BEVT: BERT Pretraining of Video Transformers.
Rui WangDongdong ChenZuxuan WuYinpeng ChenXiyang DaiMengchen LiuYu-Gang JiangLuowei ZhouLu YuanPublished in: CoRR (2021)
Keyphrases
- video data
- video content
- video sequences
- video analysis
- multimedia
- real time video
- space time
- video processing
- audio video
- video frames
- multimedia data
- video segmentation
- video clips
- video images
- real time
- event detection
- image processing
- video streams
- video surveillance
- image quality
- multiresolution
- case study
- learning algorithm