2012 Fiscal Year Final Research Report
Joint Optimization of Object Region Localization and Recognition/Detection Model Learning
Project/Area Number |
23650093
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Multi-year Fund |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | National Institute of Informatics |
Principal Investigator |
SATOH Shin'ichi 国立情報学研究所, コンテンツ科学研究系, 教授 (90249938)
|
Project Period (FY) |
2011 – 2012
|
Keywords | 一般画像認識 / 体領域検出 |
Research Abstract |
We addressed a method to locate target objects and to learn object recognition and detection models simultaneously from given large collection of images with labels of target objects. The method does not require bounding rectangles or object regions of training images but just object labels, which are easily prepared by manual annotation, or easily obtained from Flickr or closed captioned videos. Object region localization functionality enables image synthesis and more precise object recognition and detection
|
-
-
-
-
-
-
[Book] Taylor & Francis Group2012
Author(s)
Xiaomeng Wu, Sebastien Poullot, and Shin'ichi Satoh
Total Pages
423
Publisher
Multimedia Duplicate Mining toward Knowledge Discovery,' in Frank Y. Shih ed., ``Multimedia Security: Watermarking, Steganography, and Forensics,''
-
[Remarks] 佐藤真一, ``マルチメディア解析・検索研 究のための大規模コーパスの動向,'' 画 像ラボ, Vol.22, No.6, pp.19-26, 2011.