arrow
返回

Automatic image annotation by combining generative and discriminant models

delete2017-05-01
delete10
PRE
AI
P
Ping Ji *
X
Xianhe Gao
X
Xueyou Hu
DOI:10.1016/j.neucom.2016.09.108delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Generative model based image annotation methods have achieved good annotation performance. However, due to the problem of semantic gap, these methods always suffer from the images with similar visual features but different semantics. It seems promising to separate these images from semantic relevant ones by using discriminant models, since they have shown excellent generalization performance. Motivated to gain the benefits of both generative and discriminative approaches, in this paper, we propose a novel image annotation approach which combine the generative and discriminative models through local discriminant topics in the neighborhood of the unlabeled image. Singular Value Decomposition(SVD) is applied to group the images of the neighborhood into different topics according to their semantic labels. The semantic relevant images and the irrelevant ones are always assigned into different topics. By exploiting the discriminant information between different topics, Support Vector Machine(SVM) is applied to classify the unlabeled image into the relevant topic, from which the more accurate annotation will be obtained by reducing the bad influence of irrelevant images. The experiments on the ECCV 2002 [3] and NUS-WIDE [34] benchmark show that our method outperforms state-of-the-art annotation models.
Keyword:
Image annotation
Multimedia
Content Analysis
Discriminant model
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

H
hefei university
学者数:
2.3K
论文数: 1.3K
被引数: 20
引用论文

引用论文

Measuring Organ-Specific Translation Elongation Rate in Mice
err2021-03-26
err0
errOAAI
errMaxim V. Gerashchenko; Vadim N. Gladyshev
err分享
err收藏
The Dependability of Behavioral Measurements: Theory of Generalizability for Scores and Profiles
err1974-01-01
err0
PREAI
errPhilip R. Merrifield; Lee J. Cronbach; Goldine C. Gleser; Harinder Nanda; Nageswari Rajaratnam
err分享
err收藏
Role of Thrombin in Central Nervous System Injury and Disease凝血酶在中枢神经系统损伤和疾病中的作用
err2021-04-12
err0
errOAAI
errNathan A. Shlobin; Meirav Har-Even; Ze’ev Itsekson-Hayosh; Sagi Harnof; Chaim G. Pick
err分享
err收藏
学者 查看更多内容