guo2017.pdf


立即下载 google你他吗
2024-03-24
Nanjing P. R. China multiple supervised learning University frame work
381.6 KB

Deep Multi-Instance Multi-Label Learning
for Image Annotation
Hai-Feng Guo*,†, Lixin Han*,‡,¶, Shoubao Su†
and Zhou-Bao Sun§
*College of Computer and Information
Hohai University, Nanjing 210024, P. R. China
†School of Computer Engineering, Jinling Institute of Technology
Nanjing 211169, P. R. China
‡State Key Laboratory of Novel Software Technology
Nanjing University, Nanjing 210093, P. R. China
§Nanjing Audit University, Nanjing 211815, P. R. China
¶lhan@hhu.edu.cn
Received 29 March 2017
Accepted 27 June 2017
Published 18 August 2017
Multi-Instance Multi-Label learning (MIML) is a popular framework for supervised classi¯ca-
tion where an example is described by multiple instances and associated with multiple labels.
Previous MIML approaches have focused on predicting labels for instances. The idea of tackling
the problem is to identify its equivalence in the traditional supervised learning framework.
Motivated by the recent advancement in deep learning, in this pap


Nanjing/P./R./China/multiple/supervised/learning/University/frame/work/ Nanjing/P./R./China/multiple/supervised/learning/University/frame/work/
-1 条回复
登录 后才能参与评论
-->