期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 43, 期 2, 页码 660-672出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSMCB.2012.2214210
关键词
Attention; computer vision; machine learning; multiple-instance learning (MIL); saliency; saliency map
类别
资金
- National Basic Research Program of China (973 Program) [2011CB707104]
- National Natural Science Foundation of China [61172143, 61105012, 61072093, 611721412, 61125106, 91120302]
- Natural Science Foundation Research Project of Shaanxi Province [2012JM8024]
- 50th China Postdoctoral Science Foundation [2011M501487]
Saliency detection has been a hot topic in recent years. Its popularity is mainly because of its theoretical meaning for explaining human attention and applicable aims in segmentation, recognition, etc. Nevertheless, traditional algorithms are mostly based on unsupervised techniques, which have limited learning ability. The obtained saliency map is also inconsistent with many properties of human behavior. In order to overcome the challenges of inability and inconsistency, this paper presents a framework based on multiple-instance learning. Low-, mid-, and high-level features are incorporated in the detection procedure, and the learning ability enables it robust to noise. Experiments on a data set containing 1000 images demonstrate the effectiveness of the proposed framework. Its applicability is shown in the context of a seam carving application.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据