D3D: Distilled 3D Networks for Video Action Recognition.
Jonathan C. StroudDavid A. RossChen SunJia DengRahul SukthankarPublished in: CoRR (2018)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognition of human actions
- recognizing human actions
- motion features
- static images
- spatio temporal interest points
- space time interest points
- computer vision
- activity recognition
- human activities
- bag of words
- body parts
- video sequences
- human detection
- mid level
- recognizing actions
- human pose
- video data
- motion history images
- video content
- video analysis
- multimedia
- pose estimation
- depth sensors
- action primitives
- video scene
- spatio temporal
- view invariant
- space time
- video clips
- video surveillance
- temporal information