Finding of Object Class in Visual Object Recognition
Finding of Object Class in Visual Object Recognition
批准号:
21800057
负责人:
HIDAKA Akinori
金额:
$1.71万
依托单位:
依托单位国家:
日本
项目类别:
Grant-in-Aid for Research Activity Start-up
财政年份:
2008
资助国家:
日本
项目状态:
已结题
起止时间:
2008 至 2010
中文摘要
在基于模式识别的视觉对象识别中,无监督学习仍然是一个重要的问题。在本研究中,我们尝试使用无监督方法从无标记视频序列中半自动生成训练样本。我们使用基于生长切割和模板匹配的目标跟踪方法进行样本提取。在实验中,我们证明了我们的方法可以在没有教师信号的情况下生成目标簇。
英文摘要
In visual object recognition based on pattern recognition, unsupervised learning is a still important problem. In this research, we try semi-automatic generating of training samples from non-labeled video sequence by using unsupervised approach. We use grow cut and template matching based object traking method for our sample extraction. In our experiments, we show that our approach can make the clusters of targets without teacher signals.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Study of dynamic attentional selection mechanisms in deep neural networks
-
批准号:16K16090
-
项目类别:Grant-in-Aid for Young Scientists (B)
-
资助金额:$2.5万
-
财政年份:2016
-
负责人:HIDAKA Akinori
-
依托单位:
海外基金