Human Action Recognition and Localization in Video Using Structured Learning of Local Space-Time Features.
Tuan Hue ThiJian ZhangLi ChengLi WangShinichi SatohPublished in: AVSS (2010)
Keyphrases
- space time
- human actions
- action recognition
- global features
- structured learning
- motion history images
- video sequences
- action classification
- spatial and temporal
- spatio temporal
- human activities
- dynamic scenes
- bag of words
- computer vision
- space time interest points
- activity recognition
- human motion
- motion patterns
- visual features
- conditional random fields
- image features
- low level
- video frames
- video clips
- support vector machine
- temporal resolution
- feature vectors
- training data
- feature extraction
- image sequences