论文标题
动态手势检索：通过人类姿势序列搜索视频
Dynamic gesture retrieval: searching videos by human pose sequence
论文作者
论文摘要
静态人类姿势的数量有限，很难使用一个单个姿势作为线索来检索确切的视频。但是，以姿势序列或动态手势作为关键字，检索特定的视频变得更加可行。我们提出了一种新的方法，用于查询包含指定序列序列序列的视频，而先前的作品仅指定了一个静态姿势。所提出的方法从关键字手势视频和视频候选者中取得连续的3D人类姿势，然后将每个姿势的每个姿势转换为骨骼方向描述符，这些姿势描述了每个自然连接在明显的姿势中的方向。然后，应用时间金字塔滑动窗口，以查找指定的手势和视频候选者之间的匹配，这确保可以匹配具有不同持续时间的相同手势。
The number of static human poses is limited, it is hard to retrieve the exact videos using one single pose as the clue. However, with a pose sequence or a dynamic gesture as the keyword, retrieving specific videos becomes more feasible. We propose a novel method for querying videos containing a designated sequence of human poses, whereas previous works only designate a single static pose. The proposed method takes continuous 3d human poses from keyword gesture video and video candidates, then converts each pose in individual frames into bone direction descriptors, which describe the direction of each natural connection in articulated pose. A temporal pyramid sliding window is then applied to find matches between designated gesture and video candidates, which ensures that same gestures with different duration can be matched.
