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351-360 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：

DeepPFCN: Deep Parallel Feature Consensus Network for Person Re-identification 7th

DeepPFCN: Deep Parallel Feature Consensus Network for Person...

引用

7th National conference on computer vision, Pattern Recognition, image processing, and graphics, NCVPRIPG 2019

作者： Singh, Shubham Kumar Miyapuram, Krishna P. Raman, Shanmuganathan Indian Institute of Technology Gandhinagar PalajGujarat382355 India

ISBN: (纸本)9789811586965

Person re-identification aims to associate images of the same person over multiple non-overlapping camera views at different times. Depending on the human operator, manual re-identification in large camera networks is highly time consuming and erroneous. Automated person re-identification is required due to the extensive quantity of visual data produced by rapid inflation of large scale distributed multi-camera systems. The state-of-the-art works focus on learning and factorize person appearance features into latent discriminative factors at multiple semantic levels. We propose Deep Parallel Feature Consensus Network (DeepPFCN), a novel network architecture that learns multi-scale person appearance features using convolutional neural networks. This model factorizes the visual appearance of a person into latent discriminative factors at multiple semantic levels. Finally consensus is built. The feature representations learned by DeepPFCN are more robust for the person re-identification task, as we learn discriminative scale-specific features and maximize multi-scale feature fusion selections in multi-scale image inputs. We further exploit average and max pooling in separate scale for person-specific task to discriminate features globally and locally. We demonstrate the re-identification advantages of the proposed DeepPFCN model over the state-of-the-art re-identification methods on three benchmark datasets - Market1501, DukeMTMCreID, and CUHK03. We have achieved mAP results of 75.8%, 64.3%, and 52.6% respectively on these benchmark datasets. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Scene Adaptive Cosmetic Makeup Transfer 18

Scene Adaptive Cosmetic Makeup Transfer

引用

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

作者： Rishubh Parihar Aniket Dashpute Prem Kalra Indian Institute of Technology Delhi Hauz Khas New Delhi

ISBN: (纸本)9781450366151

Cosmetic makeup is an art in itself which people use to often enhance their beauty and express themselves. Putting on makeup is a tedious task, so who would not love to see themselves in makeup before physically applying it? In this work, we demonstrate the transfer of makeup from a reference makeup image to some subject image. Our technique involves generation and use of 3D face models of these images. Some nice features of our pipeline include: (1) process adapts to the lighting conditions of the subject image. (2) after makeup on subject image, it is possible to view it in different indoor and outdoor lighting conditions. (3) accessories can be added realistically with proper lighting so that they naturally fit in the subject's *** show that these also make our makeup look very realistic and improved compared to many existing *** main advantage of our novel pipeline is the requirement of only the subject and reference images as input. This is unlike other techniques using 3D models which require extensive data collection.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Gesture Recognition with Pose-based CNN Features derived from videos using LSTM 18

Dynamic Gesture Recognition with Pose-based CNN Features der...

引用

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

作者： Kankana Roy Rajiv R. Sahay Computational Vision Laboratory Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Computational Vision Laboratory Department of Electrical Engineering Indian Institute of Technology Kharagpur

ISBN: (纸本)9781450366151

In this work, we address the problem of dynamic gesture recognition using a pose based video descriptor. The proposed approach takes as input video frames and extracts pose-specific image regions which are further processed by a pre-trained Convolutional Neural Network (CNN) to derive a pose-based descriptor for each frame. A Long Short Term Memory (LSTM) network is trained from scratch for dynamic gesture classification by learning long-term spatiotemporal relations among features. We also demonstrate that only using video data (RGB frames and optical flow) one can design an effective model for recognizing dynamic gestures. We utilize ChaLearn multi-modal gesture challenge dataset [13] and Cambridge hand gesture dataset [18] for evaluation of the proposed algorithm achieving an accuracy of 91.27% and 96% respectively using only RGB data.

关键词： Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-scale HOG Feature Used in Object Detection 10

Multi-scale HOG Feature Used in Object Detection

引用

10th International conference on graphics and image processing (ICGIP)

作者： Li, Jin Zhang, Hong Zhang, Lei Li, Yawei Kang, Qiaochu Luo, Zhaohui Wu, Yujie Beihang Univ Image Ctr Sch Astronaut Beijing Peoples R China Univ Massachusetts Amherst MA 01003 USA

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

Object detection is one of the most popular and difficult field in computer vision. Although deep learning methods have great performance on object detection. For specific application, algorithms which use hand-crafted features are still widely used. One main problem in object detection is the scale problem. Algorithms usually use image pyramid to cover as many scales as possible. But gaps still exist between scale levels in image pyramid. Our work extends some sub scale level to fill the gaps between image pyramids. To this end, we use Gaussian Scales Pyramid to generate sub-scale image and extract HOG feature on the sub-scale. We use framework offered by DPM algorithm and make modification on it. We compare the result of our method with DPM baseline on Pascal VOC database. Our work has great performance on some categories and makes an improvement on the overall performance. This work can be used in other object detection frameworks. We apply multi-scale HOG feature on pre-process procedure of our own detection framework and test it on our own dataset. Then the framework gains performance improvement on precision and recall rate of the pre-process procedure comparing to the original HOG feature architecture.

关键词： multi-scale HOG object detection

来源：评论

学校读者我要写书评

暂无评论

Multimodal Egocentric Activity Recognition Using Multi-stream CNN 2018

Multimodal Egocentric Activity Recognition Using Multi-strea...

引用

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

作者： Javed Imran Balasubramanian Raman Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India

ISBN: (纸本)9781450366151

Egocentric activity recognition (EAR) is an emerging area in the field of computer vision research. Motivated by the current success of Convolutional Neural Network (CNN), we propose a multi-stream CNN for multimodal egocentric activity recognition using visual (RGB videos) and sensor stream (accelerometer, gyroscope, etc.). In order to effectively capture the spatio-temporal information contained in RGB videos, two types of modalities are extracted from visual data: Approximate Dynamic image (ADI) and Stacked Difference image (SDI). These image-based representations are generated both at clip level as well as entire video level, and are then utilized to finetune a pretrained 2D-CNN called MobileNet, which is specifically designed for mobile vision applications. Similarly for sensor data, each training sample is divided into three segments, and a deep 1D-CNN network is trained (corresponding to each type of sensor stream) from scratch. During testing, the softmax scores of all the streams (visual + sensor) are combined by late fusion. The experiments performed on multimodal egocentric activity dataset demonstrates that our proposed approach can achieve state-of-the-art results, outperforming the current best handcrafted and deep learning based techniques.

关键词： Stacked Difference image Dynamic image Egocentric Activity Recognition Convolutional Neural Network Multimodal Fusion

来源：评论

学校读者我要写书评

暂无评论

4th Workshop on Document Analysis and Recognition, DAR 2018, held in Conjunction with the 11th indian conference on vision, graphics, and image processing, ICVGIP 2018

4th Workshop on Document Analysis and Recognition, DAR 2018,...

引用

4th Workshop on Document Analysis and Recognition, DAR 2018, held in Conjunction with the 11th indian conference on vision, graphics, and image processing, ICVGIP 2018

ISBN: (纸本)9789811393600

The proceedings contain 14 papers. The special focus in this conference is on Document Analysis and Recognition. The topics include: Word-Wise Handwriting Based Gender Identification Using Multi-Gabor Response Fusion;a Secure and Light Weight User Authentication System Based on Online Signature Verification for Resource Constrained Mobile Networks;benchmark Datasets for Offline Handwritten Gurmukhi Script Recognition;benchmark Dataset: Offline Handwritten Gurmukhi City Names for Postal Automation;attributed Paths for Layout-Based Document Retrieval;textual Content Retrieval from Filled-in Form images;A Study on the Effect of CNN-Based Transfer Learning on Handwritten Indic and Mixed Numeral Recognition;symbol Spotting in Offline Handwritten Mathematical Expressions;online Handwritten Bangla Character Recognition Using Frechet Distance and Distance Based Features;an Efficient Multi Lingual Optical Character Recognition System for indian Languages Through Use of Bharati Script;telugu Word Segmentation Using Fringe Maps;an Efficient Character Segmentation Algorithm for Connected Handwritten Documents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Simulation of Human Musculature 2018

Real-time Simulation of Human Musculature

引用

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

作者： Neeladrishekhar Kanjilal Parag Chaudhuri Dept. of Computer Science & Engg. IIT Bombay

ISBN: (纸本)9781450366151

We present a reduced model based on position based dynamics for real-time simulation of human musculature. We demonstrate our methods on the muscles of the human arm. Co-simulation of all the muscles of the human arm allow us to accurately track the development of stresses and strains in the muscles, when the arm is moved. We evaluate our method for accuracy by comparing it with gold standard simulation models based on finite volume methods, and demonstrate the stability of the method under flexion, extension and torsion.

关键词： Human muscle simulation position based dynamics shape matching

来源：评论

学校读者我要写书评

暂无评论

A Bottom-Up and Top-Down Approach for image Captioning using Transformer 18

A Bottom-Up and Top-Down Approach for Image Captioning using...

引用

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

作者： Sandeep Narayan Parameswaran Sukhendu Das Indian Institute of Technology Madras Chennai Tamil Nadu India

ISBN: (纸本)9781450366151

Describing the contents of an image automatically has been a fundamental problem in the field of artificial intelligence and computer vision. Existing approaches are either top-down, which start from a simple representation of an image and convert it into a textual description; or bottom-up, which come up with attributes describing numerous aspects of an image to form the caption or a combination of both. Recurrent neural networks (RNN) enhanced by Long Short-Term Memory networks (LSTM) have become a dominant component of several frameworks designed for solving the image captioning task. Despite their ability to reduce the vanishing gradient problem, and capture dependencies, they are inherently sequential across time. In this work, we propose two novel approaches, a top-down and a bottom-up approach independently, which dispenses the recurrence entirely by incorporating the use of a Transformer, a network architecture for generating sequences relying entirely on the mechanism of attention. Adaptive positional encodings for the spatial locations in an image and a new regularization cost during training is introduced. The ability of our model to focus on salient regions in the image automatically is demonstrated visually. Experimental evaluation of the proposed architecture on the MS-COCO dataset is performed to exhibit the superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SpoofNET: Resolving Facial Makeup based Spoofs 2018

SpoofNET: Resolving Facial Makeup based Spoofs

引用

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

作者： Avishek Bhattacharjee Samik Banerjee Sukhendu Das Indian Institute of Technology Madras Chennai Tamil Nadu India

ISBN: (纸本)9781450366151

Face Recognition (FR) under adversarial conditions has been a big challenge for researchers in the computer vision and Machine Learning communities in the recent past. Most of state-of-the-art face recognition systems have been designed to overcome degradations in a face due to variations in pose, illumination, contrast, resolution, along with blur. However, interestingly none have addressed the fascinating issue of makeup as a spoof attack, which drastically changes the appearance of a face, making it difficult for even humans to detect and identify the impostor. In this paper, we propose a novel multi-component deep convolutional neural network (CNN) based architecture which performs the complex task of makeup removal from a disguised face, to reveal the original mugshot image of the impostor (i.e. without makeup). The proposed network also performs the hard tasks of FR on a disguised face in addition to recognition of identity and generation of the face of the spoofed target, by minimizing a novel multi-component objective function. Comparison of performance with a few recent state-of-the-art methods of FR over three benchmark datasets reveals the superiority of our proposed method for both synthesis as well as recognition (FR) tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cluster Loss for Person Re-Identification 18

Cluster Loss for Person Re-Identification

引用

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

作者： Doney Alex Zishan Sami Sumandeep Banerjee Subrat Panda Capillary Technologies Indian Institute of Technology Kharagpur

ISBN: (纸本)9781450366151

Person re-identification (ReID) is an important problem in computer vision, especially for video surveillance applications. The problem focuses on identifying people across different cameras or across different frames of same camera. The main challenge lies in identifying similarity of the same person against large appearance and structure variations, while differentiating between individuals. Recently, deep learning networks with triplet loss has become a common framework for person ReID. However, triplet loss focuses on obtaining correct orders on the training set. We demonstrate that it performs inferior in a clustering task. In this paper, we design a cluster loss, which can lead to the model output with a larger inter-class variation and a smaller intra-class variation compared to the triplet loss. As a result, our model has a better generalisation ability and can achieve a higher accuracy on the test set especially for a clustering task. We also introduce a batch hard training mechanism for improving the results and faster convergence of training.

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150页 << < 32 33 34 35 36 37 38 39 40 41 > >>

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：