Neural ranking for automatic image annotation
Neural ranking for automatic image annotation
复制标题
自动图像标注的神经排序
DOI：
10.1007/s11042-018-5973-x
复制
发表时间：
2018-04
影响因子：
3.6
通讯作者：
Hu Haiyang
中科院分区：
文献类型：
--
作者：
Zhang Weifeng;Hu Hua;Hu Haiyang
Automatic image annotation aims to predict labels for images according to their semantic contents and has become a research focus in computer vision, as it helps people to edit, retrieve and understand large image collections. In the last decades, researchers have proposed many approaches to solve this task and achieved remarkable performance on several standard image datasets. In this paper, we propose a novel learning to rank approach to address image auto-annotation problem. Unlike typical learning to rank algorithms for image auto-annotation which directly rank annotations for image, our approach consists of two phases. In the first phase, neural ranking models are trained to rank image’s semantic neighbors. Then nearest-neighbor based models propagate annotations from these semantic neighbors to the image. Thus our approach integrates learning to rank algorithms and nearest-neighbor based models, including TagProp and 2PKNN, and inherits their advantages. Experimental results show that our method achieves better or comparable performance compared with the state-of-the-art methods on four challenging benchmarks including Corel5K, ESP Games, IAPR TC-12 and NUS-WIDE.
登录
查看更多内容
影响因子：
19.5
作者：
Gong, Yunchao;Ke, Qifa;Lazebnik, Svetlana
通讯作者：
Lazebnik, Svetlana
MLRank：图像标注的多相关学习排名
影响因子：
8
作者：
Li, Zechao;Liu, Jing;Xu, Changsheng;Lu, Hanqing
通讯作者：
Lu, Hanqing
影响因子：
6
作者：
Gao Zan;Nie Weizhi;Liu Anan;Zhang Hua
通讯作者：
Zhang Hua
DOI：
10.5244/c.27.25
发表时间：
2013
期刊：
--
影响因子：
--
作者：
Yashaswi Verma-;C. V. Jawahar
通讯作者：
Yashaswi Verma-;C. V. Jawahar
DOI：
10.1109/cvpr.2004.171
发表时间：
2004-06
期刊：
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
影响因子：
--
作者：
Shaolei Feng;R. Manmatha;V. Lavrenko
通讯作者：
Shaolei Feng;R. Manmatha;V. Lavrenko