Learning Coupled Classifiers with RGB images for RGB-D object recognition
详细信息 查看全文
- 作者：Xiao LiAuthor Vitae ; Min Fang ; mfang@mail.xidian.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Ju-Jie ZhangAuthor Vitae ; Jinqiao WuAuthor Vitae
- 关键词：Object recognition ; Depth images ; Domain adaptation ; L2 ; 1 norm
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：433-446
- 全文大小：3935 K
文摘
- •
We aim to use RGB images to help recognizing RGB-D images.
- •
The correlation between the two target classifiers is utilized.
- •
The correlation between source and target domains is utilized.
- •
A unified framework is presented to learn the classifier parameters.
- •
Extensive experiment results show the astonishing results.