Spatial-Temporal Fusion Convolutional Neural Network for Compressed Video Enhancement in HEVC.
Xiaoyu XuJian QianLi YuHongkui WangHao TaoShengju YuPublished in: DCC (2020)
Keyphrases
- spatial temporal
- compressed video
- convolutional neural network
- video codec
- face detection
- video quality
- video content
- video streams
- video shots
- spatio temporal
- spatial and temporal
- super resolution
- action recognition
- video frames
- data hiding
- macroblock
- bitstream
- compressed domain
- temporal information
- video compression
- image processing
- spatial information
- motion estimation
- motion compensated
- reference frame
- transform domain
- key frames
- rate distortion
- video sequences
- frame rate
- object detection
- video retrieval
- human actions
- computer vision
- visual features