Large-vocabulary Semantic Image Processing: Theory and Algorithms
大词汇量语义图像处理:理论与算法
基本信息
- 批准号:0830535
- 负责人:
- 金额:$ 23.95万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2008
- 资助国家:美国
- 起止时间:2008-09-01 至 2015-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Classical image processing has mostly disregarded semantic image representations, in favor of more mathematically tractable representations based on low?]level signal properties (frequency decompositions, mean squared error, etc.). This is unlike biological solutions to image processingproblems, which rely extensively on understanding of scene content. For example, regions of faces are usually processed more carefully than the bushes in the background. The inability to tune image processing to the semantic relevance of image content frequently leads to the sub?]optimal allocation ofresources, such as bandwidth, error protection, or viewing time, to image areas that are perceptually irrelevant. One of the main obstacles to the deployment of semantic image processing systems has been the difficulty of training content?]understanding systems with large scale vocabularies. This is, in great part, due to the requirement for large amounts of training data and intensive human supervision associated with the classical methods for vocabulary learning. This research aims to establish a foundation for semantic image processing systems that can learn large scale vocabularies frominformally annotated data and no additional human supervision. It builds on recent advances in semantic image labeling, which have made it possible to learn vocabularies from noisy training data, such as that massively (and inexpensively) available on the web. The research studies both theoreticalissues in vocabulary learning, and the design of image processing algorithms that tune their behavior according to the content of the images being processed. Semantic image processing could lead to transformative advances in areas such as image compression, enhancement, encryption, de?]noising, orsegmentation, among others, which are of interest for applications as diverse as medical imaging, image search and retrieval, or security and surveillance.
经典的图像处理大多忽略了语义图像表示,有利于更数学上易于处理的表示基于低?]电平信号特性(频率分解、均方误差等)。这与图像处理问题的生物解决方案不同,后者广泛依赖于对场景内容的理解。例如,人脸区域通常比背景中的灌木丛处理得更仔细。无法将图像处理调整到图像内容的语义相关性经常导致子?]最佳的资源分配,如带宽,错误保护,或观看时间,以图像领域的感知无关。部署语义图像处理系统的主要障碍之一是训练内容的困难。理解具有大规模词汇表的系统。这在很大程度上是由于传统的词汇学习方法需要大量的训练数据和密集的人工监督。本研究的目的是建立一个语义图像处理系统,可以学习大规模的词汇非正式标注的数据和没有额外的人的监督的基础。它建立在语义图像标记的最新进展之上,这使得从嘈杂的训练数据中学习词汇成为可能,例如在网络上大量(且廉价)可用的数据。这项研究既研究了词汇学习的理论问题,也研究了图像处理算法的设计,这些算法根据被处理图像的内容来调整它们的行为。语义图像处理可能会导致图像压缩、增强、加密、去重等领域的变革性进步。噪声、或分割等,这些都是医学成像、图像搜索和检索、或安全和监视等不同应用所关注的。
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 }}
Nuno Vasconcelos其他文献
Advanced methods for robust object detection
用于稳健物体检测的先进方法
- DOI:
- 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
Zhaowei Cai;Nuno Vasconcelos - 通讯作者:
Nuno Vasconcelos
121 Neural Network Dose Prediction for Cervical Brachytherapy: Overcoming Data Scarcity for Applicator-Specific Models
用于宫颈近距离放射治疗的 121 神经网络剂量预测:克服特定施源器模型的数据稀缺性
- DOI:
10.1016/s0167-8140(23)89212-x - 发表时间:
2023-09-01 - 期刊:
- 影响因子:5.300
- 作者:
Lance Moore;Karoline Kallis;Nuno Vasconcelos;Kelly Kisling;Dominique Rash;Catheryn Yashar;Jyoti Mayadev;Kevin Moore;Sandra Meyers - 通讯作者:
Sandra Meyers
Towards Calibrated Multi-label Deep Neural Networks
迈向校准的多标签深度神经网络
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Jiacheng Cheng;Nuno Vasconcelos - 通讯作者:
Nuno Vasconcelos
Nuno Vasconcelos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('Nuno Vasconcelos', 18)}}的其他基金
RI:Small:Dynamic Networks for Efficient, Adaptive, and Multimodal Vision
RI:Small:用于高效、自适应和多模态视觉的动态网络
- 批准号:
2303153 - 财政年份:2023
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
FAI: Towards Holistic Bias Mitigation in Computer Vision Systems
FAI:迈向计算机视觉系统中的整体偏差缓解
- 批准号:
2041009 - 财政年份:2021
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
NRI: FND: Towards Scalable and Self-Aware Robotic Perception
NRI:FND:迈向可扩展和自我意识的机器人感知
- 批准号:
1924937 - 财政年份:2019
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
NRI: Real-Time Semantic Computer Vision for Co-Robotics
NRI:协作机器人的实时语义计算机视觉
- 批准号:
1637941 - 财政年份:2016
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
BIGDATA: Collaborative Research: IA: Quantifying Plankton Diversity with Taxonomy and Attribute Based Classifiers of Underwater Microscope Images
大数据:合作研究:IA:利用水下显微镜图像的分类和属性分类器量化浮游生物多样性
- 批准号:
1546305 - 财政年份:2016
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
NRI-Small: A Biologically Plausible Architecture for Robotic Vision
NRI-Small:一种生物学上合理的机器人视觉架构
- 批准号:
1208522 - 财政年份:2012
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
RI-Small: Optimal Automated Design of Cascaded Object Detectors
RI-Small:级联物体检测器的优化自动化设计
- 批准号:
0812235 - 财政年份:2008
- 资助金额:
$ 23.95万 - 项目类别:
Standard Grant
Understanding Video of Crowded Environments
了解拥挤环境的视频
- 批准号:
0534985 - 财政年份:2005
- 资助金额:
$ 23.95万 - 项目类别:
Continuing Grant
CAREER: Weakly Supervised Recognition
职业:弱监督识别
- 批准号:
0448609 - 财政年份:2005
- 资助金额:
$ 23.95万 - 项目类别:
Continuing Grant
相似海外基金
Research and development of an adverse outcome pathway-focused mechanistic inference tool for 'omics data using semantic knowledge graphs
使用语义知识图研究和开发针对“组学数据”的以不良结果途径为中心的机械推理工具
- 批准号:
10761637 - 财政年份:2023
- 资助金额:
$ 23.95万 - 项目类别:
Lexico-semantic abilities in early language growth and delay
早期语言发展和延迟的词汇语义能力
- 批准号:
10353391 - 财政年份:2021
- 资助金额:
$ 23.95万 - 项目类别:
Lexico-semantic abilities in early language growth and delay
早期语言发展和延迟的词汇语义能力
- 批准号:
10576365 - 财政年份:2021
- 资助金额:
$ 23.95万 - 项目类别:
Lexico-semantic abilities in early language growth and delay
早期语言发展和延迟的词汇语义能力
- 批准号:
10840681 - 财政年份:2021
- 资助金额:
$ 23.95万 - 项目类别:
Semantic learning deficits in school age children with developmental language disorder
患有发展性语言障碍的学龄儿童的语义学习缺陷
- 批准号:
10192694 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别:
Semantic learning deficits in school age children with developmental language disorder
患有发展性语言障碍的学龄儿童的语义学习缺陷
- 批准号:
10461824 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别:
Building a Vocabulary: Lexical-semantic Development in Latino Children with Early Language Delay
建立词汇:早期语言发育迟缓的拉丁裔儿童的词汇语义发展
- 批准号:
10594446 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别:
Building a Vocabulary: Lexical-semantic Development in Latino Children with Early Language Delay
建立词汇:早期语言发育迟缓的拉丁裔儿童的词汇语义发展
- 批准号:
10383739 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别:
Semantic learning deficits in school age children with developmental language disorder
患有发展性语言障碍的学龄儿童的语义学习缺陷
- 批准号:
10046212 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别:
Building a Vocabulary: Lexical-semantic Development in Latino Children with Early Language Delay
建立词汇:早期语言发育迟缓的拉丁裔儿童的词汇语义发展
- 批准号:
9977530 - 财政年份:2020
- 资助金额:
$ 23.95万 - 项目类别: