MFI: Multi-range Feature Interchange for Video Action Recognition.
Sikai BaiQi WangXuelong LiPublished in: ICPR (2020)
Keyphrases
- action recognition
- spatio temporal interest points
- motion features
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- bag of words
- recognition of human actions
- recognizing human actions
- static images
- activity recognition
- mid level features
- human activities
- computer vision
- space time interest points
- mid level
- human detection
- body parts
- view invariant
- video sequences
- action recognition in videos
- action primitives
- depth sensors
- video data
- feature vectors
- three dimensional
- motion history images
- human pose
- bag of features
- space time
- image sequences
- global features
- human motion
- multimedia