图 书 馆
视频中时间连贯性的深度学习Deep Learning from Temporal Coherence in Video |
|
| 课程网址: | http://videolectures.net/icml09_collobert_dlt/ |
| 主讲教师: | Ronan Collobert |
| 开课单位: | NEC Laboratories America，Inc |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled video recordings. That is, two successive frames are likely to contain the same object or objects. This coherence is used as a supervisory signal over the unlabeled data, and is used to improve the performance on a supervised task of interest. We demonstrate the effectiveness of this method on some pose invariant object and face recognition tasks. |
| 关 键 词: | 深度架构; 顺序数据; 监督任务 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-12：chenjy |
| 最后编审: | 2022-12-12：chenjy |
| 阅读次数: | 22 |