AE-Net:Adjoint Enhancement Network for Efficient Action Recognition in Video Understanding.
Bin WangChunsheng LiuFaliang ChangWenqian WangNanjun LiPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- action detection
- video dataset
- recognizing human actions
- recognition of human actions
- bag of words
- activity recognition
- human activities
- body parts
- static images
- human detection
- spatio temporal interest points
- computer vision
- motion features
- multimedia
- mid level
- space time interest points
- video sequences
- video streams
- view invariant
- action primitives
- video images
- human motion
- human pose
- video data
- motion capture data
- human computer interaction
- video surveillance
- visual features
- depth sensors
- video content
- spatio temporal
- recognizing actions
- image retrieval