Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors | |
Hou, Yuqing | |
2015 | |
关键词 | RETRIEVAL COMPLETION RECOGNITION ALGORITHM OBJECT |
英文摘要 | Tag-based image retrieval (TBIR) has drawn much attention in recent years due to the explosive amount of digital images and crowdsourcing tags. However, TBIR is still suffering from the incomplete and inaccurate tags provided by users, posing a great challenge for tag-based image management applications. In this work, we propose a novel method for image annotation, incorporating several priors: Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors. Highly representative CNN feature vectors are adopted to model the tag-visual correlation and narrow the semantic gap. And we extract word vectors for tags to measure similarity between tags in the semantic level, which is more accurate than traditional frequency-based or graph-based methods. We utilize the Accelerated Proximal Gradient (APG) method to solve our model efficiently. Extensive experiments conducted on multiple benchmark datasets demonstrate the effectiveness and robustness of the proposed method.; EI; CPCI-S(ISTP); houyuqing1988@gmail.com; 71-81; 9474 |
语种 | 英语 |
出处 | ADVANCES IN VISUAL COMPUTING, PT I (ISVC 2015) |
DOI标识 | 10.1007/978-3-319-27857-5_7 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/436886] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Hou, Yuqing. Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors. 2015-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论