arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.04293cs.CV
收藏

基于人脸-物体交互的人脸空间动作识别

Face-space Action Recognition by Face-Object Interactions

Weizmann Institute of Science(魏茨曼科学研究所)

Amir Rosenfeld, Shimon Ullman

摘要:

近年来,由于人体姿态估计、对象识别和更强的特征表示的进步,静止图像中的动作识别已经有了重大的改进。然而,仍然有许多情况下,性能仍然远远低于人类。在本文中,我们通过明确地学习来解决这个问题,然后整合传递性动作的三个组成部分:(1)与动作相关的人体部位(2)被作用的物体(3)人与物体之间的特定互动形式。该过程使用过去未用于动作识别的类特定特征和关系,并且与大多数标准方法不同,该过程中固有地使用两个循环。我们专注于面部相关的行动(FRA),一个子集的行动,包括几个目前具有挑战性的类别。我们提出了一个平均相对改善52%的国家的最先进的。我们还公开了一个新的基准。

英文摘要:

Action recognition in still images has seen major improvement in recent years due to advances in human pose estimation, object recognition and stronger feature representations. However, there are still many cases in which performance remains far from that of humans. In this paper, we approach the problem by learning explicitly, and then integrating three components of transitive actions: (1) the human body part relevant to the action (2) the object being acted upon and (3) the specific form of interaction between the person and the object. The process uses class-specific features and relations not used in the past for action recognition and which use inherently two cycles in the process unlike most standard approaches. We focus on face-related actions (FRA), a subset of actions that includes several currently challenging categories. We present an average relative improvement of 52% over state-of-the art. We also make a new benchmark publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑