AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition.
Yulin WangYang YueYuanze LinHaojun JiangZihang LaiVictor KulikovNikita OrlovHumphrey ShiGao HuangPublished in: CVPR (2022)
Keyphrases
- end to end
- dynamic networks
- scalable video
- network structure
- temporal correlation
- multimedia
- temporal evolution
- training set
- admission control
- video content
- video sequences
- network analysis
- video data
- ad hoc networks
- dynamic behavior
- supervised learning
- video streams
- spatial information
- network topology
- biological networks
- real time
- video frames
- rate allocation
- congestion control
- motion estimation
- transport layer
- video on demand