SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning.
Kevin LinLinjie LiChung-Ching LinFaisal AhmedZhe GanZicheng LiuYumao LuLijuan WangPublished in: CVPR (2022)
Keyphrases
- end to end
- scalable video
- video data
- admission control
- video sequences
- ad hoc networks
- congestion control
- multimedia
- multipath
- video content
- digital video
- real time
- video streams
- content delivery
- wireless ad hoc networks
- application layer
- rate allocation
- high bandwidth
- video frames
- internet protocol
- key frames
- multimedia data
- response time
- transport protocol