Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks
文献类型：会议论文
| 作者 | Wang Hongsong(王洪松)1,2,3,4 ; Wang Liang(王亮)1,2,3,4; Liang Wang
|
| 出版日期 | 2017 |
| 会议日期 | July 22 - July 25 2017 |
| 会议地点 | Honolulu, Hawai |
| 关键词 | Action Recognition Temporal Dynamics Spatial Configurations |
| 英文摘要 | Recently, skeleton based action recognition gains more popularity due to cost-effective depth sensors coupled with real-time skeleton estimation algorithms. Traditional approaches based on handcrafted features are limited to represent the complexity of motion patterns. Recent methods that use Recurrent Neural Networks (RNN) to handle raw skeletons only focus on the contextual dependency in the temporal domain and neglect the spatial configurations of articulated skeletons. In this paper, we propose a novel two-stream RNN architecture to model both temporal dynamics and spatial configurations for skeleton based action recognition. We explore two different structures for the temporal stream: stacked RNN and hierarchical RNN. Hierarchical RNN is designed according to human body kinematics. We also propose two effective methods to model the spatial structure by converting the spatial graph into a sequence of joints. To improve generalization of our model, we further exploit 3D transformation based data augmentation techniques including rotation and scaling transformation to transform the 3D coordinates of skeletons during training. Experiments on 3D action recognition benchmark datasets show that our method brings a considerable improvement for a variety of actions, i.e., generic actions, interaction activities and gestures. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/19624]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Liang Wang |
| 作者单位 | 1.Center for Research on Intelligent Perception and Computing (CRIPAC) 2.National Laboratory of Pattern Recognition (NLPR) 3.Institute of Automation, Chinese Academy of Sciences (CASIA) 4.University of Chinese Academy of Sciences (UCAS) |
| 推荐引用方式 GB/T 7714 | Wang Hongsong,Wang Liang,Liang Wang. Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks[C]. 见:. Honolulu, Hawai. July 22 - July 25 2017. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。