Unsupervised Domain Adaptation for Video Transformers in Action Recognition.
Victor G. Turrisi da CostaGiacomo ZaraPaolo RotaThiago Oliveira-SantosNicu SebeVittorio MurinoElisa RicciPublished in: ICPR (2022)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- static images
- recognizing human actions
- recognition of human actions
- bag of words
- spatio temporal interest points
- motion features
- activity recognition
- human activities
- space time interest points
- human detection
- computer vision
- mid level
- video streams
- video sequences
- body parts
- video frames
- video clips
- recognizing actions
- motion history images
- bag of features
- human pose
- video data
- video content
- three dimensional
- depth sensors
- multimedia
- human activity recognition
- action primitives
- spatio temporal
- view invariant
- pattern search
- visual features
- space time
- visual words
- video analysis
- key frames