CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
邱泽宇1,2; 方全1,2; 桑基韬1,2; 徐常胜1,2
Source Publication计算机学报
Other AbstractNowadays, the amount of online images has grown explosively. This triggers the development of effective image understanding techniques. As a key technique, image annotation attracts broad attention. Most existing work learns models on the whole image for annotation task. However, these methods ignore the relationship between regions inside an image and the tag co-occurrence relationships, which essentially limits the performance of image annotation. To Tackle this issue, we propose a novel scheme that aims to exploit the region and tag co-occoccrence context for image annotation. First, we use the support vector machines (SVMs) trained on object categories to identify known and unknown regions. Second, spatial region context descriptor based clustering is used to annotate the unknown regions. Finally, two instantiation models, random walka and conditional randomfield (CRF),  are explored to refine the aggregated region tags for image annotation by utilizing tag co-occurrence relationship. We conduct experiments on a subset 0f NUS-WIDE. The results have demonstrated the effectiveness of our image annotation method.
Keyword图像标注 上下文信息 随机游走 条件随机场
Citation statistics
Document Type期刊论文
Recommended Citation
GB/T 7714
邱泽宇,方全,桑基韬,等. 基于区域上下文感知的图像标注[J]. 计算机学报,2014,37(6):1390-1397.
APA 邱泽宇,方全,桑基韬,&徐常胜.(2014).基于区域上下文感知的图像标注.计算机学报,37(6),1390-1397.
MLA 邱泽宇,et al."基于区域上下文感知的图像标注".计算机学报 37.6(2014):1390-1397.
Files in This Item: Download All
File Name/Size DocType Version Access License
qzy-2014615155923.pd(804KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[邱泽宇]'s Articles
[方全]'s Articles
[桑基韬]'s Articles
Baidu academic
Similar articles in Baidu academic
[邱泽宇]'s Articles
[方全]'s Articles
[桑基韬]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[邱泽宇]'s Articles
[方全]'s Articles
[桑基韬]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: qzy-2014615155923.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.