Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling.
Rui WangZuxuan WuDongdong ChenYinpeng ChenXiyang DaiMengchen LiuLuowei ZhouLu YuanYu-Gang JiangPublished in: CoRR (2022)
Keyphrases
- spatial temporal
- action recognition
- video shots
- temporal information
- human actions
- spatial and temporal
- video frames
- spatio temporal
- video sequences
- video data
- multimedia
- video streams
- video retrieval
- video database
- object recognition
- human activities
- video content
- bag of words
- space time
- key frames
- information retrieval systems
- video analysis
- computer vision