Multi-attention deep reinforcement learning and re-ranking for vehicle re-identification.
Yu LiuJianbing ShenHaibo HePublished in: Neurocomputing (2020)
Keyphrases
- reinforcement learning
- function approximation
- real time
- ranking algorithm
- ranking functions
- multi agent
- learning process
- state space
- web search
- machine learning
- reinforcement learning algorithms
- temporal difference
- model free
- learning to rank
- visual attention
- dynamic programming
- learning algorithm
- ranked list
- link analysis
- video sequences
- feature selection
- deep learning
- electric vehicles