Modeling Video Activity with Dynamic Phrases and Its Application to Action Recognition in Tennis Videos.
Jonathan VainsteinJosé F. ManeraPablo NegriClaudio DelrieuxAna Gabriela MaguitmanPublished in: CIARP (2014)
Keyphrases
- action recognition
- human activities
- human actions
- video dataset
- action classification
- video database
- action detection
- motion history images
- spatio temporal interest points
- video data
- motion features
- activity recognition
- recognition of human actions
- human object interactions
- recognizing human actions
- space time interest points
- bag of words
- spatial temporal
- static images
- human detection
- video analysis
- human activity recognition
- video sequences
- view invariant
- video content
- ucf sports
- computer vision
- video frames
- recognizing actions
- body parts
- sports video
- action recognition in videos
- key frames
- human motion
- space time
- spatio temporal
- event recognition
- video segments
- video clips
- mid level
- dynamic textures
- bag of features
- keywords
- motion capture data
- complex events
- motion recognition
- feature vectors
- machine learning
- visual features
- sensor data
- video streams
- spatial and temporal
- event detection
- video images
- human pose