An Active Action Proposal Method Based on Reinforcement Learning.
Tao ZhangNannan LiJingjia HuangJia-Xing ZhongGe LiPublished in: ICIP (2018)
Keyphrases
- synthetic data
- preprocessing
- reinforcement learning
- pairwise
- detection method
- high accuracy
- cost function
- model free
- classification method
- computationally efficient
- data sets
- significant improvement
- multiscale
- segmentation method
- denoising
- evolutionary algorithm
- clustering method
- artificial neural networks
- feature extraction
- decision trees