A Coarse to Fine Question Answering System based on Reinforcement Learning.
Yu WangHongxia JinPublished in: CoRR (2021)
Keyphrases
- coarse to fine
- reinforcement learning
- multiscale
- dynamic programming
- multiresolution
- object detection
- hierarchical segmentation
- question answering
- matching scheme
- image registration
- state space
- image pyramid
- hierarchical representation
- optical flow estimation
- supervised learning
- active shape model
- learning algorithm
- feature correspondences
- natural language
- scan line
- deformable contour
- multi view
- object recognition