Minimally Supervised Acquisition of 3D Recognition Models from Large Visual Corpora
从大型视觉语料库中以最小监督方式获取 3D 识别模型
基本信息
- 批准号:9977206
- 负责人:
- 金额:$ 27.97万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:1999
- 资助国家:美国
- 起止时间:1999-09-01 至 2002-08-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Abstract IIS-9977206Nelson, RandalUniversity of Rochester$99,133 - 12 mos.Minimally Supervised Acquisition of 3D Recognition Models from Large Visual CorporaThis is the first year award of a three-year continuing grant. This research concerns with training 3D object recognition systems from imagery, which will allow the recognition of objects without constructing a 3D geometric model, and the recognition of objects where current geometric recognition technology does not apply. In various forms, image-based methods are currently the most successful general approach. Two issues that have been little explored are: (1) whether such systems can be trained from imagery that is unlabeled, and (2) whether they can be trained from imagery that is not trivially segmentable. These questions are the focus of this research proposal. Using a 3D recognition system the PI has developed, and possibly others, the project will investigate training, updating, and refining 3D representations for recognition from unstructured or semi-structured imagery and demonstrate the technology through working prototypes.Issues connected with training include basic algorithm design, controlling growth of the representation dealing with clutter, and correcting mistakes. Issues associated with the training corpus include quantifying the required density of salient images, allowable clutter, and required seed information. Issues connected to the recognition system include handling clutter, space requirements, and new capabilities such as dealing with hierarchical representations or flexible objects. Formal models for the various stages of the process will be developed.
摘要IIS-9977206纳尔逊,兰德尔罗切斯特大学$99,133 - 12月。最小监督收购的3D识别模型从大型视觉corporaThis是第一年奖的三年连续赠款。本研究关注从图像中训练3D对象识别系统,这将允许在不构建3D几何模型的情况下识别对象,以及识别当前几何识别技术不适用的对象。在各种形式中,基于图像的方法是目前最成功的通用方法。有两个问题很少被探讨:(1)这样的系统是否可以从未标记的图像中训练出来,以及(2)它们是否可以从不可分割的图像中训练出来。这些问题是本研究建议的重点。使用PI开发的3D识别系统,以及其他可能的系统,该项目将研究训练、更新和改进3D表示,以便从非结构化或半结构化图像中识别,并通过工作原型演示该技术。与训练有关的问题包括基本算法设计、控制表示的增长、处理杂波和纠正错误。与训练语料库相关联的问题包括量化显著图像的所需密度、允许的杂波和所需的种子信息。与识别系统相关的问题包括处理杂乱、空间要求和新功能,如处理分层表示或灵活对象。将为这一进程的各个阶段制定正式模式。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Randal Nelson其他文献
P16-016-23 Understanding the Impact of Altered Phosphatidylethanolamine (PE) Metabolism in Human Hepatoma Cells
- DOI:
10.1016/j.cdnut.2023.100776 - 发表时间:
2023-07-01 - 期刊:
- 影响因子:
- 作者:
Courtney Holdaway;Rene Jacobs;Kelly-Ann Leonard;Randal Nelson;Jelske Van der Veen - 通讯作者:
Jelske Van der Veen
P11-022-23 Dietary Trimethylamine N-Oxide Supplementation Improves Insulin Sensitivity and Hepatic Glucose Metabolism in High-Fat Diet Fed Mice
- DOI:
10.1016/j.cdnut.2023.101819 - 发表时间:
2023-07-01 - 期刊:
- 影响因子:
- 作者:
Hailey Fedoruk;Bergen Vetsch;Boshra Mandour;Bryan Lum;Randal Nelson;Kelly-Ann Leonard;Gia Shelp;Jessica Yue;Rene Jacobs - 通讯作者:
Rene Jacobs
emDe novo/em phosphatidylcholine synthesis in the small intestinal epithelium is required for normal dietary lipid handling and maintenance of the mucosal barrier
- DOI:
10.1016/j.bbalip.2021.159109 - 发表时间:
2022-04-01 - 期刊:
- 影响因子:3.300
- 作者:
Stephanie Carlin;John P. Kennelly;Hailey Fedoruk;Ariel Quiroga;Kelly-Ann Leonard;Randal Nelson;Aducio Thiesen;Jean Buteau;Richard Lehner;René Jacobs - 通讯作者:
René Jacobs
Alterations in phosphatidylethanolamine metabolism impacts hepatocellular lipid storage, energy homeostasis, and proliferation
磷脂酰乙醇胺代谢的改变影响肝细胞脂质储存、能量稳态和增殖
- DOI:
10.1016/j.bbalip.2025.159608 - 发表时间:
2025-05-01 - 期刊:
- 影响因子:3.300
- 作者:
Courtney M. Holdaway;Kelly-Ann Leonard;Randal Nelson;Jelske van der Veen;Chinmayee Das;Russell Watts;Robin D. Clugston;Richard Lehner;Rene L. Jacobs - 通讯作者:
Rene L. Jacobs
Randal Nelson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('Randal Nelson', 18)}}的其他基金
I-Corps: Nullspace: Full-Body Haptic Feedback for Virtual Reality
I-Corps:Nullspace:虚拟现实的全身触觉反馈
- 批准号:
1636992 - 财政年份:2016
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
Grounding Language in Visual Percepts
视觉感知中的基础语言
- 批准号:
0308049 - 财政年份:2003
- 资助金额:
$ 27.97万 - 项目类别:
Continuing Grant
INTEGRATED SENSING: Distributed Architecture for a Voluble Intelligent Environment
集成传感:可变智能环境的分布式架构
- 批准号:
0225413 - 财政年份:2002
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
CISE Research Infrastructure: Spatial Intelligence for Computer-Enhanced Interaction with Physical Environments
CISE 研究基础设施:用于计算机增强与物理环境交互的空间智能
- 批准号:
0080124 - 财政年份:2000
- 资助金额:
$ 27.97万 - 项目类别:
Continuing Grant
CISE Research Infrastructure: A Laboratory for Intelligent Multi-Sense Interfaces (A Planning Grant)
CISE 研究基础设施:智能多传感接口实验室(规划拨款)
- 批准号:
9972881 - 财政年份:1999
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
CISE Research Instrumentation: High-Performance Vehicle with Visual and Deictic Control
CISE 研究仪器:具有视觉和指示控制的高性能车辆
- 批准号:
9421532 - 财政年份:1995
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
Temporal Texture and Action Identification: A Recognition Approach to Motion
时间纹理和动作识别:运动的识别方法
- 批准号:
9010692 - 财政年份:1990
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
相似海外基金
Self-Supervised Sequential Biomedical Image-Omics
自监督序贯生物医学图像组学
- 批准号:
DE240100168 - 财政年份:2024
- 资助金额:
$ 27.97万 - 项目类别:
Discovery Early Career Researcher Award
Investigating the Trustworthiness of Deep Pre-trained and Self-supervised Learned Model.
研究深度预训练和自监督学习模型的可信度。
- 批准号:
24K20806 - 财政年份:2024
- 资助金额:
$ 27.97万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
SHF: Small: Semi-supervised Learning for Design and Quality Assurance of Integrated Circuits
SHF:小型:集成电路设计和质量保证的半监督学习
- 批准号:
2334380 - 财政年份:2024
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
A data-saving and self-supervised deep learning system for continuous ischemic stroke assessment
用于连续缺血性中风评估的数据保存和自我监督深度学习系统
- 批准号:
24K15011 - 财政年份:2024
- 资助金额:
$ 27.97万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Self-supervised feature learning for rapid processing of marine imagery
用于快速处理海洋图像的自监督特征学习
- 批准号:
LP220200949 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
Linkage Projects
Enhancing Hypnotic Medication Discontinuation in Primary Care through Supervised Medication Tapering and Digital Cognitive Behavioral Insomnia Therapy
通过监督药物逐渐减量和数字认知行为失眠治疗,加强初级保健中催眠药物的停药
- 批准号:
10736443 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
SCH: Dementia Early Detection for Under-represented Populations via Fair Multimodal Self-Supervised Learning
SCH:通过公平的多模式自我监督学习对代表性不足的人群进行痴呆症早期检测
- 批准号:
10816864 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
Knockoff Feature Selection Techniques for Robust Inference in Supervised and Unsupervised Learning
监督和无监督学习中鲁棒推理的仿冒特征选择技术
- 批准号:
2310955 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
CAP: Semi-supervised Fairness-Enhanced Knowledge Graph Construction on Social Media for AI-Enhanced Juvenile Justice
CAP:社交媒体上的半监督公平增强知识图谱构建,用于人工智能增强少年司法
- 批准号:
2323419 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
Standard Grant
Personal assistance for disabled people, changing labour markets and social care reform, supervised by Dr. Charlotte Pearson (first supervisor), Profe
为残疾人提供个人援助、不断变化的劳动力市场和社会保障改革,由教授 Charlotte Pearson 博士(第一导师)监督
- 批准号:
2888714 - 财政年份:2023
- 资助金额:
$ 27.97万 - 项目类别:
Studentship