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

192 篇 会议
7 册 图书
1 篇 期刊文献

馆藏范围

200 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

140 篇 工学
- 117 篇 计算机科学与技术...
- 50 篇 软件工程
- 28 篇 电气工程
- 16 篇 光学工程
- 16 篇 信息与通信工程
- 8 篇 生物工程
- 7 篇 电子科学与技术（可...
- 7 篇 控制科学与工程
- 5 篇 机械工程
- 5 篇 仪器科学与技术
- 4 篇 生物医学工程（可授...
- 3 篇 力学（可授工学、理...
- 3 篇 化学工程与技术
- 2 篇 动力工程及工程热...
- 2 篇 测绘科学与技术
- 2 篇 交通运输工程
- 2 篇 核科学与技术
56 篇 理学
- 29 篇 数学
- 27 篇 物理学
- 9 篇 生物学
- 9 篇 统计学（可授理学、...
- 3 篇 化学
- 3 篇 系统科学
- 2 篇 大气科学
- 2 篇 海洋科学
- 2 篇 地球物理学
44 篇 医学
- 40 篇 临床医学
- 4 篇 特种医学
6 篇 管理学
- 6 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学
2 篇 农学
1 篇 文学
1 篇 艺术学

主题

51 篇 pattern recognit...
21 篇 object recogniti...
11 篇 training
9 篇 semantics
8 篇 face recognition
7 篇 image segmentati...
7 篇 neural networks
6 篇 artificial intel...
5 篇 object detection
5 篇 deep learning
5 篇 gesture recognit...
5 篇 predictive model...
5 篇 image recognitio...
4 篇 task analysis
4 篇 pattern matching
4 篇 benchmark testin...
4 篇 correlation
4 篇 computer vision
3 篇 noise measuremen...
3 篇 computer graphic...

机构

4 篇 univ freiburg de...
3 篇 school of artifi...
3 篇 nlpr & cebsit ca...
2 篇 cas ctr excellen...
2 篇 university of sc...
2 篇 university leipz...
2 篇 image and patter...
2 篇 tal education gr...
2 篇 univ erlangen nu...
2 篇 visual learning ...
2 篇 institute of inf...
2 篇 heidelberg colla...
2 篇 univ chinese aca...
1 篇 university of ka...
1 篇 katholieke unive...
1 篇 centre for resea...
1 篇 fgan-fom researc...
1 篇 electrical measu...
1 篇 ecole polytech f...
1 篇 univ erlangen nu...

作者

6 篇 burkhardt hans
5 篇 schnörr christop...
5 篇 ney hermann
4 篇 keysers daniel
4 篇 schiele bernt
4 篇 cremers daniel
4 篇 ran he
3 篇 ronneberger olaf
3 篇 fritz mario
3 篇 rosenhahn bodo
3 篇 weickert joachim
3 篇 reisert marco
2 篇 fei yin
2 篇 haxhimusa yll
2 篇 goebel peter mic...
2 篇 villmann thomas
2 篇 mochalova anasta...
2 篇 hornegger joachi...
2 篇 xu-yao zhang
2 篇 franke uwe

语言

200 篇 英文

检索条件"任意字段=25th Pattern Recognition Symposium of the German-Association-for-Pattern-Recognition"

共 200 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：

Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion

Unsupervised Contrastive Photo-to-Caricature Translation bas...

引用

International Conference on pattern recognition

作者： Yuhe Ding Xin Ma Mandi Luo Aihua Zheng Ran He NLPR & CEBSIT CASIA School of Artificial Intelligence University of Chinese Academy of Sciences School of Computer Science and Technology Anhui University

Photo-to-caricature translation aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style rendering and geometry deformation are the most important aspects in photo-to-caricature translation task. To take both into consideration, we propose an unsupervised contrastive photo-to-caricature translation architecture. Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos. To obtain an exaggerating deformation in an unpaired/unsupervised fashion, we propose a Distortion Prediction Module (DPM) to predict a set of displacements vectors for each input image while fixing some controlling points, followed by the thin plate spline interpolation for warping. the model is trained on unpaired photo and caricature while can offer bidirectional synthesizing via inputting either a photo or a caricature. Extensive experiments demonstrate that the proposed model is effective to generate hand-drawn like caricatures compared with existing competitors.

关键词： Geometry Interpolation Rendering (computer graphics) Distortion pattern recognition Task analysis Splines (mathematics)

来源：评论

学校读者我要写书评

暂无评论

MA-LSTM: A Multi-Attention Based LSTM for Complex pattern Extraction

MA-LSTM: A Multi-Attention Based LSTM for Complex Pattern Ex...

引用

International Conference on pattern recognition

作者： Jingjie Guo Kelang Tian Kejiang Ye Cheng-Zhong Xu Sun Yat-sen University Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences State Key Lab of IoTSC Faculty of Science and Technology University of Macau

With the improvement of data volume, computing power and algorithms, deep learning has achieved rapid development and showing excellent performance. Recently, many deep learning models are proposed to solve the problems in different areas. A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. this allows it to exhibit temporal dynamic behavior, which makes it applicable to tasks such as handwriting recognition or speech recognition. However, the RNN relies heavily on the automatic learning ability to update parameters that concentrate on the data flow but seldom considers the feature extraction capability of the gate mechanism. In this paper, we propose a novel architecture to build the forget gate which is generated by multiple bases. Instead of using the traditional single-layer fully-connected network, we use a Multiple Attention (MA) based network to generate the forget gate which refines the optimization space of gate function and improve the granularity of the recurrent neural network to approximate the map in the ground truth. Due to the benefit of MA structure on the gate mechanism, the proposed MA-LSTM model achieves better feature extraction capability than other known models.

关键词： Deep learning Handwriting recognition Recurrent neural networks Computer architecture Speech recognition Logic gates Predictive models

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

Multi-Modal Deep Clustering: Unsupervised Partitioning of Im...

引用

International Conference on pattern recognition

作者： Guy Shiran Daphna Weinshall School of Computer Science and Engineering Hebrew University of Jerusalem Jerusalem Israel

ISBN: (纸本)9781728188089;9781728188096

the clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. the cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task of predicting image rotations. this pushes the network to learn more meaningful image representations that facilitate a better clustering. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on six challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 20% absolute accuracy points, yielding an accuracy of 82% on CIFAR-10, 45% on CIFAR-100 and 69% on STL-10.

关键词： Deep learning Neural networks Image representation Benchmark testing pattern recognition Task analysis Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Gaussian Constrained Attention Network for Scene Text recognition

Gaussian Constrained Attention Network for Scene Text Recogn...

引用

International Conference on pattern recognition

作者： Zhi Qiao Xugong Qin Yu Zhou Fei Yang Weiping Wang School of Cyber Security University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences TAL Education Group

ISBN: (纸本)9781728188089;9781728188096

Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem of attention diffusion, in which the model may not focus on a certain character area. In this paper, we propose Gaussian Constrained Attention Network to deal with this problem. It is a 2D attention-based method integrated with a novel Gaussian Constrained Refinement Module, which predicts an additional Gaussian mask to refine the attention weights. Different from adopting an additional supervision on the attention weights simply, our proposed method introduces an explicit refinement. In this way, the attention weights will be more concentrated and the attention-based recognition network achieves better performance. the proposed Gaussian Constrained Refinement Module is flexible and can be applied to existing attention-based methods directly. the experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. Our code has been available at https://***/Pay20Y/GCAN.

关键词： Computer vision Text recognition Computational modeling Benchmark testing Performance gain Decoding Faces

来源：评论

学校读者我要写书评

暂无评论

F-mixup: Attack CNNs From Fourier Perspective

F-mixup: Attack CNNs From Fourier Perspective

引用

International Conference on pattern recognition

作者： Xiu-Chuan Li Xu-Yao Zhang Fei Yin Cheng-Lin Liu School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Recent research has revealed that deep neural networks are highly vulnerable to adversarial examples. In this paper, different from most adversarial attacks which directly modify pixels in spatial domain, we propose a novel black-box attack in frequency domain, named as f-mixup, based on the property of natural images and perception disparity between human-visual system (HVS) and convolutional neural networks (CNNs): First, natural images tend to have the bulk of their Fourier spectrums concentrated on the low frequency domain; Second, HVS is much less sensitive to high frequencies while CNNs can utilize both low and high frequency information to make predictions. Extensive experiments are conducted and show that deeper CNNs tend to concentrate more on the higher frequency domain, which may explain the contradiction between robustness and accuracy. In addition, we compared f-mixup with existing attack methods and observed that our approach possesses great advantages. Finally, we show that f-mixup can be also incorporated in training to make deep CNNs defensible against a kind of perturbations effectively.

关键词： Training Frequency-domain analysis Perturbation methods Neural networks Robustness pattern recognition High frequency

来源：评论

学校读者我要写书评

暂无评论

Explanation-Guided Training for Cross-Domain Few-Shot Classification

Explanation-Guided Training for Cross-Domain Few-Shot Classi...

引用

International Conference on pattern recognition

作者： Jiamei Sun Sebastian Lapuschkin Wojciech Samek Yunqing Zhao Ngai-Man Cheung Alexander Binder Information System of Technology and Design Singapore University of Technology and Design Fraunhofer Heinrich Hertz Institute Berlin Germany

ISBN: (纸本)9781728188089;9781728188096

Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. this setup faces challenges originating from the limited labeled data in each class and, additionally, from the domain shift between training and test sets. In this paper, we introduce a novel training approach for existing FSC models. It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models. Firstly, we tailor the layer-wise relevance propagation (LRP) method to explain the predictions of FSC models. Secondly, we develop a model-agnostic explanation-guided training strategy that dynamically finds and emphasizes the features which are important for the predictions. Our contribution does not target a novel explanation method but lies in a novel application of explanations for the training phase. We show that explanation-guided training effectively improves the model generalization. We observe improved accuracy for three different FSC models: RelationNet, cross attention network, and a graph neural network-based formulation, on five few-shot learning datasets: miniImagenet, CUB, Cars, Places, and Plantae. the source code is available https://***/SunJiamei/few-shot-lrp-guided.

关键词： Training Heating systems Visualization Computational modeling Predictive models Power capacitors pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting with Contrastive Relation Network

Image Inpainting with Contrastive Relation Network

引用

International Conference on pattern recognition

作者： Xiaoqiang Zhou Junjie Li Zilei Wang Ran He Tieniu Tan University of Science and Technology of China Hefei China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728188089;9781728188096

Image inpainting faces the challenging issue of the requirements on structure reasonableness and texture coherence. In this paper, we propose a two-stage inpainting framework to address this issue. the basic idea is to address the two requirements in two separate stages. Completed segmentation of the corrupted image is firstly predicted through segmentation reconstruction network, while fine-grained image details are restored in the second stage through an image generator. the two stages are connected in series as the image details are generated under the guidance of completed segmentation map that predicted in the first stage. Specifically, in the second stage, we propose a novel graph-based relation network to model the relationship existed in corrupted image. In relation network, both intra-relationship for pixels in the same semantic region and inter-relationship between different semantic parts are considered, improving the consistency and compatibility of image textures. Besides, contrastive loss is designed to facilitate the relation network training. Such a framework not only simplifies the inpainting problem directly, but also exploits the relationship in corrupted image explicitly. Extensive experiments on various public datasets quantitatively and qualitatively demonstrate the superiority of our approach compared with the state-of-the-art.

关键词： Training Image segmentation Image texture Semantics Coherence Generators pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Self-Training for Domain Adaptive Scene Text Detection

Self-Training for Domain Adaptive Scene Text Detection

引用

International Conference on pattern recognition

作者： Yudi Chen Wei Wang Yu Zhou Fei Yang Dongbao Yang Weiping Wang University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences TAL Education Group

ISBN: (纸本)9781728188089;9781728188096

though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the detector in the target domain. However, data collection and annotation are expensive and time-consuming. To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images. To reduce the noise of hard examples, a novel text mining module is implemented based on the fusion of detection and tracking results. then, an image-to-video generation method is designed for the tasks that videos are unavailable and only images can be used. Experimental results on standard benchmarks, including ICDAR2015, MSRA-TD500, ICDAR2017 MLT, demonstrate the effectiveness of our self-training method. the simple Mask R-CNN adapted with self-training and fine-tuned on real data can achieve comparable or even superior results with the state-of-the-art methods.

关键词： Text mining Degradation Deep learning Detectors Data collection Benchmark testing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Free-Form Image Inpainting via Contrastive Attention Network

Free-Form Image Inpainting via Contrastive Attention Network

引用

International Conference on pattern recognition

作者： Xin Ma Xiaoqiang Zhou Huaibo Huang Zhenhua Chai Xiaolin Wei Ran He NLPR & CEBSIT CASIA University of Science and Technology of China Vision Intelligence Center AI Platform Meituandianping Group

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with sophisticated learning tasks. Specifically, in image inpainting tasks, masks with any shapes can appear anywhere in images (i.e., free-form masks) which form complex patterns. It is difficult for encoders to capture such powerful representations under this complex situation. To tackle this problem, we propose a self-supervised Siamese inference network to improve the robustness and generalization. It can encode contextual semantics from full resolution images and obtain more discriminative representations. we further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine both the restored and known regions in a smooth way. this multi-scale architecture is benefit for decoding discriminative representations learned by encoders into images layer by layer. In this way, unknown regions will be filled naturally from outside to inside. Qualitative and quantitative experiments on multiple datasets, including facial and natural datasets (i.e., Celeb-HQ, Pairs Street View, Places2 and ImageNet), demonstrate that our proposed method outperforms state-of-the-art methods in generating high-quality inpainting results.

关键词： Deep learning Image resolution Shape Semantics Robustness Decoding pattern recognition

来源：评论

学校读者我要写书评

暂无评论

$P^{2}$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation

$P^{2}$ Net: Augmented Parallel-Pyramid Net for Attention Gu...

引用

International Conference on pattern recognition

作者： Luanxuan Hou Jie Cao Yuan Zhao Haifeng Shen Jian Tang Ran He NLPR & CEBSIT CASIA AI Labs Didi Chuxing

the target of human pose estimation is to determine the body parts and joint locations of persons in the image. Angular changes, motion blur and occlusion in the natural scenes make this task challenging, while some joints are more difficult to be detected than others. In this paper, we propose an augmented Parallel-Pyramid Net ( P² Net) with feature refinement by dilated bottleneck and attention module. During data preprocessing, we proposed a differentiable auto data augmentation ( DA²) method. We formulate the problem of searching data augmentaion policy in a differentiable form, so that the optimal policy setting can be easily updated by back propagation during training. DA² improves the training efficiency. A parallel-pyramid structure is followed to compensate the information loss introduced by the network. We innovate two fusion structures, i.e. Parallel Fusion and Progressive Fusion, to process pyramid features from backbone network. Both fusion structures leverage the advantages of spatial information affluence at high resolution and semantic comprehension at low resolution effectively. We propose a refinement stage for the pyramid features to further boost the accuracy of our network. By introducing dilated bottleneck and attention module, we increase the receptive field for the features with limited complexity and tune the importance to different feature channels. To further refine the feature maps after completion of feature extraction stage, an Attention Module ( AM) is defined to extract weighted features from different scale feature maps generated by the parallel-pyramid structure. Compared with the traditional up-sampling refining, AM can better capture

关键词： Training Pose estimation Semantics Refining Feature extraction Search problems pattern recognition

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20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：