图 书 馆
上下文感知显著性检测Context-Aware Saliency Detection |
|
| 课程网址: | http://videolectures.net/cvpr2010_zelnik_manor_casd/ |
| 主讲教师: | Lihi Zelnik-Manor |
| 开课单位: | 以色列理工学院 |
| 开课时间: | 2010-07-19 |
| 课程语种: | 英语 |
| 中文简介: |  我们提出了一种新型的显着性-上下文感知显着性-旨在检测代表场景的图像区域。此定义不同于以前的定义，后者的目标是识别固定点或检测主要物体。根据我们的显着性定义，我们提出了一种基于心理学文献中观察到的四个原理的检测算法。在两个应用程序中评估了所提出方法的好处，在这些应用程序中，主要对象的上下文与对象本身一样重要。在图像重新定向中，我们证明了使用显着性可以防止重要区域的变形。在总结中，我们显示出我们的显着性有助于生成紧凑，吸引人且内容丰富的摘要。 |
| 课程简介: | We propose a new type of saliency – context-aware saliency – which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting we demonstrate that using our saliency prevents distortions in the important regions. In summarization we show that our saliency helps to produce compact, appealing, and informative summaries. |
| 关 键 词: | 心理学; 固定点检测 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-03-25：zyk |
| 最后编审: | 2021-03-25：zyk |
| 阅读次数: | 120 |