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

1,414 篇 会议
56 册 图书
27 篇 期刊文献

馆藏范围

1,497 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,009 篇 工学
- 904 篇 计算机科学与技术...
- 399 篇 软件工程
- 390 篇 电气工程
- 125 篇 信息与通信工程
- 119 篇 光学工程
- 83 篇 生物工程
- 62 篇 生物医学工程（可授...
- 54 篇 电子科学与技术（可...
- 38 篇 控制科学与工程
- 33 篇 化学工程与技术
- 27 篇 机械工程
- 17 篇 安全科学与工程
- 16 篇 仪器科学与技术
- 8 篇 材料科学与工程（可...
- 8 篇 建筑学
- 8 篇 土木工程
363 篇 医学
- 360 篇 临床医学
- 26 篇 基础医学(可授医学...
- 25 篇 药学(可授医学、理...
344 篇 理学
- 174 篇 物理学
- 143 篇 数学
- 86 篇 生物学
- 44 篇 统计学（可授理学、...
- 31 篇 化学
- 15 篇 系统科学
87 篇 管理学
- 65 篇 图书情报与档案管...
- 21 篇 管理科学与工程(可...
- 12 篇 工商管理
11 篇 农学
- 11 篇 作物学
10 篇 法学
- 9 篇 社会学
5 篇 经济学
1 篇 教育学
1 篇 文学
1 篇 艺术学

主题

132 篇 computer vision
86 篇 image processing
79 篇 image segmentati...
53 篇 feature extracti...
52 篇 computer graphic...
46 篇 deep learning
45 篇 cameras
35 篇 face recognition
35 篇 artificial intel...
35 篇 shape
30 篇 image reconstruc...
29 篇 object detection
29 篇 robustness
28 篇 image color anal...
24 篇 image enhancemen...
23 篇 image edge detec...
23 篇 biometrics
23 篇 image processing...
22 篇 pattern recognit...
22 篇 layout

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

1,485 篇 英文
9 篇 中文
4 篇 其他

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

共 1497 条记录，以下是461-470 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：

Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences 11

Epipolar Geometry based Learning of Multi-view Depth and Ego...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Prasad, Vignesh Das, Dipanjan Bhowmick, Brojeshwar TCS Res & Amp Innovat Embedded Syst & Amp Robot Kolkata India

ISBN: (纸本)9781450366151

Deep approaches to predict monocular depth and ego-motion have grown in recent years due to their ability to produce dense depth from monocular images. The main idea behind them is to optimize the photometric consistency over image sequences by warping one view into another, similar to direct visual odometry methods. One major drawback is that these methods infer depth from a single view, which might not effectively capture the relation between pixels. Moreover, simply minimizing the photometric loss does not ensure proper pixel correspondences, which is a key factor for accurate depth and pose estimations. In contrast, we propose a 2-view depth network to infer the scene depth from consecutive frames, thereby learning inter-pixel relationships. To ensure better correspondences, thereby better geometric understanding, we propose incorporating epipolar constraints to make the learning more geometrically sound. We use the Essential matrix obtained using Nister's Five Point Algorithm, to enforce meaningful geometric constraints, rather than using it as training labels. This allows us to use lesser no. of trainable parameters compared to state-of-the-art methods. The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way. Such a geometrically constrained learning performs successfully even in cases where simply minimizing the photometric error would fail.

关键词： Monocular Depth Visual Odometry Epipolar Geometry computer vision Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Regularized Random Walk Ranking for Co-Saliency Detection in images 11

Regularized Random Walk Ranking for Co-Saliency Detection in...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Bardhan, Sayanti Jacob, Shibu Indian Inst Technol Madras Madras Tamil Nadu India Natl Inst Ocean Technol Madras Tamil Nadu India

ISBN: (纸本)9781450366151

Co-saliency detection refers to the computational process for identification of common but prominent and salient foreground regions in an image. However most of the co-saliency detection methods suffer from the following two limitations. First, co-saliency detection models largely generate superpixel level co-saliency maps that leads to sacrifice of significant information from the pixel level input images. Second, co-saliency detection frameworks mostly involve redesigned models for detection of co-salient objects in an image group, instead of utilization of the existing single image saliency detection models. To address these problems, we propose a novel framework, Co-saliency via Regularized Random Walk Ranking (CR2WR), which provides highly efficient pixel level co-saliency maps and utilizes existing saliency models on a single image to detect co-salient objects in an image sequence. This is achieved by: (1) Introducing Regularized random walk as the ranking function for a two-stage co-saliency detection framework. (2) Novel weighting function to incorporate more image information in graph construction and utilization of normalized Laplacian matrix for efficient cosaliency maps. (3) Generated saliency maps are fused further with high level priors namely, Location and Objectness priors, that enhances detection of co-salient regions. Suitably designed novel objective functions provide an enriched solution. The proposed model is evaluated on challenging benchmark co-saliency datasets. It is demonstrated that the proposed method outperforms prominent state-of-the-art methods in terms of efficiency and computational time.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Jointly Learning Convolutional Representations to Compress Radiological images and Classify Thoracic Diseases in the Compressed Domain 11

Jointly Learning Convolutional Representations to Compress R...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Ranjan, Ekagra Paul, Soumava Kapoor, Siddharth Kar, Aupendu Sethuraman, Ramanathan Sheet, Debdoot Indian Inst Technol Gauhati India Indian Inst Technol Kharagpur W Bengal India Natl Inst Technol Mangalore Karnataka India Intel Technol India Pvt Ltd Bangalore Karnataka India

ISBN: (纸本)9781450366151

Deep learning models trained in natural images are commonly used for different classification tasks in the medical domain. Generally, very high dimensional medical images are down-sampled by using interpolation techniques before feeding them to deep learning models that are imageNet compliant and accept only low-resolution images of size 224 x 224 px. This popular technique may lead to the loss of key information thus hampering the classification. Significant pathological features in medical images typically being small sized and highly affected. To combat this problem, we introduce a convolutional neural network (CNN) based classification approach which learns to reduce the resolution of the image using an autoencoder and at the same time classify it using another network, while both the tasks are trained jointly. This algorithm guides the model to learn essential representations from high-resolution images for classification along with reconstruction. We have used the publicly available dataset of chest x-rays to evaluate this approach and have outperformed state-of-the-art on test data. Besides, we have experimented with the effects of different augmentation approaches in this dataset and report baselines using some well known imageNet class of CNNs.

关键词： Convolutional autoencoder compression X-Ray classification

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Learning using Graph Regularized Latent Discriminative Cross-domain Triplets 11

Zero-shot Learning using Graph Regularized Latent Discrimina...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Gune, Omkar Vora, Meet Banerjee, Biplab Chaudhuri, Subhasis Indian Inst Technol Mumbai Maharashtra India Indian Inst Technol Roorkee Roorkee Uttar Pradesh India

ISBN: (纸本)9781450366151

Zero-shot learning (ZSL) for visual recognition aims at identifying the previously unseen class samples given a trained model on the labeled visual samples of seen classes and additional class-level semantic side information for all classes. Often ZSL is tackled by learning an embedding function from the visual to semantic space or vice-versa. However, learning this mapping often results in loss of discriminative property of learned embedding space, thus severely compromising the recognition performance on the test samples. In order to ensure improved discrimination in the embedding space, we introduce a ZSL framework by leveraging the intuitive idea of cross-domain triplets based metric learning for learning such a space. Additionally, we introduce a novel graph Laplacian based regularizer which aligns the graph structures of the visual and semantic spaces in the learned embedding space. Simultaneously optimizing both the criteria results in a compact, discriminative, and meaningful embedding space, which is experimentally found to be superior to most of its existing counterparts on both the standard ZSL (AwA and CUB) and the challenging generalized ZSL (AwA1, AwA2, CUB) settings.

关键词： Zero-shot learning cross-domain alignment

来源：评论

学校读者我要写书评

暂无评论

1st International conference on Artificial Intelligence and Cognitive Computing, AICC 2018

1st International Conference on Artificial Intelligence and ...

引用

1st International conference on Artificial Intelligence and Cognitive Computing, AICC 2018

ISBN: (纸本)9789811315794

The proceedings contain 68 papers. The special focus in this conference is on Artificial Intelligence and Cognitive Computing. The topics include: Cognitive-based adaptive path planning for mobile robot in dynamic environment;prediction for indian road network images dataset using feature extraction method;Design and simulation of capacitive MEMS accelerometer;bioinformatics and image processing—Detection of plant diseases;hybrid approach for pixel-wise semantic segmentation using SegNet and squeezenet for embedded platforms;software modernization through model transformations;Semi-automatic annotation of images using eye gaze data (SAIGA);optimizing regression test suite reduction;application monitoring—Active learning approach;acquiring best rules that represent datasets;an automated computer vision system for extraction of retail food product metadata;attacks on two-key elliptic curve digital signature algorithm;bioinformatics: An application in information science;leveraging deep learning for anomaly detection in video surveillance;speaker diarization system using hidden Markov toolkit;Survey: Enhanced trust management for improving QoS in MANETs;a generic survey on medical big data analysis using internet of things;mean estimation under post-stratified cluster sampling scheme;privacy-preserving Naive Bayesian classifier for continuous data and discrete data;learning style recognition: A neural network approach;morphological-based localization of an Iris image;an enhanced efficiency of key management method for wireless sensor networks using mobile agents;a survey on emotion’s recognition using internet of things;KAZE feature based passive image forgery detection;efficiency-based analysis of homomorphic encryption implications;Performance and analysis of human attention using single-channel wireless EEG sensor for medical application;smart heartbeat monitoring system using machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection using Context Dependent Optical Flow 11

Anomaly Detection using Context Dependent Optical Flow

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Mondal, Ranjan Chanda, Bhabatosh Indian Stat Inst Kolkata India

ISBN: (纸本)9781450366151

Anomaly detection is a major task in crowd management through video surveillance. It refers to the events which are deviated from normal events. We have introduced an unsupervised method to detect motion anomaly in surveillance video. In this work we have considered only optical flow as feature. First, for each frame we compute magnitude of optical flow of motion using flownet2 [10]. Then, mean of magnitude of flow due to regular normal motion (given in training data) is computed at each pixel where such motion exists in the training video frames. Our strategy is to compare the motion under consideration against this mean flow magnitude, and we expect that the anomalous motion would differ significantly from normal motion. An autoencoder type network is trained to detect this anomaly. Training data patch is constructed by Interleaving the columns of mean optical flow patch and the corresponding flow patch from each frame. This interleaving is done to incorporate context dependency. The autoencoder is trained to minimize mean-square reconstruction error between input column wise interleaved patch and output (i.e., reconstructed patch) of the autoencoder. During testing, a patch is declared anomalous if the reconstruction error is high compared to the training error. Experiments have been carried out on UCSD and UMN dataset and are compared with other methods. Our method gives comparable results with other state-of-the-art methods.

关键词： Anomaly Detection Motion Representation Activity Recognition Unsupervised Method

来源：评论

学校读者我要写书评

暂无评论

Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian 11

Seek and You Will Find: A New Optimized Framework for Effici...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Das, Sudip Mukherjee, Partha Sarathi Bhattacharya, Ujjwal Indian Stat Inst Kolkata India

ISBN: (纸本)9781450366151

Studies of object detection and localization, particularly pedestrian detection have received considerable attention in recent times due to its several prospective applications such as surveillance, driving assistance, autonomous cars, etc. Also, a significant trend of latest research studies in related problem areas is the use of sophisticated Deep Learning based approaches to improve the benchmark performance on various standard datasets. A trade-off between the speed (number of video frames processed per second) and detection accuracy has often been reported in the existing literature. In this article, we present a new but simple deep learning based strategy for pedestrian detection that improves this trade-off. Since training of similar models using publicly available sample datasets failed to improve the detection performance to some significant extent, particularly for the instances of pedestrians of smaller sizes, we have developed a new sample dataset consisting of more than 80K annotated pedestrian figures in videos recorded under varying traffic conditions. Performance of the proposed model on the test samples of the new dataset and two other existing datasets, namely Caltech Pedestrian Dataset (CPD) and CityPerson Dataset (CD) have been obtained. Our proposed system shows nearly 16% improvement over the existing state-of-the-art result.

关键词： Pedestrian Detection Real Time Detection Pedestrian Dataset Convolutional Neural Networks Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Scale and Rotation Corrected CNNs (SRC-CNNs) for Scale and Rotation Invariant Character Recognition 11

Scale and Rotation Corrected CNNs (SRC-CNNs) for Scale and R...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Swetha, V. C. Mishra, Deepak Gorthi, Sai Subrahmanyam Indian Inst Space Sci & Technol Thiruvananthapuram Kerala India Indian Inst Technol Tirupati Andhra Pradesh India

ISBN: (纸本)9781450366151

Last decade has witnessed rapid growth for the popularity of Convolutional Neural Networks (CNNs), in detecting and classifying objects. The self trainable nature of CNNs makes them the strongest candidate as a classifier and a feature extractor. However, many of the existing CNN architectures fail recognizing texts or objects under input rotation and scaling. This paper introduces an elegant approach, 'Scale and Rotation Corrected CNN (SRC-CNN)' for scale and rotation invariant text recognition, exploiting the concept of principal component of characters. Prior to training and testing with baseline CNN, 'SRC-CNN' maps each character image to a reference orientation and scale, which is again derived from the character image itself. SRC-CNN is capable of recognizing characters in a document, even though they differ in orientation and scale greatly. The proposed method does not demand any training with samples which are scaled or rotated. The performance of proposed approach is validated on different character data sets like MNIST, MNIST_rot_12k and English alphabets and compared with state of the art rotation invariant classification networks. SRC-CNN is a generalized approach and can be extended for rotation and scale invariant classification of many other datasets as well, choosing any appropriate baseline CNN. Here we have demonstrated the generality of the proposed SRC-CNN on MNIST Fashion data set and found to perform well in rotation and scale invariant classification of objects as well. This paper demonstrates how the basic PCA based rotation and scale invariant image recognition can be integrated to CNN for achieving better rotational and scale invariances in classification.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification 11

Multiple Kernel Fisher Discriminant Metric Learning for Pers...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Ali, T. M. Feroz Velmurugan, Rajbabu Patel, Kalpesh K. Chaudhuri, Subhasis Indian Inst Technol Dept Elect Engn Mumbai Maharashtra India

ISBN: (纸本)9781450366151

Person re-identification addresses the problem of matching pedestrian images across disjoint camera views. Design of feature descriptor and distance metric learning are the two fundamental tasks in person re-identification. In this paper, we propose a metric learning framework for person re-identification, where the discriminative metric space is learned using Kernel Fisher Discriminant Analysis (KFDA), to simultaneously maximize the inter-class variance as well as minimize the intra-class variance. We derive a Mahalanobis metric induced by KFDA and argue that KFDA is efficient to be applied for metric learning in person re-identification. We also show how the efficiency of KFDA in metric learning can be further enhanced for person re-identification by using two simple yet efficient multiple kernel learning methods. We conduct extensive experiments on three benchmark datasets for person re-identification and demonstrate that the proposed approaches have competitive performance with state-of-the-art methods.

关键词： Person Re-identification Metric Learning Kernel Fisher Discriminant Analysis Multiple Kernel Fisher Discriminant Analysis

来源：评论

学校读者我要写书评

暂无评论

Nrityantar: Pose oblivious indian classical dance sequence classification system 11

Nrityantar: Pose oblivious Indian classical dance sequence c...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Kaushik, Vinay Mukherjee, Prerana Lall, Brejesh IIT Delhi Dept Elect Engn Delhi India

ISBN: (纸本)9781450366151

In this paper, we attempt to advance the research work done in human action recognition to a rather specialized application namely indian Classical Dance (ICD) classification. The variation in such dance forms in terms of hand and body postures, facial expressions or emotions and head orientation makes pose estimation an extremely challenging task. To circumvent this problem, we construct a pose-oblivious shape signature which is fed to a sequence learning framework. The pose signature representation is done in two-fold process. First, we represent person-pose in first frame of a dance video using symmetric Spatial Transformer Networks (STN) to extract good person object proposals and CNNb-ased parallel single person pose estimator (SPPE). Next, the pose basis are converted to pose flows by assigning a similarity score between successive poses followed by non-maximal suppression. Instead of feeding a simple chain of joints in the sequence learner which generally hinders the network performance we constitute a feature vector of the normalized distance vectors, flow, angles between anchor joints which captures the adjacency configuration in the skeletal pattern. Thus, the kinematic relationship amongst the body joints across the frames using pose estimation helps in better establishing the spatio-temporal dependencies. We present an exhaustive empirical evaluation of state-of-the-art deep network based methods for dance classification on ICD dataset.

关键词： Pose Signature Dance classification Action Recognition Motion and Video Analysis Deep Learning Supervised Learning LSTM

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 << < 43 44 45 46 47 48 49 50 51 52 > >>

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：