Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training.
Saurabh SahuPalash GoyalPublished in: CoRR (2021)
Keyphrases
- temporal information
- spatial and temporal
- temporal consistency
- space time
- video sequences
- spatial temporal
- temporal structure
- temporal coherence
- video data
- temporal analysis
- video frames
- temporal correlation
- multimedia
- temporal relationships
- spatio temporal
- temporal reasoning
- temporal resolution
- temporal constraints
- temporal segmentation
- video streams
- video content
- training set
- temporal domain
- temporal data
- fuzzy logic
- real time
- multi agent
- temporal patterns
- training process
- video analysis
- supervised learning
- video clips
- key frames
- human activities
- temporal order
- temporal continuity
- video summarization
- video database
- power system
- training examples
- training samples
- feature vectors
- expert systems
- neural network