3DSAL: An Efficient 3D-CNN Architecture for Video Saliency Prediction.
Yasser Abdelaziz Dahou DjilaliMohamed SayahKevin McGuinnessNoel E. O'ConnorPublished in: VISIGRAPP (4: VISAPP) (2020)
Keyphrases
- real time
- prediction accuracy
- cellular neural networks
- video data
- visual saliency
- management system
- video frames
- video streams
- prediction model
- multimedia
- video content
- prediction error
- saliency detection
- video database
- video clips
- polynomial neural networks
- video analysis
- saliency map
- video sequences
- video segmentation
- video surveillance
- scalable video coding
- multiscale
- video decoder
- neural network