End-to-end Generative Pretraining for Multimodal Video Captioning.
Paul Hongsuck SeoArsha NagraniAnurag ArnabCordelia SchmidPublished in: CoRR (2022)
Keyphrases
- end to end
- scalable video
- multimedia
- video data
- multipath
- admission control
- video frames
- video content
- congestion control
- wireless ad hoc networks
- video sequences
- ad hoc networks
- video streams
- high bandwidth
- internet protocol
- rate allocation
- application layer
- content delivery
- compressed video
- cross layer
- multimedia data