发明授权
US09158965B2 Method and system for optimizing accuracy-specificity trade-offs in large scale visual recognition
有权
在大规模视觉识别中优化精度特异性权衡的方法和系统
- 专利标题： Method and system for optimizing accuracy-specificity trade-offs in large scale visual recognition
- 专利标题（中）： 在大规模视觉识别中优化精度特异性权衡的方法和系统
-
申请号： US13831833申请日： 2013-03-15
-
公开(公告)号： US09158965B2公开(公告)日： 2015-10-13
- 发明人: Fei-Fei Li , Jia Deng , Jonathan Krause , Alexander C. Berg
- 申请人： The Board of Trustees for the Leland Stanford Junior University
- 申请人地址： US CA Stanford
- 专利权人： The Board of Trustees of the Leland Stanford Junior University
- 当前专利权人： The Board of Trustees of the Leland Stanford Junior University
- 当前专利权人地址： US CA Stanford
- 代理机构： KPPB LLP
- 主分类号： G06K9/00
- IPC分类号： G06K9/00 ; G06K9/62
摘要：
As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. Embodiment of the present invention include methods for optimizing accuracy-specificity trade-offs in large scale recognition where object categories form a semantic hierarchy consisting of many levels of abstraction.
公开/授权文献
信息查询
