Fast Binary-Based Video Descriptors for Action Recognition.
Roberto LeyvaVictor SanchezChang-Tsun LiPublished in: DICTA (2016)
Keyphrases
- action recognition
- human actions
- action classification
- action recognition in videos
- video dataset
- bag of features
- spatial temporal
- action detection
- mid level features
- motion features
- recognition of human actions
- recognizing human actions
- static images
- human activities
- activity recognition
- human detection
- space time interest points
- bag of words
- video sequences
- computer vision
- mid level
- body parts
- view invariant
- low level descriptors
- recognizing actions
- feature vectors
- action primitives
- space time
- human pose
- video segments
- video data
- object recognition
- image sequences
- machine learning
- motion history images
- image retrieval
- atomic actions
- video clips
- view invariant action recognition
- temporal structure
- video frames
- shape descriptors
- video analysis
- image features
- visual features
- global features
- image descriptors
- human motion
- multimedia
- video surveillance