Schroers, Christopher Swiss Fed Inst Technol Zurich Switzerland Disney Res Zurich Switzerland Oculus Menlo Pk CA USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8x) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge [35]. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster.

关键词： Training Gallium nitride Image resolution Image reconstruction Generative adversarial networks computer architecture Generators

来源：评论

学校读者我要写书评

暂无评论

Real Photographs Denoising with Noise Domain Adaptation and Attentive Generative Adversarial Network

Real Photographs Denoising with Noise Domain Adaptation and ...

引用

ieee/cvf conference on computer vision and pattern recognition workshops

作者： Kai Lin Thomas H. Li Shan Liu Ge Li School of Electronic and Computer Engineering Peking University Tencent America

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Nowadays, deep convolutional neural networks (CNNs) based methods have achieved favorable performance in synthetic noisy image denoising, but they are very limited in real photographs denoising since it's hard to obtain ground truth clean image to generate paired training data. Besides, the existing training datasets for real photographs denoising are too small. To solve this problem, we construct a new dataset and obtain corresponding ground truth by averaging, and then extend them through noise domain adaptation. Furthermore, we propose a attentive generative network by injecting visual attention into the generative network. During the training, visual attention map learns noise regions. The generative network will pay more attention to noise regions, which contributes to balancing between noise removal and texture preservation. Extensive experiments show that our method outperforms several state-of-the-art methods quantitatively and qualitatively.

关键词： Noise reduction ground truth Photographs Noise cancellation Noise averaging Visual Attention Real number

来源：评论

学校读者我要写书评

暂无评论

Recurrent Segmentation for Variable Computational Budgets 31

Recurrent Segmentation for Variable Computational Budgets

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： McIntosh, Lane Maheswaranathan, Niru Sussillo, David Shlens, Jonathon Stanford Univ Stanford CA 94305 USA Google Brain Mountain View CA USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive as new architectures must be designed and trained for every computational setting. To address this problem we develop a recurrent neural network that successively improves prediction quality with each iteration. Importantly, the RNN may be deployed across a range of computational budgets by merely running the model for a variable number of iterations. We find that this architecture is uniquely suited for efficiently segmenting videos. By exploiting the segmentation of past frames, the RNN can perform video segmentation at similar quality but reduced computational cost compared to state-of-the-art image segmentation methods. When applied to static images in the PASCAL VOC 2012 and Cityscapes segmentation datasets, the RNN traces out a speed-accuracy curve that saturates near the performance of state-of-the-art segmentation methods.

关键词： Image segmentation Semantics computer architecture Computational efficiency Videos Computational modeling Network architecture

来源：评论

学校读者我要写书评

暂无评论

ComboGAN: Unrestrained Scalability for Image Domain Translation 31

ComboGAN: Unrestrained Scalability for Image Domain Translat...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Anoosheh, Asha Agustsson, Eirikur Timofte, Radu Van Gool, Luc Swiss Fed Inst Technol D ITET Comp Vis Lab Zurich Switzerland Swiss Fed Inst Technol D ITET Zurich Switzerland Merantix Berlin Germany Katholieke Univ Leuven ESAT Leuven Belgium

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

The past year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would require an quadratic number of models to be trained. And with two-domain models taking days to train on current hardware, the number of domains quickly becomes limited by the time and resources required to process them. In this paper, we propose a multi-component image translation model and training scheme which scales linearly - both in resource consumption and time required - with the number of domains. We demonstrate its capabilities on a dataset of paintings by 14 different artists and on images of the four different seasons in the Alps. Note that 14 data groups would need ( 14 choose 2) = 91 different CycleGAN models: a total of 182 generator/discriminator pairs;whereas our model requires only 14 generator/discriminator pairs.

关键词： Training Generators Gallium nitride Decoding computer vision Task analysis Data models

来源：评论

学校读者我要写书评

暂无评论

SUSiNet: See, Understand and Summarize it

SUSiNet: See, Understand and Summarize it

引用

ieee/cvf conference on computer vision and pattern recognition workshops

作者： Petros Koutras Petros Maragos National Technical University of Athens Greece

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

In this work we propose a multi-task spatio-temporal network, called SUSiNet, that can jointly tackle the spatio-temporal problems of saliency estimation, action recognition and video summarization. Our approach employs a single network that is jointly end-to-end trained for all tasks with multiple and diverse datasets related to the exploring tasks. The proposed network uses a unified architecture that includes global and task specific layer and produces multiple output types, i.e., saliency maps or classification labels, by employing the same video input. Moreover, one additional contribution is that the proposed network can be deeply supervised through an attention module that is related to human attention as it is expressed by eye-tracking data. From the extensive evaluation, on seven different datasets, we have observed that the multi-task network performs as well as the state-of-the-art single-task methods (or in some cases better), while it requires less computational budget than having one independent network per each task.

关键词： Task analysis Three-dimensional displays Visualization Estimation Two dimensional displays Training computer architecture three-dimensional displays task analysis computer Architecture Visualization Training Functional training Religious Missions

来源：评论

学校读者我要写书评

暂无评论

Scene Understanding Networks for Autonomous Driving based on Around View Monitoring System 31

Scene Understanding Networks for Autonomous Driving based on...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Baek, JeongYeol Chelu, Ioana Veronica Iordache, Livia Paunescu, Vlad Ryu, HyunJoo Ghiuta, Alexandru Petreanu, Andrei Soh, YunSung Leica, Andrei Jeon, ByeongMoon LG Elect Convergence Ctr Seoul South Korea Arnia Software Bucharest Romania

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Modern driver assistance systems rely on a wide range of sensors (RADAR, LIDAR, ultrasound and cameras) for scene understanding and prediction. These sensors are typically used for detecting traffic participants and scene elements required for navigation. In this paper we argue that relying on camera based systems, specifically Around View Monitoring (AVM) system has great potential to achieve these goals in both parking and driving modes with decreased costs. The contributions of this paper are as follows: we present a new end-to-end solution for delimiting the safe drivable area for each frame by means of identifying the closest obstacle in each direction from the driving vehicle, we use this approach to calculate the distance to the nearest obstacles and we incorporate it into a unified end-to-end architecture capable of joint object detection, curb detection and safe drivable area detection. Furthermore, we describe the family of networks for both a high accuracy solution and a low complexity solution. We also introduce further augmentation of the base architecture with 3D object detection.

关键词： Object detection computer architecture Three-dimensional displays Cameras Task analysis Complexity theory Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Real-time Semantic Segmentation for Autonomous Driving 31

A Comparative Study of Real-time Semantic Segmentation for A...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Siam, Mennatullah Gamal, Mostafa Abdel-Razek, Moemen Yogamani, Senthil Jagersand, Martin Zhang, Hong Univ Alberta Edmonton AB Canada Cairo Univ Giza Egypt Valeo Vis Syst Tuam Ireland

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Semantic segmentation is a critical module in robotics related applications, especially autonomous driving. Most of the research on semantic segmentation is focused on improving the accuracy with less attention paid to computationally efficient solutions. Majority of the efficient semantic segmentation algorithms have customized optimizations without scalability and there is no systematic way to compare them. In this paper, we present a real-time segmentation benchmarking framework and study various segmentation algorithms for autonomous driving. We implemented a generic meta-architecture via a decoupled design where different types of encoders and decoders can be plugged in independently. We provide several example encoders including VGG16, Resnet18, MobileNet, and ShuffleNet and decoders including SkipNet, UNet and Dilation Frontend. The framework is scalable for addition of new encoders and decoders developed in the community for other vision tasks. We performed detailed experimental analysis on cityscapes dataset for various combinations of encoder and decoder. The modular framework enabled rapid prototyping of a custom efficient architecture which provides similar to x143 GFLOPs reduction compared to SegNet and runs real-time at similar to 15 fps on NVIDIA Jetson TX2. The source code of the framework is publicly available(1).

关键词： Convolution Semantics computer architecture Decoding Context modeling Real-time systems Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Suppressing Model Overfitting for Image Super-Resolution Networks

Suppressing Model Overfitting for Image Super-Resolution Net...

引用

ieee/cvf conference on computer vision and pattern recognition workshops

作者： Ruicheng Feng Jinjin Gu Yu Qiao Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences The School of Science and Engineering The Chinese University of Hong Kong

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp to train networks on interpolations of sample pairs, which encourages networks to support linear behavior in-between training samples. In addition, we propose a data synthesis method with learned degradation, enabling models to use extra high-quality images with higher content diversity. This strategy proves to be successful in reducing biases of data. By combining these components - MixUp and synthetic training data, large models can be trained without overfitting under very limited data samples and achieve satisfactory generalization performance. Our method won the second place in NTIRE2019 Real SR Challenge.

关键词： super-resolution Network images Training data Data sampling Imagery (Psychotherapy) Image

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386页 << < 370 371 372 373 374 375 376 377 378 379 > >>

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：