图 书 馆
基于可转移字典对的跨视图动作识别Cross-View Action Recognition via a Transferable Dictionary Pair |
|
| 课程网址: | http://videolectures.net/bmvc2012_zheng_transferable_dictionary/ |
| 主讲教师: | Jingjing Zheng |
| 开课单位: | 马里兰大学 |
| 开课时间: | 2012-10-09 |
| 课程语种: | 英语 |
| 中文简介: |  区别性外观特征可有效识别固定视图中的动作，但对视点变化的概括性较差。我们提出了一种基于稀疏表示的视图不变动作识别方法，该方法使用可转移字典对。可转移的字典对由两个分别对应于源视图和目标视图的字典组成。这两个字典是从以不同视角拍摄的成对视频中同时学习的，目的是鼓励成对的每个视频都具有相同的稀疏表示。因此，可转移字典对在两个视图之间链接了对动作识别有用的功能。提出了无监督算法和有监督算法，用于学习可转移字典对。使用稀疏表示作为特征，可以将源视图中内置的分类器直接传输到目标视图。我们扩展了将从多个源视图学到的动作模型转移到一个目标视图的方法。我们在多视图IXMAS数据集上证明了我们的方法的有效性。我们的结果与最新技术水平相当。 |
| 课程简介: | Discriminative appearance features are effective for recognizing actions in a fixed view, but generalize poorly to changes in viewpoint. We present a method for viewinvariant action recognition based on sparse representations using a transferable dictionary pair. A transferable dictionary pair consists of two dictionaries that correspond to the source and target views respectively. The two dictionaries are learned simultaneously from pairs of videos taken at different views and aim to encourage each video in the pair to have the same sparse representation. Thus, the transferable dictionary pair links features between the two views that are useful for action recognition. Both unsupervised and supervised algorithms are presented for learning transferable dictionary pairs. Using the sparse representation as features, a classifier built in the source view can be directly transferred to the target view. We extend our approach to transferring an action model learned from multiple source views to one target view. We demonstrate the effectiveness of our approach on the multi-view IXMAS data set. Our results compare favorably to the the state of the art. |
| 关 键 词: | 监督算法; 数据集 |
| 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: | 74 |