Video saliency prediction using enhanced spatiotemporal alignment network.
Jin ChenHuihui SongKaihua ZhangBo LiuQingshan LiuPublished in: Pattern Recognit. (2021)
Keyphrases
- spatial and temporal
- space time
- prediction accuracy
- video sequences
- multimedia
- spatiotemporal features
- peer to peer
- network model
- multimedia data
- video clips
- complex networks
- real time
- computer networks
- video streams
- video frames
- video segmentation
- communication networks
- video surveillance
- dynamic textures
- network conditions
- video delivery
- moving objects
- elman network