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

6,421 篇 会议
25 篇 期刊文献
3 册 图书

馆藏范围

6,448 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,849 篇 工学
- 3,647 篇 计算机科学与技术...
- 1,431 篇 软件工程
- 790 篇 光学工程
- 302 篇 信息与通信工程
- 242 篇 控制科学与工程
- 219 篇 电气工程
- 201 篇 机械工程
- 80 篇 生物医学工程（可授...
- 68 篇 生物工程
- 67 篇 电子科学与技术（可...
- 64 篇 仪器科学与技术
- 36 篇 建筑学
- 33 篇 力学（可授工学、理...
- 33 篇 土木工程
- 33 篇 航空宇航科学与技...
- 26 篇 安全科学与工程
- 22 篇 交通运输工程
- 20 篇 材料科学与工程（可...
- 18 篇 化学工程与技术
1,453 篇 理学
- 945 篇 物理学
- 890 篇 数学
- 352 篇 统计学（可授理学、...
- 134 篇 生物学
- 38 篇 系统科学
- 23 篇 化学
160 篇 管理学
- 110 篇 图书情报与档案管...
- 52 篇 管理科学与工程(可...
- 25 篇 工商管理
112 篇 医学
- 112 篇 临床医学
17 篇 法学
- 17 篇 社会学
12 篇 农学
8 篇 教育学
7 篇 艺术学
6 篇 经济学
2 篇 军事学

主题

2,288 篇 computer vision
789 篇 pattern recognit...
637 篇 cameras
629 篇 computer science
568 篇 face recognition
555 篇 layout
510 篇 image segmentati...
509 篇 conferences
498 篇 shape
445 篇 robustness
439 篇 object recogniti...
388 篇 humans
332 篇 feature extracti...
321 篇 training
303 篇 object detection
262 篇 image recognitio...
257 篇 application soft...
246 篇 lighting
238 篇 image reconstruc...
237 篇 computational mo...

机构

41 篇 microsoft resear...
26 篇 department of co...
21 篇 swiss fed inst t...
21 篇 school of comput...
20 篇 department of co...
19 篇 swiss fed inst t...
19 篇 carnegie mellon ...
18 篇 department of co...
17 篇 department of in...
17 篇 the robotics ins...
17 篇 institute of com...
16 篇 univ sci & techn...
16 篇 robotics institu...
15 篇 tsinghua univ pe...
14 篇 department of el...
14 篇 school of comput...
14 篇 school of comput...
13 篇 univ maryland co...
13 篇 microsoft resear...
13 篇 microsoft resear...

作者

39 篇 timofte radu
28 篇 s.k. nayar
24 篇 huang thomas s.
23 篇 xiaoou tang
22 篇 t. kanade
20 篇 t.s. huang
19 篇 van gool luc
19 篇 t. darrell
19 篇 chellappa rama
18 篇 nayar shree k.
17 篇 a.k. jain
17 篇 a. zisserman
17 篇 jain anil k.
16 篇 g. healey
16 篇 torralba antonio
16 篇 heung-yeung shum
16 篇 zisserman andrew
16 篇 l. van gool
15 篇 m. shah
15 篇 ji qiang

语言

6,447 篇 英文
2 篇 其他

检索条件"任意字段=1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992"

共 6449 条记录，以下是881-890 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：

Evaluating the Impact of Wide-Angle Lens Distortion on Learning-based Depth Estimation

Evaluating the Impact of Wide-Angle Lens Distortion on Learn...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Buquet, Julie Zhang, Jinsong Roulet, Patrice Thibault, Simon Lalonde, Jean-Francois Univ Laval Quebec City PQ Canada Immervision Montreal PQ Canada

ISBN: (纸本)9781665448994

Most computer vision research focuses on narrow angle lenses and is not adapted to super-wide-angle (aka spherical) lenses. This is mainly because current neural networks are not designed or trained to interpret the significant barrel distortion that is introduced in the captured image by such wide angle *** these lenses capture a half-sphere or a section of sphere on the object space, barrel distortion appears when the image is projected on a 2D flat image sensor. By controlling this distortion at the lens design stage, camera designers can create some areas with augmented resolution [26]. In this work, we present an analysis of the impact of such augmented resolution on computer vision algorithm accuracy, using the problem of single image depth estimation as a case study. To this end, 360 degrees panorama datasets are warped to simulate different wideangle lens datasets, which are then used to train identical neural networks. Each lens presents specific areas of the image with augmented resolution using spatially-varying non-linear distortion. We show that this property leads to better local accuracy in depth estimation. We also demonstrate that considering lens manufacturing improves performance when tested on realistic lenses, especially in the area of augmented resolution. We further show that this property helps to locally come closer to performances obtained on perspective images without cropping the field of view.

关键词： Training computer vision Nonlinear distortion Neural networks Estimation Tools Cameras

来源：评论

学校读者我要写书评

暂无评论

On the Robustness and Generalizability of Face Synthesis Detection Methods

On the Robustness and Generalizability of Face Synthesis Det...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Sabel, Johan Johansson, Fredrik Swedish Def Res Agcy FOI Stockholm Sweden

ISBN: (纸本)9781665448994

In recent years, significant progress has been made within human face synthesis. It is now possible, and easy for anyone, to generate credible high-resolution images of non-existing people. This calls for effective detection methods. In this paper, three state-of-the-art deep learning-based methods are evaluated with respect to their robustness and generalizability, which are two factors that must be taken into consideration for methods intended to be deployed in the wild. The robustness experiments show that it is possible to achieve near-perfect performance when discriminating between real and synthetic facial images that have been post-processed heavily with various perturbation techniques;especially when similar perturbations are incorporated during training of the detection models. The generalization experiments show that already trained detection models can achieve high performance on images from sources not known during training, provided that the models are fine-tuned on such images. One model achieved an average accuracy of 96.8% after being fine-tuned on 3 training images from each unknown source considered (one real and one synthetic source). However, additional images were required when fine-tuning using a different approach aimed at preventing catastrophic forgetting. Furthermore, in general, no method generalized well without fine-tuning. Hence, the limited generalization capability remains a shortcoming that must be overcome before the detection methods can be utilized in the wild.

关键词： Training Learning systems computer vision Perturbation methods Face recognition conferences Robustness

来源：评论

学校读者我要写书评

暂无评论

A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks

A Bop and Beyond: A Second Order Optimizer for Binarized Neu...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Daniel Suarez-Ramirez, Cuauhtemoc Gonzalez-Mendoza, Miguel Chang, Leonardo Ochoa-Ruiz, Gilberto Alberto Duran-Vega, Mario Tecnol Monterrey Sch Engn & Sci Dept Comp Sci Monterrey NL Mexico

ISBN: (纸本)9781665448994

The optimization of Binary Neural Networks (BNNs) relies on approximating the real-valued weights with their binarized representations. Current techniques for weight-updating use the same approaches as traditional Neural Networks (NNs) with the extra requirement of using an approximation to the derivative of the sign function - as it is the Dirac-Delta function - for back-propagation;thus, efforts are focused adapting full-precision techniques to work on BNNs. In the literature, only one previous effort has tackled the problem of directly training the BNNs with bit-flips by using the first raw moment estimate of the gradients and comparing it against a threshold for deciding when to flip a weight (Bop). In this paper, we take an approach parallel to Adam which also uses the second raw moment estimate to normalize the first raw moment before doing the comparison with the threshold, we call this method Bop2ndOrder. We present two versions of the proposed optimizer: a biased one and a bias-corrected one, each with its own applications. Also, we present a complete ablation study of the hyperparameters space, as well as the effect of using schedulers on each of them. For these studies, we tested the optimizer in CIFAR10 using the BinaryNet architecture. Also, we tested it in ImageNet 2012 with the XnorNet and BiRealNet architectures for accuracy. In both datasets our approach proved to converge faster, was robust to changes of the hyperparameters, and achieved better accuracy values.

关键词： Training computer vision conferences computer architecture Artificial neural networks pattern recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

Explainable Deep Classification Models for Domain Generalization

Explainable Deep Classification Models for Domain Generaliza...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Zunino, Andrea Bargal, Sarah Adel Volpi, Riccardo Sameki, Mehrnoosh Zhang, Jianming Sclaroff, Stan Murino, Vittorio Saenko, Kate Huawei Ireland Res Ctr Dublin Ireland Boston Univ Dept Comp Sci 111 Cummington St Boston MA 02215 USA Naver Labs Europe Meylan France Microsoft Redmond WA USA Adobe Res San Jose CA USA Ist Italiano Tecnol Pattern Anal & Comp Vis Genoa Italy Univ Verona Verona Italy

ISBN: (纸本)9781665448994

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network's decision. Our training strategy enforces a periodic saliency-based feedback to encourage the model to focus on the image regions that directly correspond to the ground-truth object. We quantify explainability using an automated metric, and using human judgement. We propose explainability as a means for bridging the visual-semantic gap between different domains where model explanations are used as a means of disentagling domain specific information from otherwise relevant features. We demonstrate that this leads to improved generalization to new domains without hindering performance on the original domain.

关键词： Training Degradation Measurement Visualization computer vision conferences Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units recognition

Multi-Scale Dynamic and Hierarchical Relationship Modeling f...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Zihan Wang Siyang Song Cheng Luo Songhe Deng Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Universiry of Leicester Monash University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hi-erarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatiotemporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and mag-nitude in different AUs' activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR.

关键词： Gold Adaptation models computer vision Graphical models Codes Adaptive systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Combining Weight Pruning and Knowledge Distillation For CNN Compression

Combining Weight Pruning and Knowledge Distillation For CNN ...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Aghli, Nima Ribeiro, Eraldo Florida Inst Technol 150 W Univ Blvd Melbourne FL 32901 USA

ISBN: (纸本)9781665448994

Complex deep convolutional neural networks such as ResNet require expensive hardware such as powerful GPUs to achieve real-time performance. This problem is critical for applications that run on low-end embedded GPU or CPU systems with limited resources. As a result, model compression for deep neural networks becomes an important research topic. Popular compression methods such as weight pruning remove redundant neurons from the CNN without affecting the network's output accuracy. While these pruning methods work well on simple networks such as VGG or AlexNet, they are not suitable for compressing current state-of-the-art networks such as ResNets because of these networks' complex architectures with dimensionality dependencies. This dependency results in filter pruning breaking the structure of ResNets leading to an untrainable network. In this paper, we first use the weight pruning method only on a selective number of layers in the ResNet architecture to avoid breaking the network structure. Second, we introduce a knowledge distillation architecture and a loss function to compress the untouched layers during the pruning. We test our method on both image-based regression and classification networks for head-pose estimation and image classification. Our compression method reduces the models' size significantly while maintaining the accuracy very close to the baseline model.

关键词： Image coding Neurons Estimation Graphics processing units computer architecture Real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved Attention for Visual Question Answering

An Improved Attention for Visual Question Answering

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Rahman, Tanzila Chou, Shih-Han Sigal, Leonid Carenini, Giuseppe Univ British Columbia Dept Comp Sci Vancouver BC Canada Vector Inst AI Toronto ON Canada Canada CIFAR AI Chair Toronto ON Canada

ISBN: (纸本)9781665448994

We consider the problem of Visual Question Answering (VQA). Given an image and a free-form, open-ended, question, expressed in natural language, the goal of VQA system is to provide accurate answer to this question with respect to the image. The task is challenging because it requires simultaneous and intricate understanding of both visual and textual information. Attention, which captures intra- and inter-modal dependencies, has emerged as perhaps the most widely used mechanism for addressing these challenges. In this paper, we propose an improved attention-based architecture to solve VQA. We incorporate an Attention on Attention (AoA) module within encoder-decoder framework, which is able to determine the relation between attention results and queries. Attention module generates weighted average for each query. On the other hand, AoA module first generates an information vector and an attention gate using attention results and current context;and then adds another attention to generate final attended information by multiplying the two. We also propose multimodal fusion module to combine both visual and textual information. The goal of this fusion module is to dynamically decide how much information should be considered from each modality. Extensive experiments on VQA-v2 benchmark dataset show that our method achieves better performance than the baseline method.

关键词： Visualization computer vision conferences Computational modeling Natural languages computer architecture Logic gates

来源：评论

学校读者我要写书评

暂无评论

Spike timing-based unsupervised learning of orientation, disparity, and motion representations in a spiking neural network

Spike timing-based unsupervised learning of orientation, dis...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Barbier, Thomas Teuliere, Celine Triesch, Jochen Univ Clermont Auvergne Inst Pascal SIGMA Clermont CNRS F-63000 Clermont Ferrand France Frankfurt Inst Adv Studies Frankfurt Germany

ISBN: (纸本)9781665448994

Neuromorphic vision sensors present unique advantages over their frame based counterparts. However, unsupervised learning of efficient visual representations from their asynchronous output is still a challenge, requiring a rethinking of traditional image and video processing methods. Here we present a network of leaky integrate and fire neurons that learns representations similar to those of simple and complex cells in the primary visual cortex of mammals from the input of two event-based vision sensors. Through the combination of spike timing-dependent plasticity and homeostatic mechanisms, the network learns visual feature detectors for orientation, disparity, and motion in a fully unsupervised fashion. We validate our approach on a mobile robotic platform.

关键词： Visualization Neuromorphics conferences Neurons Detectors vision sensors Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

On Training Sketch Recognizers for New Domains

On Training Sketch Recognizers for New Domains

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Yesilbek, Kemal Tugrul Sezgin, T. Metin Beat Res BV Amsterdam Netherlands Koc Univ Istanbul Turkey

ISBN: (纸本)9781665448994

Sketch recognition algorithms are engineered and evaluated using publicly available datasets contributed by the sketch recognition community over the years. While existing datasets contain sketches of a limited set of generic objects, each new domain inevitably requires collecting new data for training domain specific recognizers. This gives rise to two fundamental concerns: First, will the data collection protocol yield ecologically valid data? Second, will the amount of collected data suffice to train sufficiently accurate classifiers? In this paper, we draw attention to these two concerns. We show that the ecological validity of the data collection protocol and the ability to accommodate small datasets are significant factors impacting recognizer accuracy in realistic scenarios. More specifically, using sketch-based gaming as a use case, we show that deep learning methods, as well as more traditional methods, suffer significantly from dataset shift. Furthermore, we demonstrate that in realistic scenarios where data is scarce and expensive, standard measures taken for adapting deep learners to small datasets fall short of comparing favorably with alternatives. Although transfer learning, and extensive data augmentation help deep learners, they still perform significantly worse compared to standard setups (e.g., SVMs and GBMs with standard feature representations). We pose learning from small datasets as a key problem for the deep sketch recognition field, one which has been ignored in the bulk of the existing literature.

关键词： Training Deep learning computer vision Protocols conferences Transfer learning Data collection

来源：评论

学校读者我要写书评

暂无评论

BoxInst: High-Performance Instance Segmentation with Box Annotations

BoxInst: High-Performance Instance Segmentation with Box Ann...

引用

2021 ieee/CVF conference on computer vision and pattern recognition, cvpr 2021

作者： Tian, Zhi Shen, Chunhua Wang, Xinlong Chen, Hao The University of Adelaide Australia

ISBN: (纸本)9781665445092

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance with a simple design (e.g., dramatically improving previous best reported mask AP of 21.1% [13] to 31.6% on the COCO dataset). Our core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself. The new loss functions can supervise the mask training without relying on mask annotations. This is made possible with two loss terms, namely, 1) a surrogate term that minimizes the discrepancy between the projections of the ground-truth box and the predicted mask;2) a pairwise loss that can exploit the prior that proximal pixels with similar colors are very likely to have the same category label. Experiments demonstrate that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations. For example, without using any mask annotations, with a ResNet-101 backbone and 3× training schedule, we achieve 33.2% mask AP on COCO test-dev split (vs. 39.1% of the fully supervised counterpart). Our excellent experiment results on COCO and Pascal VOC indicate that our method dramatically narrows the performance gap between weakly and fully supervised instance segmentation. Code is available at: https://***/AdelaiDet. © 2021 ieee

关键词： computer vision

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500页 << < 85 86 87 88 89 90 91 92 93 94 > >>

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：