End-to-End Video Captioning With Multitask Reinforcement Learning.
Lijun LiBoqing GongPublished in: WACV (2019)
Keyphrases
- end to end
- multi task
- reinforcement learning
- scalable video
- multi task learning
- multitask learning
- transfer learning
- learning problems
- video data
- video content
- learning tasks
- multimedia
- congestion control
- admission control
- transport protocol
- video streams
- multi class
- video sequences
- multiple tasks
- feature selection
- real time
- decision trees
- learning algorithm
- video frames
- compressed video
- application layer
- key frames
- supervised learning
- information gain
- rate allocation
- machine learning