Structured Dictionary Models and Learning for High Resolution Images
高分辨率图像的结构化字典模型和学习
基本信息
- 批准号:1724979
- 负责人:
- 金额:$ 10.55万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2016
- 资助国家:美国
- 起止时间:2016-07-01 至 2018-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
We will develop novel techniques for the multi-resolution analysis of high-resolution images, to obtain novel efficient and information representations. These representations will take into account natural invariances in images, and will lead to novel dictionary learning constructions and algorithms for images and in signal processing in general. These representations will then be used to analyze, search, and recognize similar objects or features in collections of (scans of) paintings, in particular a large collection by the baroque artist Jan Brueghel. The distances between images and portions thereof, the features learned by the extensions of dictionary learning we will construct, and the associated statistical similarities, together with labels provided by experts to be used to train classifiers and algorithms that learn similarities among items to match those provided by expert, will enable us to enrich the current set of capabilities in building these large networks of paintings, to search through them more easily and with more general search patterns, and to visualize them according to different metrics by using dimensionality reduction techniques.The automatic learning of templates and patterns, and their statistical relationships, in images and signals in general is crucial in a wide variety of applications, such as automating object recognition, and in defining visually meaningful similarities between images, needed to enable searches in large image databases. We will both develop novel techniques for automatically learning good templates for images, that incorporate natural invariances such as translations and scalings, and novel ways of exploiting these templates for analyzing large collections images, measuring the similarities between then, and finding and characterizing recurrent patterns in them. These novel techniques will be applied to the data on the Jan Brueghel Research site, that allows scholars to investigate and conceptualize a very different notion of old master pictures. Instead of creating absolute categories of genuine and not-genuine, the team will be drawing a map of interconnections between the thousands of paintings produced in the workshops of early modern Antwerp. These pictures were made over several generations, in the shops of masters ranging from world-famous (Pieter Brueghel, Rubens) to utterly obscure. The website will chart how ideas were generated, exchanged, reused and retooled by different artists, mapping networks of creation and production well beyond those traceable through archival documents.
我们将开发用于高分辨率图像的多分辨率分析的新技术,以获得新的高效和信息表示。这些表示将考虑图像中的自然不变性,并将导致新的字典学习结构和算法的图像和信号处理一般。然后,这些表示将用于分析,搜索和识别绘画(扫描)集合中的类似对象或特征,特别是巴洛克艺术家Jan Brueghel的大型收藏。图像及其部分之间的距离,通过我们将构建的字典学习的扩展学习的特征,以及相关的统计相似性,以及专家提供的用于训练分类器的标签和学习项目之间相似性以匹配专家提供的那些的算法,将使我们能够丰富当前构建这些大型绘画网络的能力,在图像和信号中,模板和模式的自动学习以及它们的统计关系通常在各种各样的应用中是至关重要的,例如自动化对象识别,以及定义图像之间的视觉上有意义的相似性,这是在大型图像数据库中进行搜索所需要的。我们都将开发新的技术,用于自动学习图像的良好模板,这些模板包含自然的不变性,如翻译和缩放,以及利用这些模板分析大型集合图像的新方法,测量它们之间的相似性,并发现和表征它们中的循环模式。这些新颖的技术将应用于Jan Brueghel研究网站上的数据,使学者能够调查和概念化一个非常不同的概念。该团队将绘制一张地图,展示早期现代安特卫普工作室制作的数千幅画作之间的相互联系,而不是创建真正和非真正的绝对类别。这些画是几代人在大师的商店里制作的,从世界著名的(彼得·勃鲁盖尔,鲁本斯)到完全默默无闻的。该网站将描绘不同艺术家如何产生、交换、重用和重组想法,绘制创作和生产的网络,远远超出那些通过档案文件可追溯的网络。
项目成果
期刊论文数量(1)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Adaptive Geometric Multiscale Approximations for Intrinsically Low-dimensional Data
- DOI:
- 发表时间:2016-11
- 期刊:
- 影响因子:0
- 作者:Wenjing Liao;M. Maggioni
- 通讯作者:Wenjing Liao;M. Maggioni
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Mauro Maggioni其他文献
A scalable framework for learning the geometry-dependent solution operators of partial differential equations
用于学习偏微分方程的几何依赖解算符的可扩展框架
- DOI:
10.1038/s43588-024-00732-2 - 发表时间:
2024-12-09 - 期刊:
- 影响因子:18.300
- 作者:
Minglang Yin;Nicolas Charon;Ryan Brody;Lu Lu;Natalia Trayanova;Mauro Maggioni - 通讯作者:
Mauro Maggioni
Critical Exponent of Short Even Filters andBurt-Adelson Biorthogonal Wavelets
- DOI:
10.1007/s006050070024 - 发表时间:
2000-11-15 - 期刊:
- 影响因子:0.800
- 作者:
Mauro Maggioni - 通讯作者:
Mauro Maggioni
DH-482888-001 PREDICTING PERSONALIZED CARDIAC ELECTROPHYSIOLOGY USING DEEP LEARNING
DH-482888-001 使用深度学习预测个性化心脏电生理学
- DOI:
10.1016/j.hrthm.2024.03.261 - 发表时间:
2024-05-01 - 期刊:
- 影响因子:5.700
- 作者:
Minglang Yin;Nicolas Charon;Ryan Brody;Lu Lu;Mauro Maggioni;Natalia A. Trayanova - 通讯作者:
Natalia A. Trayanova
PO-01-212 strongA NOVEL DEEP LEARNING MODEL FOR PATIENT-SPECIFIC COMPUTATIONAL MODELING OF CARDIAC ELECTROPHYSIOLOGY/strong
PO-01-212 一种用于患者特异性心脏电生理计算建模的强大新型深度学习模型
- DOI:
10.1016/j.hrthm.2023.03.530 - 发表时间:
2023-05-01 - 期刊:
- 影响因子:5.700
- 作者:
Minglang Yin;Lu Lu;Mauro Maggioni;Natalia A. Trayanova - 通讯作者:
Natalia A. Trayanova
Mauro Maggioni的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Mauro Maggioni', 18)}}的其他基金
BIGDATA: F: Compositional Learning, Maps and Transfer: Statistical and Machine Learning on Collections of Data Sets
BIGDATA:F:组合学习、地图和迁移:数据集集合的统计和机器学习
- 批准号:
1837991 - 财政年份:2019
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
ATD: Estimation and Anomaly Detection for high-dimensional Data, Maps and Dynamic Processes
ATD:高维数据、地图和动态过程的估计和异常检测
- 批准号:
1737984 - 财政年份:2017
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
ATD: Online Multiscale Algorithms for Geometric Density Estimation in High-Dimensions and Persistent Homology of Data for Improved Threat Detection
ATD:用于高维几何密度估计和数据持久同源性的在线多尺度算法,以改进威胁检测
- 批准号:
1756892 - 财政年份:2016
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
Collaborative Proposal: SI2-CHE: ExTASY Extensible Tools for Advanced Sampling and analYsis
合作提案:SI2-CHE:用于高级采样和分析的 ExTASY 可扩展工具
- 批准号:
1708353 - 财政年份:2016
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
BIGDATA: Collaborative Research: F: From Data Geometries to Information Networks
BIGDATA:协作研究:F:从数据几何到信息网络
- 批准号:
1708553 - 财政年份:2016
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
Statistical Learning for High-Dimensional Stochastic Dynamical Systems
高维随机动力系统的统计学习
- 批准号:
1708602 - 财政年份:2016
- 资助金额:
$ 10.55万 - 项目类别:
Continuing Grant
BIGDATA: Collaborative Research: F: From Data Geometries to Information Networks
BIGDATA:协作研究:F:从数据几何到信息网络
- 批准号:
1546392 - 财政年份:2016
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
Statistical Learning for High-Dimensional Stochastic Dynamical Systems
高维随机动力系统的统计学习
- 批准号:
1522651 - 财政年份:2015
- 资助金额:
$ 10.55万 - 项目类别:
Continuing Grant
Structured Dictionary Models and Learning for High Resolution Images
高分辨率图像的结构化字典模型和学习
- 批准号:
1320655 - 财政年份:2013
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
Collaborative Proposal: SI2-CHE: ExTASY Extensible Tools for Advanced Sampling and analYsis
合作提案:SI2-CHE:用于高级采样和分析的 ExTASY 可扩展工具
- 批准号:
1265920 - 财政年份:2013
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
相似海外基金
A complete double copy dictionary and its applications
完整的双副本词典及其应用
- 批准号:
2868821 - 财政年份:2023
- 资助金额:
$ 10.55万 - 项目类别:
Studentship
North American Indian Sign Language Video Dictionary
北美印第安手语视频词典
- 批准号:
2302419 - 财政年份:2023
- 资助金额:
$ 10.55万 - 项目类别:
Standard Grant
Development and maintenance of an English-Japanese dictionary for learners based on the perspective of English phraseology research.
基于英语短语学研究视角的英日学习词典的开发与维护
- 批准号:
23K00592 - 财政年份:2023
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Distributed video coding and deep learning using convolutional sparse dictionary generated with large scale datasets
使用大规模数据集生成的卷积稀疏字典进行分布式视频编码和深度学习
- 批准号:
23K11159 - 财政年份:2023
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Development of a Practical Medical Terminology Dictionary toward Entity Linking
开发面向实体链接的实用医学术语词典
- 批准号:
23H03492 - 财政年份:2023
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
Development of a new-concept Japanese-English dictionary: concise but comprehensive with wide applications for Japanese students of English
新概念日英词典的开发:简洁全面,适用范围广,适合日本英语学生
- 批准号:
22K00775 - 财政年份:2022
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Integrated Dictionary Usage during Online Extensive Reading and its Effect on Learner Enjoyment, Confidence and Use of Reading Strategies
在线泛读过程中词典的综合使用及其对学习者享受、自信心和阅读策略运用的影响
- 批准号:
22K00821 - 财政年份:2022
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
A Geographical Pursuit on the Development of a "GIS Place-Name Dictionary" for Japan as a Foundation for Interdisciplinary Research on Digital Humanities
为日本开发“GIS地名词典”作为数字人文跨学科研究基础的地理学追求
- 批准号:
22K18254 - 财政年份:2022
- 资助金额:
$ 10.55万 - 项目类别:
Grant-in-Aid for Challenging Research (Pioneering)
Automating Dictionary Construction for Better Natural Language Processing
自动构建字典以实现更好的自然语言处理
- 批准号:
RGPIN-2015-05615 - 财政年份:2022
- 资助金额:
$ 10.55万 - 项目类别:
Discovery Grants Program - Individual
Online Dictionary Learning for Dependent and Multimodal Data Samples: Convergence, Complexity, and Applications
相关和多模态数据样本的在线字典学习:收敛性、复杂性和应用
- 批准号:
2206296 - 财政年份:2022
- 资助金额:
$ 10.55万 - 项目类别:
Continuing Grant