BAR - A Reinforcement Learning Agent for Bounding-Box Automated Refinement.
Morgane AyleJimmy TekliJulia El ZiniBoulos El AsmarMariette AwadPublished in: AAAI (2020)
Keyphrases
- bounding box
- learning agent
- reinforcement learning
- state space
- solving problems
- object segmentation
- learning algorithm
- object categories
- learning capabilities
- reinforcement learning algorithms
- learning tasks
- test images
- particle filtering
- object classes
- region of interest
- feature space
- target object
- search algorithm