Divide and Conquer for Single-frame Temporal Action Localization.
Chen JuPeisen ZhaoSiheng ChenYa ZhangYanfeng WangQi TianPublished in: ICCV (2021)
Keyphrases
- single frame
- temporal redundancy
- super resolution
- multi frame
- image sequences
- video frames
- video sequences
- optical flow
- multiple frames
- spatio temporal
- low resolution
- temporal information
- high resolution video
- temporal coherence
- surveillance videos
- space time
- human actions
- motion estimation
- motion segmentation
- d objects
- motion analysis
- multimedia
- high resolution