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

140 篇 会议
3 篇 期刊文献

馆藏范围

143 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

134 篇 工学
- 128 篇 计算机科学与技术...
- 101 篇 电气工程
- 30 篇 软件工程
- 12 篇 信息与通信工程
- 12 篇 生物工程
- 9 篇 光学工程
- 8 篇 生物医学工程（可授...
- 4 篇 电子科学与技术（可...
- 4 篇 控制科学与工程
- 3 篇 化学工程与技术
- 1 篇 力学（可授工学、理...
- 1 篇 机械工程
- 1 篇 仪器科学与技术
- 1 篇 轻工技术与工程
- 1 篇 安全科学与工程
27 篇 理学
- 14 篇 物理学
- 12 篇 生物学
- 10 篇 数学
- 3 篇 化学
- 3 篇 统计学（可授理学、...
- 1 篇 地质学
- 1 篇 系统科学
9 篇 医学
- 9 篇 临床医学
- 4 篇 基础医学(可授医学...
- 4 篇 药学(可授医学、理...
7 篇 管理学
- 7 篇 图书情报与档案管...
2 篇 法学
- 1 篇 法学
- 1 篇 社会学

主题

10 篇 deep learning
3 篇 segmentation
3 篇 object detection
3 篇 compressed sensi...
3 篇 magnetic resonan...
3 篇 image inpainting
3 篇 image reconstruc...
3 篇 convolutional ne...
2 篇 image fusion
2 篇 facial expressio...
2 篇 sketch-based
2 篇 deep neural netw...
2 篇 optical flow
2 篇 image segmentati...
2 篇 local binary pat...
2 篇 face recognition
2 篇 image forensics
2 篇 dehazing
2 篇 tracking
2 篇 image retrieval

机构

4 篇 indian inst tech...
3 篇 indian inst tech...
3 篇 department of co...
3 篇 indian inst tech...
3 篇 indian inst sci ...
2 篇 natl inst ocean ...
2 篇 indian stat inst...
2 篇 iiit chittoor sr...
2 篇 indian statistic...
2 篇 indian institute...
2 篇 ocean univ china...
2 篇 indian space res...
2 篇 indian stat inst...
2 篇 iit madras madra...
2 篇 indian inst spac...
2 篇 indian inst tech...
2 篇 univ calif irvin...
2 篇 indian stat inst...
2 篇 indian inst sci ...
2 篇 indian inst sci ...

作者

7 篇 mukherjee jayant...
6 篇 chaudhury santan...
6 篇 sheet debdoot
5 篇 mishra deepak
4 篇 mukherjee dipti ...
4 篇 babu r. venkates...
4 篇 chanda bhabatosh
4 篇 krishna k. madha...
4 篇 mukherjee snehas...
4 篇 chaudhuri subhas...
3 篇 nandedkar amit v...
3 篇 biswas soma
3 篇 sural shamik
3 篇 maity santi p.
3 篇 harit gaurav
3 篇 gupta anubha
3 篇 raman shanmugana...
2 篇 subrahmanyam g. ...
2 篇 das sukhendu
2 篇 narayanan p. j.

语言

143 篇 英文

检索条件"任意字段=10th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2016"

共 143 条记录，以下是131-140 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：

Knowledge Distillation with Ensemble Calibration 14

Knowledge Distillation with Ensemble Calibration

引用

14th indian conference on computer vision, graphics and image processing, icvgip 2023

作者： Mishra, Ishan Jain, Riyanshu Viradiya, Dhruv Patel, Divyam Mishra, Deepak Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798400716256

Knowledge Distillation is a transfer learning and compression technique that aims to transfer hidden knowledge from a teacher model to a student model. However, this transfer often leads to poor calibration in the student model. this can be problematic for high-risk applications that require well-calibrated models to capture prediction uncertainty. To address this issue, we propose a simple and novel technique that enhances the calibration of the student network by using an ensemble of well-calibrated teacher models. We train multiple teacher models using various data-augmentation techniques such as cutout, mixup, CutMix, and AugMix and use their ensemble for knowledge distillation. We evaluate our approach on different teacher-student combinations using CIFAR-10 and CIFAR-100 datasets. Our results demonstrate that our technique improves calibration metrics (such as expected calibration and overconfidence errors) while also increasing the accuracy of the student network. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Distillation

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 13

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

引用

13th indian conference on computer vision, graphics, and image processing, icvgip 2022

作者： Grover, Chanda Mastan, Indra Deep Gupta, Debayan Ashoka University Sonipat Haryana India Rajasthan Jaipur India

ISBN: (纸本)9781450398237

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. © 2022 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

AECNN: Autoencoder with Convolutional Neural Network for Hyperspectral image Classification 1

引用

3rd Workshop on computer vision Applications, WCVA 2018, held in conjunction with the 11th indian conference on computer vision, graphics and image processing, icvgip 2018

作者： Patel, Heena Upla, Kishor P. Sardar Vallabhbhai National Institute of Technology SuratGujarat India

ISBN: (数字)9789811513879

ISBN: (纸本)9789811513862

this paper addresses an approach for classification of hyperspectral imagery (HSI). In remote sensing, the HSI sensor acquires hundreds of images with very narrow but continuous spectral width in visible and near-infrared regions of the electromagnetic (EM) spectrum. Due to the nature of data acquisition with contiguous bands, the HS images are very useful in classification and/or the identification of materials present in the captured geographical area. However, the low spatial resolution and large volume of HS images make the classification of those images as a challenging task. In the proposed approach, we use an autoencoder with convolutional neural network (AECNN) for classification of HS image. Pre-processing procedure with autoencoder leads to obtain optimized weights in the initial layer of CNN model. Moreover, features are enhanced in the HS images by utilizing the autoencoder. the CNN is used for efficient extraction of the features and same is also utilised for the classification of HS data. the potential of the proposed approach has been verified by conducting the experiments on three recent datasets. the experimental results are compared with the results obtained in the geoscience and remote sensing society (GRSS) image Fusion Contest-2018 held at IEEE International Geoscience and Remote Sensing Symposium (IGARSS)-2018 and other existing frameworks for HSI classification. the testing accuracy of classification for the proposed approach is better than that of the other existing deep learning based methods. © Springer Nature Singapore Pte Ltd, 2019.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Towards Realistic Underwater Dataset Generation and Color Restorationg± 13

Towards Realistic Underwater Dataset Generation and Color Re...

引用

13th indian conference on computer vision, graphics, and image processing, icvgip 2022

作者： Jain, Neham Matta, Gopi Raju Mitra, Kaushik IIT Madras Tamil Nadu Chennai India

ISBN: (纸本)9781450398237

Recovery of true color from underwater images is an ill-posed problem. this is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is backscattering due to suspended particles in water. thus, most existing deep-learning based color restoration methods, which are trained on synthetic underwater datasets, do not perform well on real underwater data. this can be attributed to the fact that synthetic data cannot accurately represent real conditions. To address this issue, we use an image to image translation network to bridge the gap between the synthetic and real domains by translating images from synthetic underwater domain to real underwater domain. Using this multimodal domain adaptation technique, we create a dataset that can capture a diverse array of underwater conditions. We then train a simple but effective CNN based network on our domain adapted dataset to perform color restoration. Code and pre-trained models can be accessed at https://***/nehamjain10/TRUDGCR © 2022 ACM.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

IDENTIFICATION OF GROUND GLASS STRUCTURE IN LUNG CT imageS BY computer AIDED DIAGNOSIS TECHNIQUE 10

IDENTIFICATION OF GROUND GLASS STRUCTURE IN LUNG CT IMAGES B...

引用

10th International conference on Intelligent Systems and Control (ISCO)

作者： Arabi, Punal. M. Vamsha, Deepa. N. Krishna, Nanditha Prathibha, T. P. ACSCE Dept Biomed Engn Bangalore Karnataka India

ISBN: (纸本)9781467378079

Lung diseases are the leading cause of death. Main factors that cause lung diseases are inhaling dusts, chemicals, or bacteria and molds at work. 70275 indian people were affected by lung disease among them 63759 people died. CAD system assists the doctors for the diagnosis of diseases in higher degree of perfection within a short period of time. High-resolution Computed Tomography (HRCT) is the preferred method for diagnosing a number of lung diseases. Ground glass structures are characterized by a slight increase in lung density, with persistent visibility of vascular structures and bronchial walls are imaged as abnormal lungs. Ground glass structure is a marker for pulmonary edema, desquamative pneumonitis, hypersensitive pneumonitis, pneumocystis carinii pneumonia. image processing techniques play a significant role in the diagnosis of lung disease. this paper presents a novel image processing method to identify the ground glass structure in lung CT images using mean intensity pattern identification. the results obtained show the feasibility of the proposed method to diagnose the ground glass structure of lung CT image.

关键词： Identifications computer vision Ground glass structures CT images lung

来源：评论

学校读者我要写书评

暂无评论

Proceedings of icvgip 2022thirteenth indian conference on computervision, graphics, and image processingDecember 8-10, 2022

ACM International Conference Proceeding Series

引用

ACM International conference Proceeding Series 2022年

作者： Biswas, Soma Raman, Shanmuganathan Roy-Chowdhury, Amit K

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Architecture Based Dimensionality Reduction and Online Signature Verification 4th

A Deep Learning Architecture Based Dimensionality Reduction ...

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

作者： Vorugunti, Chandra Sekhar Pulabaigari, Viswanath Indian Institute of Information Technology-SriCity Chittoor India

ISBN: (纸本)9789811393600

In this paper, we propose a novel hybrid deep learning based autoencoder-CNN-Softmax architecture aims at obtaining reduced dimension feature set from raw feature set. the reduced feature set forms an input to CNN layers to learn deep global features. these global features are used to train the SoftMax layer for online signature classification. Ability to reduce the noisy features and to discover the hidden corelated features makes the proposed architecture light weight and efficient to use in critical applications like online signature verification (OSV) and to deploy in resource constraint mobile devices. We demonstrate the superiority of our model for feature correlation learning and signature classification by conducting experiments on standard datasets MCYT, SUSIG. the experimentation confirms that the proposed model achieves better accuracy (lower error rates) with a lesser number of features compared to the current state-of-the-art models. the proposed models yield state-of-the-art performance of 0.4% EER on MCYT-100 dataset and 3.47% with SUSIG dataset. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Shrimps Classification Based on Multi-layer Feature Fusion 10

Shrimps Classification Based on Multi-layer Feature Fusion

引用

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

作者： Zhang, Xiaoxue Wei, Zhiqiang Huang, Lei Ji, Xiaopeng Ocean Univ China Qingdao 266000 Shandong Peoples R China

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

this paper aims to highlight vision related tasks centered on "shrimps". With the further study of computer vision of marine life, we show that "shrimps" has been largely neglected in comparison to other objects. In image classification, the degree of visual separation between different shrimp categories is highly uneven, the appearance of some categories in same genus is very similar, and it is more difficult to distinguish than others. Based on the classification model of traditional convolutional neural network, this paper presents a method of merging shallow and deep features extracting feature maps from different levels according to the characteristics of shrimp. In order to facilitate future shrimps-related research, we present our on-going effort in collecting a dataset in this paper, "ShrimpX", that covers not only shrimps and lobsters living in the sea, but also some freshwater shrimps. the "ShrimpX" dataset contains a variety of shrimp images crawled from image search engines. Experimental results on the "ShrimpX" dataset demonstrate that the proposed method can effectively improve the accuracy.

关键词： Convolutional Neural Network (CNN) image classification deep feature shallow feature multi-layer feature fusion

来源：评论

学校读者我要写书评

暂无评论

Coin Classification in a Complex Environment 10

Coin Classification in a Complex Environment

引用

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

作者： Chang, Huanhuan Wei, Zhiqiang Huang, Lei Nie, Jie Zhang, Wenfeng Wang, Lu Ocean Univ China Qingdao 266000 Shandong Peoples R China

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

Coin classification automatically plays important roles in many applications, e.g., vending systems. Glossy reflection is one of the key factor that affect the performance of vision-based coin classification, especially in a complex environment. In this paper, we propose a novel method for robust coin classification. Contrary to the previous method, we get the glossy area first. Edge features and texture features are used in glossy area detection. then the deep learning features are extracted based on non-glossy area instead of the whole coin image. Finally, the coin classification results are got from the VGG nets scheme. Comprehensive experiments show that our method is robust under various complex environments. the comparison experiments demonstrate that our method can outperform the state-of-the-art method. Our method achieves 95.80% accuracy.

关键词： coin classification deep learning mirror reflection computer vision glossy area

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

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15页 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：