Abstract | ||
---|---|---|
In computer vision area, extracting effective information from video data to realize automatic human action recognition has become one of the most active research points. In order to deal with the high dimensional challenge from massive amount of video data and extract effective features by feature self-learning model based on deep learning, a method based on a sparse long-short term memory (LSTM)auto-encoder and improved 3D convolution neural network (3D CNN)is proposed in this paper. We first construct a sparse LSTM auto-encoder to extract the key frames. And then, to extract lower dimensional features for approximating the upper limit of these features classification ability, the 3D CNN model is improved by combing with the feature engineering method, that is recursive feature elimination (RFE)algorithm. Finally, we extract high-level features by the improved 3D CNN for human action recognition. The experimental results on typical datasets UCF101 demonstrate that our algorithm has significant effect on data dimensionality reduction and outperforms some competing hand-craft feature and single feature methods. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/FSKD.2018.8686921 | 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) |
Keywords | Field | DocType |
human action recognition,sparse LSTM auto-encoder,Improved 3D CNN,RFE | Autoencoder,Pattern recognition,Convolutional neural network,Computer science,Action recognition,Feature engineering,Artificial intelligence,Data dimensionality reduction,Deep learning,Machine learning,Recursion | Conference |
ISBN | Citations | PageRank |
978-1-5386-8098-8 | 0 | 0.34 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Q. Fu | 1 | 16 | 3.51 |
Shiwei Ma | 2 | 136 | 21.79 |
Lina Liu | 3 | 6 | 3.11 |
Jinjin Liu | 4 | 0 | 0.34 |