.png){kind=icon}
返回
Learning Visual Contexts for Image Annotation From Flickr Groups
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2010.2101051.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present an extension of automatic image annotation that takes the context of a picture into account. Our core assumption is that users do not only provide individual images to be tagged, but group their pictures into batches (e. g., all snapshots taken over the same holiday trip), whereas the images within a batch are likely to have a common style. These batches are matched with categories learned from Flickr groups, and an accurate context-specific annotation is performed. In quantitative experiments, we demonstrate that Flickr groups, with their user-driven categorization and their rich group space, provide an excellent basis for learning context categories. Our approach-which can be integrated with virtually any annotation model-is demonstrated to give significant improvements of above 100%, compared to standard annotations of individual images.
Keyword:
Content-based image retrieval
context
image annotation
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
分享收藏The future of imaging: developing the tools for monitoring response to therapy in oncology: the 2009 Sir James MacKenzie Davidson Memorial lecture影像学的未来: 开发监测肿瘤学治疗反应的工具: 2009詹姆斯·麦肯齐·戴维森爵士纪念讲座
OAAI
OAAI分享收藏Tissue persistence and vaccine efficacy of tricarboxylic acid cycle and one-carbon metabolism mutant strains of Edwardsiella ictaluri.png)
Vaccine
VaccineIF0
PREAI
分享收藏
查看更多内容