Spatio-temporal adaptive convolution and bidirectional motion difference fusion for video action recognition.
Linxi LiMingwei TangZhendong YangJie HuMingfeng ZhaoPublished in: Expert Syst. Appl. (2024)
Keyphrases
- action recognition
- human actions
- recognition of human actions
- spatio temporal
- action recognition in videos
- recognizing human actions
- spatio temporal interest points
- motion features
- spatial temporal
- space time
- static images
- human movements
- view invariant
- action classification
- human motion
- spatial and temporal
- motion recognition
- motion history images
- activity recognition
- motion capture data
- computer vision
- motion patterns
- image sequences
- action detection
- mid level
- bag of words
- video dataset
- action primitives
- recognizing actions
- human activities
- human detection
- body parts
- bag of features
- human activity recognition
- temporal structure
- human pose
- moving objects
- video sequences
- space time interest points
- dynamic scenes
- machine learning
- motion capture
- video content
- camera motion
- visual features
- multimedia