Sparse Coding on Local Spatial-Temporal Volumes for Human Action Recognition.
Yan ZhuXu ZhaoYun FuYuncai LiuPublished in: ACCV (2) (2010)
Keyphrases
- spatial temporal
- sparse coding
- action recognition
- human actions
- dictionary learning
- natural images
- sparse representation
- linear combination
- image classification
- unsupervised learning
- visual words
- bag of words
- generative model
- image representation
- activity recognition
- spatio temporal
- feature space
- temporal information
- spatial and temporal
- video shots
- computer vision
- three dimensional
- high dimensional
- space time
- image patches
- video sequences
- multiscale
- higher order
- signal processing
- spatial information
- active learning
- human activities
- learning algorithm
- face recognition
- dimensionality reduction