Collaborative Research: Learning Taxonomies of the Visual World
Collaborative Research: Learning Taxonomies of the Visual World
批准号:
0535292
负责人:
Pietro Perona
金额:
$15.62万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2005
资助国家:
美国
项目状态:
已结题
起止时间:
2005-08-01 至 2008-07-31
中文摘要
学习视觉对象类别和识别图像中的对象,可能是当今机器视觉中最困难和最令人兴奋的问题。鉴于科学、工程、工业和社会中快速增长的数据洪流,识别系统必须能够在没有人类监督的情况下运行。这带来了新的挑战:如何从未标记的图像中自动学习大量对象类的模型?如何表示这些对象类,以便能够有效地搜索它们?如何利用已经学习的模型从很少的例子中学习新的对象类呢?有人提出,这些挑战可以通过从未标记的图像数据中推断对象类的层次表示来解决。对象类表示为部件的星座,其中每个部件提取形状和外观信息。非参数贝叶斯技术可以用来将这些对象类组织成树状结构的表示。随着向系统提供的数据越来越多,这种表示的丰富性也会逐渐增加。对象类之间的新的相似性度量自然从这种表示中派生出来,从而促进识别。通过与加州州立大学北岭分校(California State University Northridge)的合作,建立了与当地社区的联系,在那里,学生(通常是家庭中第一个获得大学学位的少数民族)将有机会参与当地公司提出的和与之相关的视觉识别问题。
英文摘要
Learning visual object categories, and recognizing objects in images, is perhaps the most difficult and exciting problem in machine vision today. In light of the fast growing data deluge in science, engineering, industry and society, recognition systems must be able to operate without human supervision. This poses new challenges: How can one learn automatically models of a large number of object classes from unlabelled images? How can one represent these object classes such that they can be searched efficiently? How can one leverage the learnt models to learn new object classes from very few examples?It is proposed that these challenges may be met by inferring hierarchical representations of object classes from unlabelled image data. Object classes are represented as constellations of parts, where each part extracts shape and appearance information.Non-parametric Bayesian techniques may be employed to organize these object classes into tree-structured representations. The richness of this representation grows incrementally as more data is presented to the system. New similarity measures between object classes naturally derive from this representation facilitating recognition.Outreach to the local community is established through a collaboration with the California State University Northridge where students, often minorities who are the first in the family to obtain a university degree, will have the opportunity to engage in visual recognition problems proposed by and relevant to local companies.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
RI: Medium: CompCog: Automated Discovery of Macro-Variables from Raw Spatiotemporal Data
-
批准号:1564330
-
项目类别:Continuing Grant
-
资助金额:$110.0万
-
财政年份:2016
-
负责人:Pietro Perona
-
依托单位:
I-Corps: Combining Machine Vision and Crowdsourcing for Convenient and Accurate Image Annotation
-
批准号:1216839
-
项目类别:Standard Grant
-
资助金额:$5.0万
-
财政年份:2012
-
负责人:Pietro Perona
-
依托单位:
RI: Small: Collaborative Research: Infinite Bayesian Networks for Hierarchical Visual Categorization
-
批准号:0914789
-
项目类别:Standard Grant
-
资助金额:$20.0万
-
财政年份:2009
-
负责人:Pietro Perona
-
依托单位:
3d Perception of Specular Surfaces
-
批准号:0413312
-
项目类别:Continuing Grant
-
资助金额:$0.0万
-
财政年份:2005
-
负责人:Pietro Perona
-
依托单位:
ITR: Learning and recognition of objects in sensory data.
-
批准号:0082830
-
项目类别:Standard Grant
-
资助金额:$41.32万
-
财政年份:2000
-
负责人:Pietro Perona
-
依托单位:
Cortical Models for Neuromorphic Engineering
-
批准号:9908537
-
项目类别:Standard Grant
-
资助金额:$20.0万
-
财政年份:2000
-
负责人:Pietro Perona
-
依托单位:
Equipment Proposal: Early Reach Plans in Parietal Cortex: Toward a Cortical Prosthetic for Arm Movements
-
批准号:9907396
-
项目类别:Standard Grant
-
资助金额:$11.12万
-
财政年份:1999
-
负责人:Pietro Perona
-
依托单位:
ERC-CREST Partnership Towards Consumer Telepresence
-
批准号:9730980
-
项目类别:Continuing Grant
-
资助金额:$50.01万
-
财政年份:1998
-
负责人:Pietro Perona
-
依托单位:
Human-Computer Interaction with Virtual Social Groups
-
批准号:9812714
-
项目类别:Continuing Grant
-
资助金额:$29.29万
-
财政年份:1998
-
负责人:Pietro Perona
-
依托单位:
A Real-Time Human-Coupled Maultiagent System with Reactive Social Organization, Based on Biological Principles
-
批准号:9615071
-
项目类别:Standard Grant
-
资助金额:$5.0万
-
财政年份:1996
-
负责人:Pietro Perona
-
依托单位:
Engineering Research Center for Neuromorphic Systems Engineering
-
批准号:9402726
-
项目类别:Cooperative Agreement
-
资助金额:$816.98万
-
财政年份:1994
-
负责人:Pietro Perona
-
依托单位:
NSF Young Investigator
-
批准号:9457618
-
项目类别:Continuing Grant
-
资助金额:$31.25万
-
财政年份:1994
-
负责人:Pietro Perona
-
依托单位:
U. S.-ESPRIT Collaboration: Geometry-Driven Diffusion in Vision
-
批准号:9306155
-
项目类别:Continuing Grant
-
资助金额:$7.5万
-
财政年份:1993
-
负责人:Pietro Perona
-
依托单位:
RIA: Deformable Kernel Filtering for Early Visual Processing
-
批准号:9211651
-
项目类别:Continuing Grant
-
资助金额:$9.0万
-
财政年份:1992
-
负责人:Pietro Perona
-
依托单位:
国内基金
海外基金
登录
查看更多内容
Research on Quantum Field Theory without a Lagrangian Description
-
批准号:24ZR1403900
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2024
-
负责人:SATOSHI NAWATA
-
依托单位:
Cell Research
-
批准号:31224802
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2012
-
负责人:程磊
-
依托单位:
Cell Research
-
批准号:31024804
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2010
-
负责人:程磊
-
依托单位:
Cell Research (细胞研究)
-
批准号:30824808
-
项目类别:专项基金项目
-
资助金额:24.0万元
-
批准年份:2008
-
负责人:张爱兰
-
依托单位:
Research on the Rapid Growth Mechanism of KDP Crystal
-
批准号:10774081
-
项目类别:面上项目
-
资助金额:45.0万元
-
批准年份:2007
-
负责人:滕冰
-
依托单位: