Multi-scale volumes for deep object detection and localization
详细信息 查看全文
- 作者：Eshed Ohn-Bar ; eohnbar@ucsd.edu" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Mohan Manubhai TrivediAuthor Vitae
- 关键词：Multi-scale reasoning ; Context modeling ; Efficient detection with deep features ; Scale variation handling ; Structured prediction
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：557-572
- 全文大小：5354 K
文摘
- •
Multi-scale feature reasoning for deep object detection in images is analyzed.
- •
A multi-scale contextual reasoning approach is proposed using multi-scale volumes.
- •
Scale-specific, joint detection and localization models increase robustness.
- •
The approach efficiently handles challenging cases of large variation in scale.