End-to-End Dense Video Captioning With Masked Transformer.
Luowei ZhouYingbo ZhouJason J. CorsoRichard SocherCaiming XiongPublished in: CVPR (2018)
Keyphrases
- end to end
- scalable video
- video sequences
- multimedia
- video data
- video frames
- real time
- admission control
- wireless ad hoc networks
- high bandwidth
- video streams
- video content
- digital video
- content delivery
- transport layer
- compressed video
- ad hoc networks
- multipath
- congestion control
- key frames
- rate allocation
- internet protocol
- multimedia data