MuAt-Va: Multi-Attention and Video-Auxiliary Network for Device-Free Action Recognition.
Biyun ShengChaorun SunFu XiaoLinqing GuiZhengxin GuoPublished in: IEEE Internet Things J. (2023)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- recognition of human actions
- activity recognition
- human detection
- static images
- human activities
- bag of words
- spatio temporal interest points
- space time interest points
- computer vision
- body parts
- motion features
- video sequences
- mid level
- video data
- view invariant
- machine learning
- view invariant action recognition
- wireless sensor networks
- event recognition
- human pose
- video surveillance
- video frames
- depth sensors
- space time
- video shots
- video streams
- motion history images
- human computer interaction
- optical flow
- multimedia