VidTr: Video Transformer Without Convolutions.
Xinyu LiYanyi ZhangChunhui LiuBing ShuaiYi ZhuBiagio BrattoliHao ChenIvan MarsicJoseph TighePublished in: CoRR (2021)
Keyphrases
- video sequences
- video data
- video content
- multimedia
- key frames
- video streams
- real time
- fuzzy logic
- video analysis
- space time
- fault diagnosis
- real time video
- video clips
- image processing
- human activities
- video summarization
- video frames
- video database
- video segmentation
- compressed video
- event recognition
- multimedia data
- video shots
- video surveillance
- fourier transform
- artificial intelligence
- neural network