SDCNet: Video Prediction Using Spatially-Displaced Convolution.
Fitsum A. RedaGuilin LiuKevin J. ShihRobert KirbyJon BarkerDavid TarjanAndrew TaoBryan CatanzaroPublished in: CoRR (2018)
Keyphrases
- prediction accuracy
- multimedia
- image processing
- video sequences
- video data
- video streams
- video content
- real time
- video processing
- scalable video coding
- video frames
- prediction error
- prediction model
- spatio temporally
- real time video
- video analysis
- video retrieval
- event detection
- action recognition
- video search
- low resolution
- multiscale
- data sets