Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow.
Kaihong WangKumar AkashTeruhisa MisuPublished in: CoRR (2022)
Keyphrases
- video sequences
- video streams
- video data
- active learning
- learning algorithm
- temporal information
- multimedia
- learning process
- video frames
- interactive video
- learning systems
- optical flow
- space time
- real time
- moving camera
- video clips
- key frames
- video database
- video analysis
- supervised learning
- multimedia data
- spatial and temporal
- image sequences
- e learning
- video content
- human actions
- video surveillance
- video retrieval
- human activities
- prior knowledge
- real world