Utilization of Deep Reinforcement Learning for saccadic-based object visual search.
Tomasz KornutaKamil RockiPublished in: CoRR (2016)
Keyphrases
- visual search
- eye movements
- reinforcement learning
- visual attention
- object recognition
- eye tracking
- visual environment
- d objects
- image retrieval
- active vision
- human computer interaction
- human computer interactions
- visual processing
- function approximation
- human vision
- state space
- moving objects
- eye tracker
- visual saliency
- visual search tasks
- target detection
- video retrieval
- model free
- markov decision processes
- eye tracking data
- pose estimation
- optimal policy
- digital libraries