Dual attentional transformer for video visual relation prediction.
Mingcheng QuGanlin DengDonglin DiJianxun CuiTonghua SuPublished in: Neurocomputing (2023)
Keyphrases
- visual data
- visual cues
- prediction accuracy
- visual search
- selective attention
- visual analysis
- video sequences
- video content
- video data
- video frames
- human vision
- video database
- video streams
- visual information
- real time
- video clips
- prediction model
- video search
- digital video
- visual concepts
- video indexing and retrieval
- video retrieval
- prediction algorithm
- visual field
- fuzzy logic
- low level
- multimedia
- content based video retrieval
- event recognition
- scalable video coding
- prediction error
- video shots
- cognitive processes
- video analysis
- visual attention
- fault diagnosis
- space time
- visual features
- computer vision
- neural network
- focus of attention
- news video
- key frames