Encoding spatio-temporal distribution by generalized VLAD for action recognition.
Biyun ShengYan YanChangyin SunPublished in: CCECE (2015)
Keyphrases
- action recognition
- human actions
- spatio temporal
- spatial temporal
- action recognition in videos
- spatio temporal interest points
- view invariant
- bag of words
- recognition of human actions
- computer vision
- human detection
- activity recognition
- action classification
- body parts
- image search
- recognizing human actions
- recognizing actions
- human activities
- depth sensors
- static images
- video dataset
- visual features
- human pose
- action primitives
- spatial and temporal
- independent subspace analysis
- depth cameras
- motion estimation
- space time
- image sequences
- three dimensional
- machine learning
- view invariant action recognition