期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 20, 期 9, 页码 2330-2343出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2018.2802648
关键词
Action recognition; skeleton; geometric feature; LSTM; score fusion
资金
- National Key Research and Development Program of China [2017YFB0203001]
- National Natural Science Foundation of China [61572431]
- Zhejiang Natural Science Foundation [LZ17F020001]
- Key R&D Program of Zhejiang Province [2018C01006]
- ZJU
- Hikvision Research Institute
Recent skeleton-based action recognition approaches achieve great improvement by using recurrent neural network (RNN) models. Currently, these approaches build an end-to-end network from coordinates of joints to class categories and improve accuracy by extending RNN to spatial domains. First, while such well-designed models and optimization strategies explore relations between different parts directly from joint coordinates, we provide a simple universal spatial modeling method perpendicular to the RNN model enhancement. Specifically, according to the evolution of previous work, we select a set of simple geometric features, and then seperately feed each type of features to a three-layer LSTM framework. Second, we propose a multistream LSTM architecture with a new smoothed score fusion technique to learn classification from different geometric feature streams. Furthermore, we observe that the geometric relational features based on distances between joints and selected lines outperform other features and the fusion results achieve the state-of-the-art performance on four datasets. We also show the sparsity of input gate weights in the first LSTM layer trained by geometric features and demonstrate that utilizing joint-line distances as input require less data for training.
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