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11-20 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：

Towards Automatic Translation of machine Learning Visual Insights to Analytical Assertions

Towards Automatic Translation of Machine Learning Visual Ins...

引用

Natural Language-Based Software Engineering (NLBSE), ieee/ACM International workshop on

作者： Arumoy Shome Luìs Cruz Arie Van Deursen Delft University of Technology Netherlands

ISBN: (数字)9798400705762

ISBN: (纸本)9798350352559

We present our vision for developing an automated tool capable of translating visual properties observed in machine Learning (ML) visualisations into Python assertions. The tool aims to streamline the process of manually verifying these visualisations in the ML development cycle, which is critical as real-world data and assumptions often change post-deployment. In a prior study, we mined 54, 070 Jupyter notebooks from Github and created a catalogue of 269 semantically related visualisation-assertion (VA) pairs. Building on this catalogue, we propose to build a taxonomy that organises the VA pairs based on ML verification tasks. The input feature space comprises of a rich source of information mined from the Jupyter notebooks-visualisations, Python source code, and associated markdown text. The effectiveness of various AI models, including traditional NLP4Code models and modern Large Language Models, will be compared using established machine translation metrics and evaluated through a qualitative study with human participants. The paper also plans to address the challenge of extending the existing VA pair dataset with additional pairs from Kaggle and to compare the tool’s effectiveness with commercial generative AI models like ChatGPT. This research not only contributes to the field of ML system validation but also explores novel ways to leverage AI for automating and enhancing software engineering practices in ML.

关键词： visualization Source coding Taxonomy Data visualization machine learning Task analysis System validation

来源：评论

学校读者我要写书评

暂无评论

Gas Phase Nucleation Detection Using machine vision

Gas Phase Nucleation Detection Using Machine Vision

引用

ieee/SEMI Conference and workshop on Advanced Semiconductor Manufacturing

作者： Anthony Chua Amon Tan Koh Chuah Giga + PVD GlobalFoundries Singapore

ISBN: (数字)9798331531850

ISBN: (纸本)9798331531867

LAM ® Altus Tungsten chemical vapor deposition (WCVD) process needs to monitor gas phase nucleation (GPN) as one of process control parameters. Main factor causing GPN is the increased in silane (SiH 4 ) flow (relative to WF 6 flow), which create W x Si y particles. The GPN, which occurs during production, will lead to tungsten void due to SiH4 burst in nucleation step. However, control for such critical parameters is still manually done by visual inspection on a weekly basis. Hence, the auto GPN detection has been implemented using image recognition that is able to reduce human error and misjudgment, which in turn prevent wafer scraps incidents.

关键词： visualization machine vision Tungsten Process control Lighting Production Semiconductor device manufacture Inspection Reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Class Unlearning in CLIP with Synthetic Samples

Zero-Shot Class Unlearning in CLIP with Synthetic Samples

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Alexey Kravets Vinay P. Namboodiri University of Bath Bath UK

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

machine unlearning is a crucial area of research. It is driven by the need to remove sensitive information from models to safeguard individuals' right to be forgotten under rigorous regulations such as GDPR. In this work, we focus on unlearning within CLIP, a dual vision-language encoder model trained on a massive dataset of image-text pairs using contrastive loss. To achieve forgetting we expand the application of Lipschitz regularization to the multimodal context of CLIP. Specifically, we smooth both visual and textual embeddings associated with the class intended to be forgotten relative to the perturbation introduced to the samples from that class. Additionally, importantly, we remove the necessity for real forgetting data by generating synthetic samples via gradient ascent maximizing the target class. Our forgetting procedure is iterative, where we track accuracy on a synthetic forget set and stop when accuracy falls below a chosen threshold. We employ a selective layers update strategy based on their average absolute gradient value to mitigate over-forgetting. We validate our approach on several standard datasets and provide thorough ablation analysis and comparisons with previous work.

关键词： visualization Computer vision Accuracy Target tracking Perturbation methods Training data Regulation Data models Iterative methods Standards

来源：评论

学校读者我要写书评

暂无评论

Active Event Alignment for Monocular Distance Estimation

Active Event Alignment for Monocular Distance Estimation

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Nan Cai Pia Bideau Technical University of Berlin Germany UGA Inria CNRS Grenoble INP LJK France

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Event cameras provide a natural and data efficient representation of visual information, motivating novel computational strategies towards extracting visual information. Inspired by the biological vision system, we propose a behavior driven approach for object-wise distance estimation from event camera data. This behavior-driven method mimics how biological systems, like the human eye, stabilize their view based on ob-ject distance: distant objects require minimal compensatory rotation to stay in focus, while nearby objects demand greater adjustments to maintain alignment. This adaptive strategy leverages natural stabilization behaviors to estimate relative distances effectively. Unlike traditional vision algorithms that estimate depth across the entire image, our approach targets local depth estimation within a specific region of interest. By aligning events within a small region, we estimate the angular velocity required to stabilize the image motion. We demonstrate that, under certain assumptions, the compensatory rotational flow is inversely proportional to the object's distance. The proposed approach achieves new state-of-the-art accuracy in distance estimation - a performance gain of 16% on EVIM02. EVIM02 event sequences comprise complex camera motion and substantial variance in depth of static real world scenes. Code: https://***/pbideau/AAEDepth.

关键词： visualization machine vision Pipelines Estimation vision sensors Performance gain Cameras Vectors Data mining Optimization

来源：评论

学校读者我要写书评

暂无评论

Visualizing Tourism's Future: The Impact of Image-Based AI on Destination Development

Visualizing Tourism's Future: The Impact of Image-Based AI o...

引用

Metrology for Living Environment (MetroLivEn), ieee International workshop on

作者： Fiorella Folino Tommaso Ruga Ester Zumpano Eugenio Vocaturo DESF University of Calabria Rende CS Italy DIMES NANOTEC National Research Council University of Calabria Rende CS Italy

ISBN: (数字)9798350385014

ISBN: (纸本)9798350385021

Tourism represents an economically significant sector, leveraging a country's unique cultural heritage as a competitive advantage. Interest in cultural assets in the tourism sector has grown significantly in recent years as travelers seek authentic and meaningful experiences. In the context of this evolution, Artificial Intelligence (AI) is emerging as a key factor, radically transforming how travelers experience and share their adventures. Exploring architectural works, museums, archaeological sites can be completely revolutionized through the use of advanced image recognition and search technologies, allowing visitors to enhance their knowledge and arouse deeper interest in art cities. In this work we focus on App that use AI approaches on cultural heritage images, capturing the salient aspects useful for prototyping an our proprietary App designed to support an immersive experience in tourism.

关键词： visualization Image recognition machine vision Urban areas Education Immersive experience Metrology

来源：评论

学校读者我要写书评

暂无评论

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Pro...

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Xiwen Chen Huayu Li Peijie Qiu Wenhui Zhu Rahul Amin Abolfazl Razi Clemson University University of Arizona Washington University in St. Louis Arizona State University MIT Lincoln Laboratory

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Selecting representative samples plays an indispensable role in many machine learning and computer vision applications under limited resources (e.g., limited communication bandwidth and computational power). Determinantal Point Process (DPP) is a widely used method for selecting the most diverse representative samples that can summarize a dataset. However, its adaptability to different tasks remains an open challenge, as it is challenging for DPP to perform task-specific tuning. In contrast, Rate-Distortion (RD) theory provides a way to measure task-specific diversity. However, optimizing RD for a data selection problem remains challenging because the quantity that needs to be optimized is the index set of the selected samples. To tackle these challenges, we first draw an inherent relationship between DPP and RD theory. Our theoretical derivation paves the way to take advantage of both RD and DPP for a task-specific data selection. To this end, we propose a novel method for task-specific data selection for multi-level classification tasks, named RD-DPP. Empirical studies on seven different datasets using five benchmark models demonstrate the effectiveness of the proposed RD-DPP method. Our method also outperforms recent strong competing methods, while exhibiting high generalizability to a variety of learning tasks. The source code is available on https://***/xiwencl/RD-DPP 1 .

关键词： Training Computer vision Source coding Rate-distortion Data visualization machine learning Bandwidth Benchmark testing Indexes Tuning

来源：评论

学校读者我要写书评

暂无评论

Temporally Grounding Instructional Diagrams in Unconstrained Videos

Temporally Grounding Instructional Diagrams in Unconstrained...

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Jiahao Zhang Frederic Z. Zhang Cristian Rodriguez Yizhak Ben-Shabat Anoop Cherian Stephen Gould The Australian National University The Australian Institute for Machine Learning Technion Israel Institute of Technology Mitsubishi Electric Research Labs

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

We study the challenging problem of simultaneously localizing a sequence of instructional diagram queries in a video. This requires understanding not only the individual diagram queries but also their interrelationships. However, most existing methods focus on grounding one query at a time, ignoring the inherent structures among queries such as the general mutual exclusiveness and the temporal order. Consequently, the predicted timespans of different step diagrams may overlap considerably or violate the temporal order, thus harming the accuracy. In this paper, we tackle this issue by simultaneously grounding a sequence of step diagrams. Specifically, we propose composite queries, constructed by exhaustively pairing up the visual content features of the step diagrams and a fixed number of learnable positional embeddings. Our insight is that self-attention among composite queries carrying different content features suppress each other to reduce timespan overlaps in predictions, while the cross-attention corrects the temporal misalignment via content and position joint guidance. We demonstrate the effectiveness of our approach on the lAWdatasetfor grounding step diagrams and the YouCook2 benchmark for grounding natural language queries, significantly outperforming existing methods while simultaneously grounding multiple queries.

关键词： visualization Computer vision Accuracy Grounding Computational modeling Semantics Natural languages Manuals Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

GlobalDoc: A Cross-Modal vision-Language Framework for Real-World Document Image Retrieval and Classification

GlobalDoc: A Cross-Modal Vision-Language Framework for Real-...

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Souhail Bakkali Sanket Biswas Zuheng Ming Mickaël Coustaty Marçal Rusiñol Oriol Ramos Terrades Josep Lladós L3i La Rochelle Université France Computer Vision Center Universitat Autònoma de Barcelona Spain L2TI Université Sorbonne Paris Nord France AllRead Machine Learning Technologies Spain

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce GlobalDoc, a cross modal transformer-based architecture pre-trained in a self supervised manner using three novel pretext objective tasks. GlobalDoc improves the learning of richer semantic concepts by unifying language and visual representations, resulting in more transferable models. For proper evaluation, we also propose two novel document-level downstream VDU tasks, Few-Shot Document Image Classification (DIC) and Content-based Document Image Retrieval (DIR), designed to simulate industrial scenarios more closely. Extensive experimentation has been conducted to demonstrate GlobalDoc's effectiveness in practical settings.

关键词： Representation learning visualization Image retrieval Semantics Optical character recognition Transformers Robustness Data models Engines Image classification

来源：评论

学校读者我要写书评

暂无评论

Shape-Biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation

Shape-Biased Texture Agnostic Representations for Improved T...

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Peter Hönig Stefan Thalhammer Jean-Baptiste Weibel Matthias Hirschmanner Markus Vincze TU Wien Austria UAS Technikum Vienna Austria

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address this issue, we propose a strategy for inducing a shape bias to CNN training. In particular, by randomizing textures applied to object surfaces during data rendering, we create training data without consistent textural cues. This methodology allows for seamless integration into existing data rendering engines, and results in negligible computational overhead for data rendering and network training. Our findings demonstrate that the shape bias we induce via randomized texturing, improves over existing approaches using style transfer. We evaluate with five detectors and two pose estimators. For three object detectors and for pose estimation in general, estimation accuracy improves for textureless and metallic objects. Additionally we show that our approach increases the pose estimation accuracy in the presence of image noise and strong illumination changes. Code available at https://***/hoenigpeter/randomized_texturing.

关键词： Training Computer vision visualization Accuracy Shape Pose estimation Detectors Object detection Rendering (computer graphics) Transformers

来源：评论

学校读者我要写书评

暂无评论

Improving Keypoints Tracking With machine-Learned Features in Event-Camera-Based Visual Odometry

Improving Keypoints Tracking With Machine-Learned Features i...

引用

ieee Metrology for Aerospace

作者： Sebastiano Chiodini Giovanni Trevisanuto Carlo Bettanini Giacomo Colombatti Marco Pertile Dept. of Industrial Engineering University of Padova Padova Italy DAFNAE University of Padova Padova Italy

ISBN: (数字)9798350385045

ISBN: (纸本)9798350385052

This paper introduces a feature detection method developed through machine learning specifically tailored for event-camera based visual odometry techniques used in reconstructing trajectories for unmanned aerial vehicles. The proposed approach leverages machine-learned features to improve the precision of trajectory reconstruction. Unlike conventional visual odometry methods, which often struggle in low light and high-speed scenarios, the event-camera-based method addresses these challenges by focusing solely on detecting and processing changes in the visual scene. The machine-learned features are designed to capture the distinctive attributes of event-camera data, thereby refining the accuracy of trajectory reconstruction. The inference pipeline consists of a module that is iterated twice sequentially, comprising a Squeeze-and-Excite block and a ConvLSTM block with residual connection. This is succeeded by a final convolutional layer that generates trajectory information for corners in the form of heatmap sequences. In the experimental phase, a series of images was gathered using an event-camera in outdoor settings for both training and testing purposes.

关键词： Training visualization Tracking Robot vision systems Feature extraction Cameras Trajectory

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：