An adaptive stacked denoising auto-encoder architecture for human action recognition | |
Wu, Dao Xi ; Pan, Wei ; Xie, Li Dong ; Huang, Chao Xi ; Pan W(潘伟) | |
2014 | |
关键词 | Classification (of information) Gesture recognition Image denoising Image recognition Learning systems Musculoskeletal system Network architecture |
英文摘要 | Conference Name:3rd International Conference on Information Technology and Management Innovation, ICITMI 2014. Conference Address: Shenzhen, China. Time:July 19, 2014 - July 20, 2014.; Chungbuk National University, Korea; Hong Kong Industrial Technology Research Centre; Inha University; Korea Maritime University; National Chengchi University, Taiwan; Queensland University of Technology; In this paper, a stacked denoising auto-encoder architecture method with adaptive learning rate for action recognition based on skeleton features is presented. Firstly a Kinect is used for capturing the skeleton images and extracting skeleton features. Then an adaptive stacked denoising auto-encoder with three hidden layers is constructed for unsupervised pre-training. So the trained weights are achieved. Finally, a neural network is constructed for action recognition, in which the trained weights are used as the initial value, covering the random value. Based on the experimental results from the Kinect dataset of human actions sampled in experiments, it is clear to see that our method possesses better robustness and accuracy, compared with the classic classification methods. ? 2014 Trans Tech Publications, Switzerland. |
语种 | 英语 |
出处 | http://dx.doi.org/10.4028/www.scientific.net/AMM.631-632.403 |
出版者 | Trans Tech Publications Ltd |
内容类型 | 其他 |
源URL | [http://dspace.xmu.edu.cn/handle/2288/86891] |
专题 | 信息技术-会议论文 |
推荐引用方式 GB/T 7714 | Wu, Dao Xi,Pan, Wei,Xie, Li Dong,et al. An adaptive stacked denoising auto-encoder architecture for human action recognition. 2014-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论