E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context.
Zizhang LiMengmeng WangHuaijin PiKechun XuJianbiao MeiYong LiuPublished in: ECCV (35) (2022)
Keyphrases
- temporal context
- video representation
- spatio temporal
- spatial context
- space time
- spatial and temporal
- spatial information
- dynamic textures
- contextual information
- spatial data
- video analysis
- video streams
- audio visual
- image sequences
- temporal information
- spatial relationships
- image regions
- visual vocabulary
- video sequences
- visual information
- text classification
- multiscale