Indexed spatio-temporal appearance models for query-driven video action recognition.
Haomian ZhengZhu LiAggelos K. KatsaggelosJia YouPublished in: ICME (2011)
Keyphrases
- action recognition
- human actions
- appearance model
- spatio temporal interest points
- spatial temporal
- spatio temporal
- action classification
- recognition of human actions
- bag of words
- visual tracking
- action detection
- human detection
- human activities
- object tracking
- activity recognition
- view invariant
- action recognition in videos
- video sequences
- recognizing human actions
- motion patterns
- computer vision
- space time
- body parts
- particle filter
- bag of features
- object class
- space time interest points
- background subtraction
- object retrieval
- mid level
- human pose
- visual words
- keywords
- machine learning
- human motion
- appearance information
- human body
- face recognition