D3D: Distilled 3D Networks for Video Action Recognition.
Jonathan C. StroudDavid A. RossChen SunJia DengRahul SukthankarPublished in: WACV (2020)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognizing human actions
- motion features
- recognition of human actions
- static images
- spatio temporal interest points
- human activities
- bag of words
- space time interest points
- computer vision
- activity recognition
- human detection
- video sequences
- video data
- body parts
- bag of features
- depth sensors
- view invariant
- motion history images
- multimedia
- recognizing actions
- mid level
- human motion
- video content
- pose estimation
- motion capture data
- video clips
- view invariant action recognition
- human activity recognition
- video shots
- action primitives
- spatio temporal