Multiview Transformers for Video Recognition.
Shen YanXuehan XiongAnurag ArnabZhichao LuMi ZhangChen SunCordelia SchmidPublished in: CoRR (2022)
Keyphrases
- recognition rate
- recognition accuracy
- human activities
- video data
- video sequences
- real time
- object recognition
- activity detection
- video content
- feature extraction
- video streams
- depth video
- recognition process
- pattern recognition
- automatic recognition
- spatial and temporal
- recognition algorithm
- video database
- video analysis
- multimedia
- video frames
- video clips
- video retrieval
- image recognition
- multiple views
- video shots
- visual recognition
- action recognition
- human computer interaction
- video processing
- online video
- facial expressions
- face recognition
- video based face recognition