Recognizing human actions by fusing spatio-temporal appearance and motion descriptors.
Lamberto BallanMarco BertiniAlberto Del BimboLorenzo SeidenariGiuseppe SerraPublished in: ICIP (2009)
Keyphrases
- recognizing human actions
- action recognition
- action recognition in videos
- human actions
- spatio temporal
- recognition of human actions
- static images
- human motion
- space time
- bag of words
- image sequences
- bag of features
- activity recognition
- mid level
- computer vision
- spatial and temporal
- motion patterns
- visual features
- human activities
- appearance model
- dynamic textures
- appearance descriptors
- object motion
- input image
- feature extraction