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

1,413 篇 会议
54 册 图书
27 篇 期刊文献

馆藏范围

1,494 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,010 篇 工学
- 901 篇 计算机科学与技术...
- 410 篇 软件工程
- 389 篇 电气工程
- 131 篇 信息与通信工程
- 122 篇 光学工程
- 90 篇 生物工程
- 65 篇 生物医学工程（可授...
- 58 篇 电子科学与技术（可...
- 38 篇 控制科学与工程
- 34 篇 化学工程与技术
- 29 篇 机械工程
- 21 篇 仪器科学与技术
- 17 篇 安全科学与工程
- 10 篇 材料科学与工程（可...
- 9 篇 建筑学
- 8 篇 土木工程
347 篇 医学
- 344 篇 临床医学
- 27 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
333 篇 理学
- 158 篇 物理学
- 147 篇 数学
- 93 篇 生物学
- 47 篇 统计学（可授理学、...
- 32 篇 化学
- 16 篇 系统科学
92 篇 管理学
- 69 篇 图书情报与档案管...
- 23 篇 管理科学与工程(可...
- 13 篇 工商管理
12 篇 农学
- 12 篇 作物学
10 篇 法学
- 9 篇 社会学
6 篇 经济学
3 篇 教育学
2 篇 文学
1 篇 艺术学

主题

142 篇 computer vision
80 篇 image processing
77 篇 image segmentati...
54 篇 computer graphic...
54 篇 feature extracti...
52 篇 cameras
46 篇 deep learning
38 篇 shape
35 篇 face recognition
34 篇 image reconstruc...
32 篇 artificial intel...
30 篇 robustness
28 篇 object detection
28 篇 image color anal...
25 篇 image enhancemen...
25 篇 image edge detec...
25 篇 pattern recognit...
25 篇 layout
24 篇 biometrics
23 篇 image processing...

机构

20 篇 indian statistic...
19 篇 indian institute...
17 篇 department of co...
14 篇 computer vision ...
12 篇 indian institute...
11 篇 department of el...
10 篇 indian inst tech...
9 篇 indian stat inst...
9 篇 indian institute...
9 篇 indian inst tech...
9 篇 indian institute...
8 篇 indian institute...
8 篇 department of el...
8 篇 indian institute...
8 篇 indian inst sci ...
8 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian institute...
7 篇 indian inst tech...
7 篇 indian inst tech...

作者

40 篇 chaudhury santan...
29 篇 chaudhuri subhas...
26 篇 mukherjee jayant...
20 篇 das sukhendu
19 篇 raman shanmugana...
18 篇 santanu chaudhur...
17 篇 balasubramanian ...
16 篇 harit gaurav
16 篇 lall brejesh
15 篇 babu r. venkates...
15 篇 chanda bhabatosh
14 篇 mukherjee dipti ...
13 篇 das partha prati...
12 篇 biswas prabir ku...
12 篇 mishra deepak
11 篇 raman balasubram...
11 篇 sukhendu das
10 篇 biswas soma
10 篇 bhowmick partha
10 篇 bhavsar arnav

语言

1,484 篇 英文
7 篇 中文
3 篇 其他

检索条件"任意字段=Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing"

共 1494 条记录，以下是1401-1410 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：

Temporal Modeling of EEG Signals using Block Sparse Variational Bayes Framework 18

Temporal Modeling of EEG Signals using Block Sparse Variatio...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Shruti Sharma Santanu Chaudhury Jayadeva Jayadeva Indian Institute of Technology Delhi

ISBN: (纸本)9781450366151

Compressed Sensing (CS) has emerged as an alternate method to acquire high dimensional signals effectively by exploiting the sparsity assumption. However, owing to non-sparse and non-stationary nature, it is extremely difficult to process Electroencephalograph (EEG) signals using CS paradigm. The success of Bayesian algorithms in recovering non-sparse signals has triggered the research in CS based models for neurophysiological signal processing. In this paper, we address the problem of Temporal Modeling of EEG Signals using Block Sparse Variational Bayes (SVB) Framework. Temporal correlation of EEG signals is modeled blockwise using normal variance scale mixtures parameterized via some random and deterministic parameters. Variational inference is exploited to infer the random parameters and Expectation Maximization (EM) is used to obtain the estimate of deterministic parameters. To validate the framework, we present experimental results for benchmark State Visual Evoked Potential (SSVEP) dataset with 40-target Brain-computer Interface (BCI) speller using two frequency recognition algorithms viz. Canonical Correlation Analysis (CCA) and L1-regularized Multiway CCA. Results show that the proposed temporal model is highly useful in processing SSVEP-EEG signals irrespective of the recognition algorithms used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BatchOut: Batch-level feature augmentation to improve robustness to adversarial examples 18

BatchOut: Batch-level feature augmentation to improve robust...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Akshayvarun Subramanya Konda Reddy Mopuri R. Venkatesh Babu Video Analytics Lab Indian Institute of Science Bangalore India

ISBN: (纸本)9781450366151

Machine Learning models are known to be susceptible to small but structured changes to their inputs that can result in wrong inferences. It has been shown that such samples, called adversarial samples, can be created rather easily for standard neural network architectures. These adversarial samples pose a serious threat for deploying state-of-the-art deep neural network models in the real world. We propose a feature augmentation technique called BatchOut to learn robust models towards such examples. The proposed approach is a generic feature augmentation technique that is not specific to any adversary and handles multiple attacks. We evaluate our algorithm on benchmark datasets and architectures to show that models trained using our method are less susceptible to adversaries created using multiple methods.

关键词： Adversarial examples

来源：评论

学校读者我要写书评

暂无评论

ContextCLIP: Contextual Alignment of image-Text pairs on CLIP visual representations 22

ContextCLIP: Contextual Alignment of Image-Text pairs on CLI...

引用

proceedings of the Thirteenth indian conference on computer vision, graphics and image processing

作者： Chanda Grover Indra Deep Mastan Debayan Gupta Ashoka University India The LNM Institute of Information Technology Jaipur India

ISBN: (纸本)9781450398220

State-of-the-art empirical work has shown that visual representations learned by deep neural networks are robust in nature and capable of performing classification tasks on diverse datasets. For example, CLIP demonstrated zero-shot transfer performance on multiple datasets for classification tasks in a joint embedding space of image and text pairs. However, it showed negative transfer performance on standard datasets, e.g., BirdsNAP, RESISC45, and MNIST. In this paper, we propose ContextCLIP, a contextual and contrastive learning framework for the contextual alignment of image-text pairs by learning robust visual representations on Conceptual Captions dataset. Our framework was observed to improve the image-text alignment by aligning text and image representations contextually in the joint embedding space. ContextCLIP showed good qualitative performance for text-to-image retrieval tasks and enhanced classification accuracy. We evaluated our model quantitatively with zero-shot transfer and fine-tuning experiments on CIFAR-10, CIFAR-100, Birdsnap, RESISC45, and MNIST datasets for classification task.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

STTGC-Net: Spatial-Temporal Transformer with Graph Convolution for Skeleton-Based Action Recognition 23

STTGC-Net: Spatial-Temporal Transformer with Graph Convoluti...

引用

proceedings of the fourteenth indian conference on computer vision, graphics and image processing

作者： Tanishka Yagneshwar Snehasis Mukherjee Computer Science and Engineering Shiv Nadar Institute of Eminence IN Computer Science and Engineering Shiv Nadar Institute of Eminence Greater Noida India IN

ISBN: (纸本)9798400716256

Skeleton data plays an important role in human action recognition due to the compact and distinct information of human poses provided by the skeleton data. Skeleton-based action recognition is gaining interest due to the availability of Kinect cameras at a reasonable price. With the growing popularity of Geometric deep learning, Graph Convolutional networks (GCN) are extensively used for processing skeleton data, due to their ability to model data topology. It has been found that Spatial-Temporal Graph Convolutional Networks (ST-GCN) are efficient in learning both spatial and temporal dependencies on non-Euclidean data, such as skeleton graphs. However, the state-of-the-art ST-GCN models lack flexibility in feature extraction and do not explicitly consider the high-order Spatio-Temporal significance of the spatial connection topology and intensity of the joints. They lack an attention module that can help us learn together when and where to concentrate on a certain action in the action sequence. The transformer-based methods can effectively capture long-distance dependencies. However, using just a traditional transformer approach overlooks the graph structure in the data, which can provide valuable information about the inter-relationships among the joint points during actions. To address this problem, we propose an architecture named Spatial-Temporal Transformer Network with Graph Convolution (STTGC-Net), that can flexibly capture local and global contexts. Spatial-Temporal Graph Convolutional Networks and Spatial-Temporal Transformer Attention Modules are sequentially fused to create the proposed framework. The ST-GCNs capture temporal dynamics, hierarchy, and local topological information at several levels, and the transformer attention module displays the correlations between joint pairs in global topology via dynamic attention, which resolves the mentioned constraints of the GCN and transformer. We validate our model by conducting tests on the NTU 60 and NTU 12

关键词： Attention ST-GCN action recognition skeleton transformer

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic segmentation of tissue cells from confocal microscope images

Semi-automatic segmentation of tissue cells from confocal mi...

引用

International conference on Pattern Recognition

作者： P.S.Umesh Adiga B.B. Chaudhuri K. Rodenacker Computer Vision & Pattern Recognition Unit Indian Statistical Institute Calcutta India Institute of Pathology GSF Munich Germany

We present a semi-automatic method for extracting the 3D boundary of the cells in a compact tissue cross-section photographed by a confocal microscope. The confocal microscope provides pictures at different depths of the cells which can be considered as the image slices of the tissue section. Segmentation of cell boundary from different image slices and combining them to obtain 3D surface automatically is a difficult task. We have developed an approach where given one segmented image slice, the other image slices can be automatically segmented in a layered approach. The idea is to use the information of the previous segmented image slice for segmenting the current image slice.

关键词： image segmentation Microscopy Laser beams image processing computer vision Pattern recognition Pathology Lighting Hardware Laser noise

来源：评论

学校读者我要写书评

暂无评论

Real time object tracking for high performance system using GPGPU

Real time object tracking for high performance system using ...

引用

International conference on Information processing (ICIP)

作者： Kinjal B. Mistree Ashutosh Dutt Shraddha V. Kothiya Department of Computer Engineering Chhotubhai Gopalbhai Patel Institute of Technology Bardoli India Indian Space Research Organization Ahmedabad India

ISBN: (纸本)9781467377591

Real time object tracking is the process of locating moving objects over time using the camera in video sequences in real time. The objective of object tracking is to associate target objects in consecutive video frames. Object tracking requires location and shape or features of objects in the video frames. Every tracking algorithm needs to detect moving object. So object detection is the preceding step of object tracking in computer vision applications. After that, detected object can be extracted by the feature of moving object to track that moving object into video scene. It is challenging task in image processing to track the objects into consecutive frames. Various challenges can arise due to complex object motion, irregular shape of object, occlusion of object to object and object to scene and real time processing requirements. Object tracking has a variety of uses, some of which are: surveillance and security, traffic monitoring, video communication, robot vision and animation.

关键词： Streaming media Object tracking Real-time systems Estimation graphics processing units Standards Central processing Unit

来源：评论

学校读者我要写书评

暂无评论

Estimation of Ball Possession Statistics in Soccer Video 18

Estimation of Ball Possession Statistics in Soccer Video

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Saikat Sarkar Amlan Chakrabarti Dipti Prasad Mukherjee Bangabasi College University of Calcutta Kolkata India A. K. Choudhury School of Information Technology University of Calcutta Kolkata India Indian Statistical Institute Kolkata India

ISBN: (纸本)9781450366151

In this work, we have estimated ball possession statistics from the video of a soccer match. The ball possession statistics is calculated based on the valid pass counts of two playing teams. We propose a player-ball interaction energy function to detect ball pass event. Based on position and velocity of the ball and players, a model for interaction energy is defined. The energy increases when the ball is closer and about to collide with a player. Lower energy denotes that the ball is freely moving and not near to any player. The interaction energy generates a binary state sequence which determines a valid pass or a miss-pass. We assess the performance of our model on publicly available soccer videos and have achieved close to 83% accuracy.

关键词： Ball possession statistics

来源：评论

学校读者我要写书评

暂无评论

A novel SOM-based approach for active contour modeling

A novel SOM-based approach for active contour modeling

引用

Intelligent Sensors, Sensor Networks and Information processing conference (ISSNIP)

作者： Y.V. Venkatesh S.K. Raja N. Ramya Computer Vision Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India

We integrate the advantages of SOM- and snake-based ACMs in order to extract the desired contour from images. We employ: (i) the feature points to guide the contour, as in the case of SOM-based ACMs; (ii) the gradient and intensity variations in a local region to control the contour movement. However, in contrast with the snake-based ACMs, we do not use an explicit energy functional based on gradient or intensity. The algorithm is tested on synthetic binary and gray-level images, and the results show the superiority of the proposed algorithm over other conventional SOM- and snake-based ACM algorithms.

关键词： Active contours Neurons computer vision image edge detection Deformable models Neural networks Laboratories Testing Joining processes Object detection

来源：评论

学校读者我要写书评

暂无评论

A Rapid Non-Linear Diffusion Compressed Sensing parallel MR image Reconstruction 18

A Rapid Non-Linear Diffusion Compressed Sensing parallel MR ...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Ajin Joy Joseph Suresh Paul Indian Institute of Information Technology and Management-Kerala Trivandrum India

ISBN: (纸本)9781450366151

Optimization of the tradeoff between computation time and image quality is essential for reconstructing high-quality magnetic resonance image (MRI) from a limited number of acquired samples in a short time using compressed sensing (CS) algorithms. In this paper, we achieve this for the edge preserving non-linear diffusion reconstruction (NLDR) which eliminates the critical step-size tuning of the total variation (TV) based CS-MRI. Based on optimization of contrast parameter that controls noise and signal in sensitivity modulated channel images, we propose an â-switching NLDR technique for a faster approximation of reconstruction image without affecting the image quality. Proposed algorithm exploits the difference in the extent of undersampling artifacts in signal-background regions of the channel images to arrive at different estimates of contrast parameter, leading to an effective optimization of speed and quality. While maintaining better image quality as compared to conventional TV reconstruction, the switched NLDR also achieves 25-35% gain in convergence time over NLDR without switching. This makes the switched NLDR a better candidate for fast reconstruction over traditional TV and NLDR approaches. In the detailed numerical experiments, we have compared and optimized the tradeoff for various state-of-the-art choices of contrast parameter.

关键词： contrast parameter

来源：评论

学校读者我要写书评

暂无评论

image Co-segmentation using Graph Convolution Neural Network 18

Image Co-segmentation using Graph Convolution Neural Network

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Sayan Banerjee Avik Hati Subhasis Chaudhuri Rajbabu Velmurugan Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9781450366151

image co-segmentation is jointly segmenting two or more images sharing common foreground objects. In this paper, we propose a novel graph convolution neural network (graph CNN) based end-to-end model for performing co-segmentation. At the beginning, each input image is over-segmented into a set of superpixels. Next, a weighted graph is formed using the over-segmented images exploiting spatial adjacency and both intra-image and inter-image feature similarities among the image superpixels (nodes). Subsequently, the proposed network, consisting of graph convolution layers followed by node classification layers, classifies each superpixel either into the common foreground or its complement. During training, along with the co-segmentation network, an additional network is introduced to exploit the corresponding semantic labels, and the two networks share the same weights in graph convolution layers. The whole model is learned in an end-to-end fashion using a novel cost function comprised of a superpixel wise binary cross entropy and a multi-label cross entropy. We also use empirical class probabilities in the loss function to deal with class imbalance. Experimental results reflect that the proposed technique is very competitive with the state-of-the-art methods on two challenging datasets, Internet and Pascal-VOC.

关键词： Co-segmentation

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150页 << < 137 138 139 140 141 142 143 144 145 146 > >>

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：