期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 27, 期 7, 页码 3459-3471出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2818328
关键词
Spatio attention; temporal attention; action recognition; action detection; skeleton data
资金
- National Natural Science Foundation of China [61772043, 61672519]
- Microsoft Research Asia Fund [FY17-RES-THEME-013]
- CCF-Tencent Open Research Fund
Human action analytics has attracted a lot of attention for decades in computer vision. It is important to extract discriminative spatio-temporal features to model the spatial and temporal evolutions of different actions. In this paper, we propose a spatial and temporal attention model to explore the spatial and temporal discriminative features for human action recognition and detection from skeleton data. We build our networks based on the recurrent neural networks with long short-term memory units. The learned model is capable of selectively focusing on discriminative joints of skeletons within each input frame and paying different levels of attention to the outputs of different frames. To ensure effective training of the network for action recognition, we propose a regularized cross-entropy loss to drive the learning process and develop a joint training strategy accordingly. Moreover, based on temporal attention, we develop a method to generate the action temporal proposals for action detection. We evaluate the proposed method on the SBU Kinect Interaction data set, the NTU RGB + D data set, and the PKU-MMD data set, respectively. Experiment results demonstrate the effectiveness of our proposed model on both action recognition and action detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据