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

920 篇 会议
61 册 图书
23 篇 期刊文献

馆藏范围

1,004 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

821 篇 工学
- 719 篇 计算机科学与技术...
- 375 篇 软件工程
- 336 篇 电气工程
- 108 篇 信息与通信工程
- 105 篇 光学工程
- 91 篇 生物工程
- 54 篇 生物医学工程（可授...
- 41 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 28 篇 控制科学与工程
- 21 篇 机械工程
- 15 篇 安全科学与工程
- 12 篇 仪器科学与技术
- 10 篇 土木工程
- 8 篇 建筑学
- 8 篇 航空宇航科学与技...
- 7 篇 交通运输工程
280 篇 理学
- 126 篇 物理学
- 118 篇 数学
- 94 篇 生物学
- 39 篇 统计学（可授理学、...
- 33 篇 化学
- 11 篇 系统科学
269 篇 医学
- 269 篇 临床医学
- 25 篇 基础医学(可授医学...
- 22 篇 药学(可授医学、理...
75 篇 管理学
- 63 篇 图书情报与档案管...
- 13 篇 管理科学与工程(可...
- 8 篇 工商管理
10 篇 法学
- 9 篇 社会学
4 篇 农学
3 篇 经济学
1 篇 教育学

主题

46 篇 computer graphic...
44 篇 artificial intel...
42 篇 image processing...
33 篇 computer vision
29 篇 deep learning
27 篇 pattern recognit...
25 篇 image segmentati...
22 篇 computer imaging...
20 篇 image enhancemen...
19 篇 graphics process...
17 篇 face recognition
17 篇 image reconstruc...
15 篇 cameras
13 篇 image processing
11 篇 generative adver...
10 篇 object detection
10 篇 computer communi...
10 篇 pixels
10 篇 feature extracti...
10 篇 machine learning

机构

15 篇 indian institute...
11 篇 indian statistic...
11 篇 carnegie mellon ...
11 篇 hebrew universit...
11 篇 google research
10 篇 indian inst tech...
8 篇 indian stat inst...
8 篇 indian inst tech...
7 篇 indian institute...
7 篇 indian institute...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 technische unive...
7 篇 indian inst sci ...
6 篇 indian institute...
6 篇 indian institute...
6 篇 indian inst tech...
6 篇 technical univer...
6 篇 indian inst tech...
6 篇 department of co...

作者

31 篇 chaudhury santan...
26 篇 mukherjee jayant...
25 篇 chaudhuri subhas...
19 篇 das sukhendu
15 篇 babu r. venkates...
14 篇 das partha prati...
14 篇 lall brejesh
14 篇 raman shanmugana...
13 篇 harit gaurav
12 篇 mukherjee dipti ...
12 篇 chanda bhabatosh
12 篇 mishra deepak
11 篇 martial hebert
11 篇 yair weiss
11 篇 vittorio ferrari
11 篇 cristian sminchi...
11 篇 biswas prabir ku...
10 篇 banerjee biplab
10 篇 biswas soma
10 篇 sur arijit

语言

997 篇 英文
3 篇 俄文
3 篇 中文
2 篇 其他

检索条件"任意字段=15th Indian Conference on Computer Vision Graphics and Image Processing"

共 1004 条记录，以下是961-970 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

From an image to a Scene: Learning to Imagine the World from a Million 360◦ Videos 38

From an Image to a Scene: Learning to Imagine the World from...

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Wallingford, Matthew Bhattad, Anand Kusupati, Aditya Ramanujan, Vivek Deitke, Matt Kakade, Sham Kembhavi, Aniruddha Mottaghi, Roozbeh Ma, Wei-Chiu Farhadi, Ali University of Washington United States Toyota Technological Institute Chicago United States Harvard University United States Allen Institute for AI United States

three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and object-centric 3D datasets have shown to be effective in training models that have 3D understanding of objects. However, applying a similar approach to real-world objects and scenes is difficult due to a lack of large-scale data. Videos are a potential source for real-world 3D data, but finding diverse yet corresponding views of the same content has shown to be difficult at scale. Furthermore, standard videos come with fixed viewpoints, determined at the time of capture. this restricts the ability to access scenes from a variety of more diverse and potentially useful perspectives. We argue that large scale 360◦ videos can address these limitations to provide: scalable corresponding frames from diverse views. In this paper, we introduce 360-1M, a 360◦ video dataset, and a process for efficiently finding corresponding frames from diverse viewpoints at scale. We train our diffusion-based model, ODIN1, on 360-1M. Empowered by the largest real-world, multi-view dataset to date, ODIN is able to freely generate novel views of real-world scenes. Unlike previous methods, ODIN can move the camera through the environment, enabling the model to infer the geometry and layout of the scene. Additionally, we show improved performance on standard novel view synthesis and 3D reconstruction benchmarks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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 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

An incremental topological map building using monocular vision 18

An incremental topological map building using monocular visi...

引用

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

作者： Soumabha Bhowmick Jayanta Mukherjee Alok Kanti Deb Indian Institute of Technology Kharagpur India Institute for Clarity in Documentation Kharagpur India

ISBN: (纸本)9781450366151

In this work a memory efficient topological map generation algorithm has been proposed using local descriptors. A topological map is a graphical data structure where each node signifies an area within an environment. these nodes are connected by links which ensure the presence of a physical path between the pair. Experiments have been conducted with feature descriptors using a vocabulary based approach. these approaches take huge memory and time. To deal with these a KD-tree based map generation algorithm has been proposed where each node in the tree stores a descriptor and a table of occurrence. this table stores node ids of the locations, where the corresponding descriptor is present. the map generation algorithm is a two-stage algorithm. In the first stage, the visual similarity based position identification is conducted in order to check for loop-closures. It is followed by a corrective step on validating the decision of loop closure, if any. the table of occurrence keeps track of presence of each descriptor. the least occurring descriptors are pruned at regular intervals, making the algorithm memory-efficient. the approach has been experimented with several benchmark datasets.

关键词： KD-tree

来源：评论

学校读者我要写书评

暂无评论

On-Demand Augmentation of Contour Trees 18

On-Demand Augmentation of Contour Trees

引用

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

作者： Mohit Sharma Vijay Natarajan Indian Institute of Science Bangalore

ISBN: (纸本)9781450366151

the contour tree represents the topology of level sets of a scalar function. Nodes of the tree correspond to critical level sets and arcs of the tree represent a collection of topologically equivalent level sets connecting two critical level sets. the augmented contour tree contains degree-2 nodes on the arcs that represent regular level sets. the degree-2 nodes correspond to regular points of the scalar function and other critical points that do not affect the number of level set components. the augmented contour tree is significantly larger in size and requires more effort to compute when compared to the contour tree. Applications of the contour tree to data exploration and visualization require the augmented contour tree. Current approaches propose algorithms to compute the contour tree and the augmented contour tree from scratch. Precomputing and storing the large augmented contour tree will not be necessary if the contour tree can be augmented on-demand. this paper poses the problem of computing the augmented contour tree given a contour tree as input. Computational experiments demonstrate that the on-demand augmentation can be computed fast while resulting in good memory savings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Neural Network Based Approach for Geo-Localizing Events in Crowd Sourced Videos 2018

A Neural Network Based Approach for Geo-Localizing Events in...

引用

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

作者： Amit More Subhasis Chaudhuri Indian Institute of Technology Bombay Mumbai Maharastra

ISBN: (纸本)9781450366151

Popular events are often video recorded simultaneously by a general crowd using smartphones. In the present work, we propose a robust recurrent neural network (RNN) based approach for geo-localizing these events using sensor data collected by user smartphones while recording such events. For this task we use GPS and compass sensors, which are commonly available on the smartphones. the circular nature (modulo 2π) of the orientation data from compass limits the ability of the classical neural networks (NN) to geo-localize these events. We mitigate this issue by incorporating circular nodes in our network and show the performance improvements. We train the proposed NN model using simulated data and apply it directly on real data. We train several RNN models using this strategy and show our analyses. the proposed work outperforms all previous approaches in terms of event geo-localization accuracy.

关键词： Event Geo-localization Neural Network Compass Data Smartphone Circular Nodes GPS data

来源：评论

学校读者我要写书评

暂无评论

Bag of Visual Words based Correlation Filter Tracker (BoVW-CFT) 18

Bag of Visual Words based Correlation Filter Tracker (BoVW-C...

引用

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

作者： Priya Mariam Raju Deepak Mishra Gorthi Rama Krishna Sai Subrahmanyam Indian Institute of Space Science and Technology Thiruvananthapuram Kerala Indian Institute of Technology Tirupati Andhra Pradesh

ISBN: (纸本)9781450366151

Accurate and robust visual object tracking is one of the most challenging computer vision problems. Recently, discriminative correlation filter trackers have shown promising results on benchmark datasets with continuous performance improvements in tracking accuracy and robustness. Still, these algorithms fail to track as the target object and background conditions undergo drastic changes over time. they are also incapable to resume tracking once the target is lost, limiting the ability to track long term. the proposed BoVW-CFT is a classifier-based generic technique to handle tracking uncertainties in correlation filter trackers. Tracking failures in correlation trackers are automatically identified and an image classifier with training, testing and online update stages is proposed as detector in the tracking scenario using Bag of Visual Words (BoVW) features. the proposed detector falls under the parts based model and is quite well suited in the tracking framework. Further, the online training stage in the proposed framework with updated model or training samples, incorporates temporal information, helping to detect rotated, blurred and scaled versions of the target. On detecting a target loss in the correlation tracker, the trained classifier, referred to as detector, is invoked to re-initialize the tracker with the actual target location. therefore, for each tracking uncertainty, two output patches are obtained, one each from the base tracker and the classifier. the final target location is estimated using the normalized cross-correlation with the initial target patch. the method has the advantages of mitigating the model drift in correlation trackers and learns a robust model that tracks long term. Extensive experimental results demonstrate an improvement of 4.1% in the expected overlap, 1.86% in accuracy and 15.46% in robustness on VOT2016 and 1.82% in overlap precision, 2.32% in AUC and 2.87% in success rates on OTB100.

关键词：

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101页 << < 92 93 94 95 96 97 98 99 100 101 > >>

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：