TDViT: Temporal Dilated Video Transformer for Dense Video Tasks.
Guanxiong SunYang HuaGuosheng HuNeil RobertsonPublished in: CoRR (2024)
Keyphrases
- video sequences
- space time
- video content
- video data
- multimedia
- spatial and temporal
- real time
- temporal information
- real time video
- temporal coherence
- video analysis
- spatio temporal
- multimedia data
- temporal consistency
- spatial temporal
- spatio temporally
- temporal analysis
- neural network
- video images
- video database
- video streams
- image sequences
- dynamic scenes
- event recognition
- temporal correlation
- video clips
- key frames
- event detection
- temporal domain
- temporal order