Learning Temporally and Semantically Consistent Unpaired Video-to-Video Translation through Pseudo-Supervision from Synthetic Optical Flow.
Kaihong WangKumar AkashTeruhisa MisuPublished in: AAAI (2022)
Keyphrases
- video data
- video sequences
- optical flow
- interactive video
- real time
- video content
- video streams
- learning algorithm
- moving camera
- video clips
- spatio temporal
- learning systems
- video frames
- learning tasks
- digital video
- video surveillance
- supervised learning
- learning process
- reinforcement learning
- optical flow computation
- video retrieval
- prior knowledge
- active learning
- video analysis
- video database
- motion features
- space time
- spatio temporally