What is the best way for extracting meaningful attributes from pictures?

详细信息    查看全文

• 作者：Liangchen Liu ; ^{l.liu9@uq.edu.au}Author Vitae ; Arnold Wiliem ^{a.wiliem@uq.edu.au}Author Vitae ; Shaokang Chen ^{shaokangchenuq@gmail.com}Author Vitae ; Brian C. Lovell ^{lovell@itee.uq.edu.au}Author Vitae
• 关键词：Visual attribute ; Meaningfulness metric ; Attribute discovering ; Semantic content
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：64
• 期：Complete
• 页码：314-326
• 全文大小：1828 K
• 卷排序：64

文摘

We proposed a metric to automatically measure visual attribute meaningfulness. The metric is based on subspace interpolation on a decision boundary manifold. Meaningfulness distance is computed via approximated distance on the manifold. An improved metric calibration method is developed based on the in-depth analysis. We present extensive experiments and analysis on four popular attribute datasets.