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

57 篇 会议
1 册 图书

馆藏范围

58 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

50 篇 工学
- 35 篇 计算机科学与技术...
- 33 篇 软件工程
- 16 篇 光学工程
- 12 篇 信息与通信工程
- 12 篇 生物工程
- 8 篇 电气工程
- 6 篇 化学工程与技术
- 6 篇 生物医学工程（可授...
- 3 篇 电子科学与技术（可...
- 2 篇 土木工程
- 1 篇 机械工程
- 1 篇 材料科学与工程（可...
- 1 篇 建筑学
- 1 篇 农业工程
- 1 篇 林业工程
- 1 篇 城乡规划学
- 1 篇 安全科学与工程
36 篇 理学
- 17 篇 物理学
- 13 篇 数学
- 13 篇 生物学
- 6 篇 化学
- 3 篇 系统科学
- 2 篇 统计学（可授理学、...
15 篇 管理学
- 11 篇 图书情报与档案管...
- 3 篇 管理科学与工程(可...
- 2 篇 工商管理
9 篇 医学
- 9 篇 临床医学
- 4 篇 基础医学(可授医学...
- 3 篇 药学(可授医学、理...
1 篇 经济学
- 1 篇 应用经济学
1 篇 农学

主题

4 篇 generative adver...
3 篇 deep learning
3 篇 image reconstruc...
2 篇 object detection
2 篇 magnetic resonan...
2 篇 large dataset
2 篇 cameras
2 篇 computer vision
1 篇 image enhancemen...
1 篇 covid-19
1 篇 superpixels
1 篇 mot
1 篇 learning systems
1 篇 transformer
1 篇 semantic segment...
1 篇 gabor filters
1 篇 vitrual vehicle ...
1 篇 urban growth
1 篇 graphics process...
1 篇 speech

机构

3 篇 indian institute...
2 篇 iiit hyderabad
2 篇 department of co...
2 篇 indian institute...
2 篇 indian institute...
1 篇 iit kharagpur
1 篇 cvit iiit hydera...
1 篇 thiagarajar coll...
1 篇 vit-ap universit...
1 篇 indian statistic...
1 篇 university of co...
1 篇 philips bengulur...
1 篇 techno india uni...
1 篇 indian institute...
1 篇 jawaharlal nehru...
1 篇 rajiv gandhi ins...
1 篇 indian institute...
1 篇 indian institute...
1 篇 ocean univ china...
1 篇 government engin...

作者

4 篇 mukherjee jayant...
3 篇 nandedkar amit v...
3 篇 sreeni k.g.
3 篇 sural shamik
2 篇 bhattacharya sau...
2 篇 ji shiva
2 篇 biswas soma
2 篇 kumar jyoti
2 篇 mukhopadhyay jay...
2 篇 vorugunti chandr...
2 篇 biswas prabir ku...
2 篇 chaudhuri subhas...
2 篇 raman shanmugana...
1 篇 chakraborty shil...
1 篇 jha ritika
1 篇 das sukhendu
1 篇 jeena r.s.
1 篇 jain aryamaan
1 篇 gautam avinash
1 篇 banerjee biplab

语言

58 篇 英文

检索条件"任意字段=12th Indian Conference on Computer Vision, Graphics, and Image Processing, ICVGIP 2021"

共 58 条记录，以下是21-30 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：

A novel unsupervised thresholding technique for landsat image change detection 21

A novel unsupervised thresholding technique for landsat imag...

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Gupta, Neha Ari, Samit Mishra, Anoop Kumar VIT-AP University Andhra Pradesh Amaravati India National Institute of Technology Odisha Rourkela India

ISBN: (纸本)9781450391276

thresholding is the most widely used change detection technique for identifying the changes in remote sensing images. However, most of the thresholding methods would generate isolated spots in the final change map, which are reduced by applying postprocessing step. this paper proposes a novel thresholding technique to address the aforesaid problem without applying the postprocessisng operation. the proposed technique uses two thresholds simultaneously to generate the change map, which is the key point of this method. Above-stated thresholds are calculated by initial indicators that are generated by local neighborhood mutual information. In addition, this approach compares the local statistics of the interested pixel with the derived thresholds instead of the pixel itself, which enhances the robustness of this technique. Particularly, the method resides on three things: generation of initial indicators, use of two thresholds simultaneously, and comparison of local statistics with thresholds. Finally, the method is tested on multitemporal multispectral images of different sensors, and experimental results validate the effectiveness of the proposed method. © 2021 ACM.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

MATIC: Memory-Guided Adaptive Transformer for image Captioning 12th

MATIC: Memory-Guided Adaptive Transformer for Image Captioni...

引用

12th indian conference on computer vision, graphics, and image processing, icvgip 2021

作者： Gajhiye, Gaurav O. Nandedkar, Abhijeet V. Nanded India

ISBN: (纸本)9789811941351

Transforming the visual knowledge into linguistic description is a demanding and essential task known as image captioning, which necessitates a vision-language-based system to co-relate the multi-modal information. Transformer architecture has recently become cutting-edge in addressing the image captioning-related problems. In this paper, the utility of the transformer is explored by bridging single layer memory-guided encoder and multi-layer adaptive attention decoder framework entitled as Memory-guided Adaptive Transformer for image Captioning. the memory-based encoder is used to capture the relative spatial information from CNN-based visual features and transfer it to the decoder, which then learns the inter-modality affinity between visual and linguistic features. the decoder with multi-headed adaptive attention reconciles the visual and linguistic information to describe the visual contents in a comprehensible way by balancing visual and semantic patterns through adaptive gate channeling. the performance of the proposed method is evaluated on widely used captioning datasets viz. Flickr8k and Flickr30k. the proposed method performs remarkable and earns a superior caption generation score on both datasets as compared to state-of-the-art. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Estimation of the area of mouth opening during speech production 12

Estimation of the area of mouth opening during speech produc...

引用

8th indian conference on computer vision, graphics and image processing, icvgip 2012

作者： Saha, Sudipan Pandey, Prem C. Department of Electrical Engineering Indian Institute of Technology Bombay Mumbai-400076 Maharashtra India

ISBN: (纸本)9781450316606

Estimation of the area of mouth opening from a video of the speaker's face and processing of the simultaneously recorded speech signal can be used for estimation of vocal tract shape during speech production. A technique is presented to estimate the area of mouth opening, using a processing based on contrast enhancement with multi-threshold binarization and connected component detection for reducing the errors in estimating the vertical opening due to the presence of teeth and tongue in mouth opening. the method is tested on vowel utterances from 12 speakers. © 2012 ACM.

关键词： Speech

来源：评论

学校读者我要写书评

暂无评论

Enhancing label transfer in non-parametric scene parsing by superpixel-based dense alignment 21

Enhancing label transfer in non-parametric scene parsing by ...

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Bhowmick, Alexy Saharia, Sarat Hazarika, Shyamanta M. Dept. of Computer Science and Engineering Assam Don Bosco University Assam Guwahati781017 India Dept. of Computer Science and Engineering Tezpur University Assam Tezpur784028 India Biomimetic Robotics and Artificial Intelligence Lab Dept. of Mechanical Engineering IIT Guwahati Assam Guwahati781039 India

ISBN: (纸本)9781450391276

Contemporary (parametric) scene parsing methods are learning-based and mostly operate in a closed-universe scenario. We introduce a non-parametric scene parsing framework that is model-free, data-driven, and scales naturally to growing data. the scene parsing performance in the non-parametric approach depends on reliable dense correspondence or alignment across scenes for label transfer. Incorrect correspondence is known to affect the scene parsing results adversely. We propose a label transfer approach that relies on the dense correspondence of super-pixel pairs (in a query and candidate image) matched by a homogeneous kernel map to guide semantic label transfer. the aggregation (fusing) of multiple labels is done through a simple heuristic aggregation scheme (simple majority voting). the Markov Random Field (MRF) provides a principled probabilistic framework for combining the disparate information in the smoothing stage and ensures plausible labeling results. Evaluation results show that our non-parametric system obtains competitive scene parsing performance on the standard SIFT Flow and MSRC-21 datasets. © 2021 ACM.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Deformable deep networks for instance segmentation of overlapping multi page handwritten documents 21

Deformable deep networks for instance segmentation of overla...

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Aitha, Sowmya Bollampalli, Sindhu Sarvadevabhatla, Ravi Kiran CVIT IIIT Hyderabad Hyderabad500032 India

ISBN: (纸本)9781450391276

Digitizing via scanning the physical artifact often forms the first primary step in preserving historical handwritten manuscripts. To maximally utilize scanner surface area and minimize manual labor, multiple manuscripts are usually scanned together into a scanned image. therefore, the first crucial task in manuscript content understanding is to ensure that each of the individual manuscripts within a scanned image can be isolated (segmented) on a per-instance basis. Existing deep network based approaches for manuscript layout understanding implicitly assume a single or two manuscripts per image. Since this assumption may be routinely violated, there is a need for a precursor system which extracts individual manuscripts before downstream processing. Another challenge is the highly curved and deformed boundaries of manuscripts, causing them to often overlap with each other. To tackle such challenges, we introduce a new document image dataset called IMMI (Indic Multi Manuscript images). To improve the efficiency of dataset and aid deep network training, we also propose an approach which generates synthetic images to augment sourced non-synthetic images. We conduct experiments using modified versions of existing document instance segmentation frameworks. the results demonstrate the efficacy of the new frameworks for the task. Overall, our contributions enable robust extraction of individual historical manuscript pages. this in turn, could potentially enable better performance on downstream tasks such as region-level instance segmentation within handwritten manuscripts and optical character recognition. © 2021 ACM.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

G3AN++: Exploring wide GANs with complementary feature learning for video generation 21

G3AN++: Exploring wide GANs with complementary feature learn...

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Gupta, Sonam Keshari, Arti Das, Sukhendu Indian Institute of Technology Madras Tamil Nadu Chennai India

ISBN: (纸本)9781450391276

Video generation task is a challenging problem which involves the modelling of complex real-world dynamics. Most of the existing methods have designed deep networks to tackle high-dimensional video data distributions. However, the utilization of wide networks is still under explored. Inspired by the success of wide networks in the image recognition literature, we present G3AN++, a three-stream generative adversarial network for video. the three streams are spatial, temporal and spatio-temporal processing branches. In pursuit of improving the quality of video generation, we make our network wider by splitting the spatial stream into two parallel identical branches learning complementary feature representations. We further introduce a novel adaptive masking layer to impose the complementary constraint. the masking layer encourages the parallel branches to learn distinct and richer visual features. Extensive quantitative and qualitative analysis demonstrates that our model outperforms the existing state-of-the-art methods by a significant margin on Weizmann Action, UvA-Nemo Smile and UCF101 Action datasets. Additional exploration reveals that G3AN++ is capable of disentangling the appearance and motion. We also show that the proposed method can be easily extended to solve the hard task of text-to-video generation. © 2021 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

How empathizing with persona helps in design thinking: An experimental study with novice designers 12

How empathizing with persona helps in design thinking: An ex...

引用

12th International conference on Interfaces and Human computer Interaction 2018, 11th International conference on Game and Entertainment Technologies 2018 and 12th International conference on computer graphics, Visualization, computer vision and image processing 2018, part of the Multi conference on computer Science and Information Systems 2018, MCCSIS 2018

作者： Dahiya, Abhishek Kumar, Jyoti Indian Institute of Technology Delhi New Delhi India

ISBN: (纸本)9789898533791

Personas are widely used by HCI designers in design process. From defining target users to explicating user understanding, persona assists designers at various stages of design process of HCI systems. Design literature advocates the use of persona not only as a source of information about users but also as a tool to empathize. this paper reports observations from an experimental study done on novice designers on how empathizing with persona affected their design solutions. A total of 30 novice designers participated in this study. Participants were asked to design a graphical composition for persona. the data collected was analyzed through expert’s rating on design solutions on the basis of directness of illustration of persona information and verbal protocols. On the basis of direct illustration of persona information on design solutions it was observed that empathizing with persona helped designers to iterate more on design thinking. © 2018.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

HazeNet: Does the image have haze? 21

HazeNet: Does the image have haze?

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Kalaivani, P. Rooomi, S. Mohamed Mansoor Nathan, D. Sabari Government College of Engineering Bodinayakanur Theni Tamilnadu India Thiagarajar College of Engineering Tamilnadu Madurai India Couger Inc Tokyo Japan

ISBN: (纸本)9781450391276

the visibility of scene is much important in applications of Intelligent Video surveillance systems, Autonomous Vehicle Navigation. the presence of haze limits the visibility, thereby hindering the proper operation of computer vision algorithms. there are lot of algorithms to remove haze unconditionally. But the haze removal on clear images or frames will cause adverse effects. Unnecessary dehazing results in the loss of original information and also delays the following process. To address these challenges, there is a need to recognize the image as hazy and haze-free before applying dehazing on it. Hence, this paper presents three light-weight deep neural network models to automatically classify image as hazy and haze-free in the name of HazeNet, R-HazeNet and RSE-HazeNet. the HazeNet is Convolutional Neural Network having five convolutional blocks and results in classification accuracy of 97.89%. In order to improve the performance of HazeNet further, the Residual blocks have been included after each convolutional layer. the model is called R-HazeNet. the residual blocks help in producing hierarchical features. To strengthen the useful convolutional channel features alone, Squeeze and Excitation blocks have been included with Residual units in RSE-HazeNet model. Both R-HazeNet and RSE-HazeNet produced classification accuracy of 99.98% which demonstrate superior performance compared to the stat-of-the-art methods. the proposed models are light-weight models due to the percentage improvement in number of parameters as a minimum of 93% has been achieved with respect to the the baseline method. © 2021 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Disparity based depth estimation using light field camera 21

Disparity based depth estimation using light field camera

引用

12th indian conference on computer vision, graphics and image processing, icvgip 2021

作者： Nehra, Suresh Das, Tamal Chakraborty, Simantini Biswas, P.K. Mukhopadhyay, J. Indian Institute of Technology Kharagpur India National Institute of Technology Agartala India

ISBN: (纸本)9781450391276

Light field cameras have a unique feature of capturing the direction of light rays along with its intensity. this additional information is used to estimate the depth of a 3-D scene. Recently a considerable amount of research has been done in depth estimation using light field data. However, these depth estimation methods heavily rely on iterative optimization techniques and do not fully exploit the inherent structured light field data. In this paper, we present a novel three-step disparity based algorithm to estimate accurate depth maps of a light field image. First, an initial depth map of scene points is estimated using principal views by estimating the disparity of segments in the central image. this initial depth helps in resolving ambiguity in depth propagation of refined depth map in Epi-Polar line images (EPIs). Second, refined depth is estimated at lines using the disparity vector in EPIs. Finally, refined depth at lines in EPIs is propagated to other locations using the initial depth map. We also provided a synthetic data-set having inherent characteristic of a light field. We have tested our approach on a variety of real-world scenes captured with Lytro Illum camera and also on synthetic images. the proposed method outperforms several state-of-the-art algorithms. © 2021 ACM.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An experimental study to evaluate influence of usability on learning behaviour 12

An experimental study to evaluate influence of usability on ...

引用

作者： Kumar, Jyotish Khare, Aarati Prakash Kumar, Jyoti Indian Institute of technology Delhi New Delhi India

ISBN: (纸本)9789898533791

Usability has been one of the well-established quality measures of HCI systems. Designing an efficient e-learning system is a complex process and requires usability testing at various stages. Unlike conventional HCI systems, e-learning system is not only designed to interact with users but also to facilitate learning to user. In order to develop learner centric system design, there is a need to find the ways in which learning and usability interact. In this study, six learning behaviour markers were identified which can be integrated with conventional usability testing. this paper investigates a relationship between usability attributes and learning behaviour through usability testing of two different e-learning websites with similar in content but different in usability. Other than usability attributes and learning behaviour markers, Galvanic skin response (GSR) of users was also recorded and compared to support the usability testing results. Significant difference (p © 2018.

关键词： Websites

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6页 << < 1 2 3 4 5 6 > >>

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：