A3D: Adaptive 3D Networks for Video Action Recognition.
Sijie ZhuTaojiannan YangMatías MendietaChen ChenPublished in: CoRR (2020)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognizing human actions
- static images
- motion features
- recognition of human actions
- spatio temporal interest points
- activity recognition
- human activities
- human detection
- bag of words
- space time interest points
- computer vision
- mid level
- body parts
- video sequences
- view invariant
- video data
- recognizing actions
- motion capture data
- depth sensors
- atomic actions
- bag of features
- motion history images
- video clips
- video content
- action primitives
- key frames
- multimedia
- image retrieval
- space time
- spatio temporal
- video frames
- max margin
- video streams
- human pose
- event detection
- video retrieval
- independent component analysis