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