图 书 馆
核密度主题模型:视觉主题没有视觉单词Kernel Density Topic Models: Visual Topics Without Visual Words |
|
| 课程网址: | http://videolectures.net/nipsworkshops2012_rematas_visual/ |
| 主讲教师: | Konstantinos Rematas |
| 开课单位: | 鲁汶大学 |
| 开课时间: | 2013-01-16 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The computer vision community has greatly benefited from transferring techniques originally developed in the document processing domain to the visual domain by means of discretizing the features space into visual words. This paper reinvestigates the necessity of this artificially discretization of the continuous space of visual features and consequently proposes an alternative formulation of the popular topic models that is based on kernel density estimates. Results indicate the benefits of our model in terms of decreased perplexity as well as improved performance on object discovery tasks. |
| 关 键 词: | 计算机视觉领域; 离散; 核密度估计 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-02：张荧(课程编辑志愿者) |
| 阅读次数: | 49 |