An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning.
Xinhao MeiQiushi HuangXubo LiuGengyun ChenJingqian WuYusong WuJinzheng ZhaoShengchen LiTom KoH. Lilian TangXi ShaoMark D. PlumbleyWenwu WangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- video codec
- decoding process
- distributed video coding
- transfer learning
- low complexity
- error control
- successive approximation
- wyner ziv
- noisy channel
- video coding
- wyner ziv video coding
- video coding scheme
- distributed source coding
- rate distortion
- mpeg avc
- multimedia
- function approximation
- motion compensated prediction
- turbo codes
- state space
- error resilience
- bit rate
- motion estimation
- video encoder
- knowledge transfer
- low bit rate
- rate allocation
- markov decision processes
- transform domain
- temporal correlation
- pixel domain
- rate distortion optimized
- visual information
- audio visual
- machine learning
- video transcoding
- bit budget
- decoding algorithm
- video coder
- video quality
- inter frame
- optimal policy
- video signals
- error correction
- motion compensation
- image compression
- enhancement layer
- error propagation
- video transmission
- compressed video
- compressive sensing
- error concealment
- motion compensated