A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition.
Beidi ZhaoShuai LiYanbo GaoChuankun LiWanqing LiPublished in: Sensors (2020)
Keyphrases
- short term
- long term
- activity recognition
- spatial frequency
- feature extraction
- short term and long term
- human activity recognition
- long term memory
- load forecasting
- human activities
- action recognition
- forecasting model
- accelerometer data
- computer vision
- bayesian framework
- transfer learning
- frequency domain
- image data
- data points
- prior knowledge
- computational complexity