Deep Multi-Instance Multi-Label Learning for Image Annotation
Deep Multi-Instance Multi-Label Learning for Image Annotation
复制标题
用于图像标注的深度多实例多标签学习
DOI:
10.1142/s021800141859005x
复制
发表时间:
2018-03
影响因子:
1.5
通讯作者:
Zhoubao Sun
中科院分区:
文献类型:
--
作者:
Haifeng Guo;Lixin Han;Shoubao Su;Zhoubao Sun
Multi-Instance Multi-Label learning (MIML) is a popular framework for supervised classification 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 paper, we still consider the problem of predicting labels and attempt to model deep learning in MIML learning framework. The proposed approach enables us to train deep convolutional neural network with images from social networks where images are well labeled, even labeled with several labels or uncorrelated labels. Experiments on real-world datasets demonstrate the effectiveness of our proposed approach.
登录
查看更多内容
DOI:
--
发表时间:
--
期刊:
--
影响因子:
--
作者:
Jia Li;James Ze Wang
通讯作者:
Jia Li;James Ze Wang
DOI:
10.1145/1873951.1874164
发表时间:
2010-10
期刊:
Proceedings of the 18th ACM international conference on Multimedia
影响因子:
--
作者:
Shenghua Gao;Zhengxiang Wang-;L. Chia;I. Tsang
通讯作者:
Shenghua Gao;Zhengxiang Wang-;L. Chia;I. Tsang
DOI:
10.1109/icdm.2010.109
发表时间:
2010-12
期刊:
2010 IEEE International Conference on Data Mining
影响因子:
--
作者:
Nam Nguyen
通讯作者:
Nam Nguyen
DOI:
10.1109/bmei.2011.6098544
发表时间:
2011-12
期刊:
2011 4th International Conference on Biomedical Engineering and Informatics (BMEI)
影响因子:
--
作者:
Jianjun Yan;Qingwei Shen;Jintao Ren;Yiqin Wang;Chunfeng Chen;Rui Guo;Haixia Yan
通讯作者:
Jianjun Yan;Qingwei Shen;Jintao Ren;Yiqin Wang;Chunfeng Chen;Rui Guo;Haixia Yan
DOI:
10.1109/iccv.2011.6126300
发表时间:
2011-11
期刊:
2011 International Conference on Computer Vision
影响因子:
--
作者:
X. Xue;Wei Zhang;Jie Zhang;Bin Wu;Jianping Fan;Yao Lu
通讯作者:
X. Xue;Wei Zhang;Jie Zhang;Bin Wu;Jianping Fan;Yao Lu