图 书 馆
一种用于动作识别的镜头相似度量学习One Shot Similarity Metric Learning for Action Recognition |
|
| 课程网址: | http://videolectures.net/simbad2011_kliper_gross_recognition/ |
| 主讲教师: | Orit Kliper-Gross |
| 开课单位: | 魏茨曼科学研究所 |
| 开课时间: | 2011-10-17 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The One-Shot-Similarity (OSS) is a framework for classifier-based similarity functions. It is based on the use of background samples and was shown to excel in tasks ranging from face recognition to document analysis. However, we found that its performance depends on the ability to effectively learn the underlying classifiers, which in turn depends on the underlying metric. In this work we present a metric learning technique that is geared toward improved OSS performance. We test the proposed technique using the recently presented ASLAN action similarity labeling benchmark. Enhanced, state of the art performance is obtained, and the method compares favorably to leading similarity learning techniques. |
| 关 键 词: | 计算机科学; 机器学习; 监督学习 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-12：yumf |
| 阅读次数: | 46 |