Local fusion networks with chained residual pooling for video action recognition.
Feixiang HeFayao LiuRui YaoGuosheng LinPublished in: Image Vis. Comput. (2019)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognition of human actions
- recognizing human actions
- bag of words
- human activities
- motion features
- static images
- spatio temporal interest points
- space time interest points
- human detection
- activity recognition
- computer vision
- motion history images
- mid level
- motion capture data
- body parts
- video sequences
- video data
- spatio temporal
- bag of features
- video streams
- video content
- video frames
- event recognition
- video surveillance
- multimedia
- human pose
- human motion
- view invariant
- atomic actions
- depth sensors
- visual features
- image sequences