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

118 篇 会议
1 册 图书
1 篇 期刊文献

馆藏范围

120 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

47 篇 工学
- 35 篇 计算机科学与技术...
- 21 篇 控制科学与工程
- 8 篇 机械工程
- 8 篇 软件工程
- 5 篇 电气工程
- 3 篇 仪器科学与技术
- 3 篇 电子科学与技术（可...
- 2 篇 力学（可授工学、理...
- 2 篇 光学工程
- 1 篇 信息与通信工程
9 篇 理学
- 6 篇 数学
- 6 篇 物理学
- 2 篇 统计学（可授理学、...
1 篇 医学
- 1 篇 临床医学

主题

97 篇 visualization
28 篇 computer vision
20 篇 cameras
19 篇 feature extracti...
18 篇 machine vision
16 篇 machine learning
16 篇 training
14 篇 computational mo...
13 篇 robot vision sys...
11 篇 three-dimensiona...
10 篇 robustness
9 篇 robots
9 篇 shape
8 篇 image recognitio...
7 篇 task analysis
7 篇 data visualizati...
6 篇 computer archite...
6 篇 robot sensing sy...
6 篇 estimation
6 篇 streaming media

机构

2 篇 munich center fo...
2 篇 eidgenossische t...
2 篇 lmu munich
2 篇 universitat de b...
2 篇 siemens ag
1 篇 technical univer...
1 篇 luddy school of ...
1 篇 university of te...
1 篇 united states mi...
1 篇 school of inform...
1 篇 florida institut...
1 篇 university of ar...
1 篇 west chester uni...
1 篇 chalearn berkele...
1 篇 department of el...
1 篇 calif state univ...
1 篇 lund university ...
1 篇 university of ox...
1 篇 rutgers universi...
1 篇 univ minnesota m...

作者

2 篇 volker tresp
2 篇 jindong gu
2 篇 luc van gool
2 篇 dengxin dai
1 篇 protzel peter
1 篇 escalera sergio
1 篇 guyon isabelle
1 篇 a. biancardi
1 篇 aneta lisowska
1 篇 simon åberg
1 篇 janani ramaswamy
1 篇 pillai sudeep
1 篇 zlatinsi athanas...
1 篇 matveyev s.v.
1 篇 zoe betta
1 篇 boon-lock yeo
1 篇 cristian rodrigu...
1 篇 i. pappas
1 篇 geiger b
1 篇 narayan srinivas...

语言

119 篇 英文
1 篇 其他

检索条件"任意字段=IEEE Workshop on Visualization and Machine Vision"

共 120 条记录，以下是41-50 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：

Explaining Visual Models by Causal Attribution

Explaining Visual Models by Causal Attribution

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Álvaro Parafita Jordi Vitrià Universitat de Barcelona Spain

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.

关键词： Computational modeling Generators Data models machine learning Face Rain visualization

来源：评论

学校读者我要写书评

暂无评论

Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation

Explaining Convolutional Neural Networks using Softmax Gradi...

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Brian Kenji Iwana Ryohei Kuroki Seiichi Uchida Kyushu University Fukuoka Japan

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relevance of the output probability to the input image. Through qualitative and quantitative analysis, we demonstrate that SGLRP can successfully localize and attribute the regions on input images which contribute to a target object's classification. We show that the proposed method excels at discriminating the target objects class from the other possible objects in the images. We confirm that SGLRP performs better than existing Layer-wise Relevance Propagation (LRP) based methods and can help in the understanding of the decision process of CNNs.

关键词： visualization Heating systems Convolutional neural networks machine learning Robustness Computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploring CNN-based architectures for Multimodal Salient Event Detection in Videos 13

Exploring CNN-based architectures for Multimodal Salient Eve...

引用

13th ieee Image, Video, and Multidimensional Signal Processing workshop (IVMSP)

作者： Koutras, Petros Zlatinsi, Athanasia Maragos, Petros Natl Tech Univ Athens Sch ECE GR-15773 Athens Greece

ISBN: (纸本)9781538609514

Nowadays, multimodal attention plays a significant role in many machine-based understanding applications, computer vision and robotic applications, such as action recognition or summarization. In this paper, we present our approach to the problem of audio-visual salient event detection based on visual and audio modalities by employing modern Convolutional Neural Network (CNN) based architectures. In this way, we extend our previous work, where a hand-crafted frontend was examined, an energy based synergistic approach, where a non-parametric classification technique was used for the classification of salient vs. non-salient events. Our comparative evaluations over the COGNIMUSE database [1], consisting of movies and travel documentaries, as well as ground-truth data denoting the perceptually mono- and multimodal salient events, provided strong evidence that the CNN-based approach for all modalities (i.e., audio, visual and audiovisual), even in this task, manages to outperform the hand-crafted frontend in almost all cases, accomplishing really good average results.

关键词： Videos visualization Computer architecture Three-dimensional displays Event detection Motion pictures Kernel"

来源：评论

学校读者我要写书评

暂无评论

A Tale of Two Modalities for Video Captioning

A Tale of Two Modalities for Video Captioning

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Pankaj Joshi Chitwan Saharia Vishwajeet Singh Digvijaysingh Gautam Ganesh Ramakrishnan Preethi Jyothi Department of CSE Indian Institute of Technology Bombay

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Recent advances in machine learning have led to significant accuracy improvements for the task of generating textual captions from videos based on audio and visual signals. In this work, we focus on the influence of modality (audio and visual input) on semantic coherence and well-formedness of the generated captions. We explore both architectural and algorithmic choices that potentially influence the utilization of these modalities. (Algorithmic choices include pretraining while architectural choices include modality-specific weighing schemes.) We study the influence of our choices on a popular video captioning dataset, MSRVTT, by providing quantitative and ex-tensive qualitative evaluations that measure the influence of audio-visual modalities, cohesiveness and ranked relevance of keywords. We are able to assert qualitative improvements on metrics characterizing the quality of the captions, along with obtaining performance that is comparable to state-of-the-art on standard quantitative metrics such as BLEU-4, METEOR, etc.

关键词： Measurement Decoding Training Task analysis visualization Standards Streaming media

来源：评论

学校读者我要写书评

暂无评论

SalGaze: Personalizing Gaze Estimation using Visual Saliency

SalGaze: Personalizing Gaze Estimation using Visual Saliency

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Zhuoqing Chang J. Matias Di Martino Qiang Qiu Steven Espinosa Guillermo Sapiro Duke University Durham NC USA

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy. This process is cumbersome and recalibration is often required when there are changes in factors such as illumination and pose. To address this challenge, we introduce SalGaze, a framework that utilizes saliency information in the visual content to transparently adapt the gaze estimation algorithm to the user without explicit user calibration. We design an algorithm to transform a saliency map into a differentiable loss map that can be used for the optimization of CNN-based models. SalGaze is also able to greatly augment standard point calibration data with implicit video saliency calibration data using a unified framework. We show accuracy improvements over 24% using our technique on existing methods.

关键词： Estimation Calibration visualization machine learning Head Computational modeling Lighting

来源：评论

学校读者我要写书评

暂无评论

A Visual Memory System for Humanoid Robots 15

A Visual Memory System for Humanoid Robots

引用

15th Latin American Robotic Symposium (LARS) / 6th Brazilian Symposium on Robotics (SBR) / 9th workshop on Robotics in Education (WRE)

作者： Ferreira, Vinicius N. Neto, Sylvio R. J. Almeida, Aislan C. Bianchi, Reinaldo A. C. Ctr Univ Fundacao Educ Inaciana Pe Saboia Medeiro Sao Bernardo Do Campo Brazil

ISBN: (纸本)9781538677612

Competitions like RoboCup, require a robot that is capable of playing soccer competitively. Therefore the robot must have functional control, vision, localization and decision systems. This project proposes the implementation of an object tracking system, using the vision system of a robot in the domain of RoboCup KidSize Soccer. The proposed system detects multiple objects like: robots, landmarks and the ball;transmit these informations to the tracking system and keep track of their positions, even when the vision system loses the objects. It also considers the movement of the robot in order to predict the objects positions relative to the robot. Real humanoid robots were used in order to implement and test the proposal. Experiments showed that the system was able to track the position of a second moving robot in the field.

关键词： machine vision Computer architecture visualization Robot sensing systems Instruction sets Tracking

来源：评论

学校读者我要写书评

暂无评论

Free-Lunch Saliency via Attention in Atari Agents

Free-Lunch Saliency via Attention in Atari Agents

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Dmitry Nikulin Anastasia Ianina Vladimir Aliev Sergey Nikolenko Samsung AI Center Moscow Russia

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

We propose a new approach to visualize saliency maps for deep neural network models and apply it to deep reinforcement learning agents trained on Atari environments. Our method adds an attention module that we call FLS (Free Lunch Saliency) to the feature extractor from an established baseline of Mnih et al, 2015. This addition results in a trainable model that can produce saliency maps, i.e., visualizations of the importance of different parts of the input for the agent's current decision making. We show experimentally that a network with an FLS module exhibits performance similar to the baseline (i.e., it is “free”, with no performance cost) and can be used as a drop-in replacement for reinforcement learning agents. We also design another feature extractor that scores slightly lower but provides higher-fidelity visualizations. In addition to attained scores, we report saliency metrics evaluated on the Atari-HEAD dataset of human gameplay.

关键词： visualization Games Feature extraction Measurement Neural networks machine learning Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Hallucinating Agnostic Images to Generalize Across Domains

Hallucinating Agnostic Images to Generalize Across Domains

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Fabio Maria Carlucci Paolo Russo Tatiana Tommasi Barbara Caputo Huawei Noah's Ark Lab London UK University of Rome Sapienza Italy Politecnico di Torino Italy Italian Institute of Technology

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

The ability to generalize across visual domains is crucial for the robustness of artificial recognition systems. Although many training sources may be available in real contexts, the access to even unlabeled target samples cannot be taken for granted, which makes standard unsupervised domain adaptation methods inapplicable in the wild. In this work we investigate how to exploit multiple sources by hallucinating a deep visual domain composed of images, possibly unrealistic, able to maintain categorical knowledge while discarding specific source styles. The produced agnostic images are the result of a deep architecture that applies pixel adaptation on the original source data guided by two adversarial domain classifier branches at image and feature level. Our approach is conceived to learn only from source data, but it seamlessly extends to the use of unlabeled target samples. Remarkable results for both multi-source domain adaptation and domain generalization support the power of hallucinating agnostic images in this framework.

关键词： Feature extraction Training visualization Standards machine learning Image recognition Target recognition

来源：评论

学校读者我要写书评

暂无评论

Image Pattem Classification for Plant Disease Identification using Local Tri-directional Features

Image Pattem Classification for Plant Disease Identification...

引用

International Conference and workshop on Computing and Communication (IEMCON)

作者： Sumair Aziz Mudassar Bashir Ovais Mughal Muhammad Umar Khan Arsalan Khan Department of Electronics Engineering University of Engineering and Technology Taxila Pakistan Department of Electrical Engineering Sir Syed CASE Institute of Technology Islamabad Pakistan Department of Electrical Engineering International Islamic University Islamabad Pakistan

Plant diseases are main culprits of reduction in production in agronomy, which inflicts huge economic damages. Efficient detection and classification of plant diseases contributes significantly towards reducing these losses. This paper presents computer vision framework for plant disease identification and classification. The proposed system extracts Local Tri-directional Patterns (LTriDP) from plant leaf images of different classes. LTriDP features efficiently extracts discriminant information and represent each class with reduced dimensions. Classification is performed through multiclass support vector machines (SVM). Experiments are conducted on Tomato leaf dataset comprising five different classes. Experimental results show that the proposed framework out performs other methods based on commonly used feature descriptors and achieved 94% overall accuracy.

关键词： visualization Shape Support vector machine classification Feature extraction Systems support Data mining Diseases

来源：评论

学校读者我要写书评

暂无评论

U2Eyes: A Binocular Dataset for Eye Tracking and Gaze Estimation

U2Eyes: A Binocular Dataset for Eye Tracking and Gaze Estima...

引用

International Conference on Computer vision workshops (ICCV workshops)

作者： Sonia Porta Benoît Bossavit Rafael Cabeza Andoni Larumbe-Bergera Gonzalo Garde Arantxa Villanueva Public University of Navarre Pamplona Spain Trinity College Dublin Dublin Ireland

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Theory shows that huge amount of labelled data are needed in order to achieve reliable classification/regression methods when using deep/machine learning techniques. However, in the eye tracking field, manual annotation is not a feasible option due to the wide variability to be covered. Hence, techniques devoted to synthesizing images show up as an opportunity to provide vast amounts of annotated data. Considering that the well-known UnityEyes tool provides a framework to generate single eye images and taking into account that both eyes information can contribute to improve gaze estimation accuracy we present U2Eyes dataset, that is publicly available. It comprehends about 6 million of synthetic images containing binocular data. Furthermore, the physiology of the eye model employed is improved, simplified dynamics of binocular vision are incorporated and more detailed 2D and 3D labelled data are provided. Additionally, an example of application of the dataset is shown as work in progress. Employing U2Eyes as training framework Supervised Descent Method (SDM) is used for eyelids segmentation. The model obtained as result of the training process is then applied on real images from GI4E dataset showing promising results.

关键词： Estimation Gaze tracking visualization Face Cameras Eyelids

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12页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：