Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning.
Sangdoo YunJongwon ChoiYoungjoon YooKimin YunJin Young ChoiPublished in: CVPR (2017)
Keyphrases
- visual tracking
- reinforcement learning
- particle filter
- appearance model
- particle filtering
- video sequences
- mean shift
- state space
- action selection
- object tracking
- robust visual tracking
- appearance modeling
- hand tracking
- data association
- state estimation
- real time tracking
- action space
- model based tracking
- partial occlusion
- multi target tracking
- multiple targets
- multi target
- learning algorithm
- robust tracking
- optimal policy
- model free
- markov decision processes
- appearance variations
- object appearance
- human computer interaction
- feature space
- face recognition
- computer vision
- machine learning
- robust object tracking
- articulated structures
- abrupt motion