Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection.
Mohammadamin BarekatainMiquel MartíHsueh-Fu ShihSamuel MurrayKotaro NakayamaYutaka MatsuoHelmut PrendingerPublished in: CVPR Workshops (2017)
Keyphrases
- action detection
- action recognition
- video dataset
- human actions
- action classification
- human activities
- static images
- activity recognition
- bag of words
- computer vision
- object detection
- pattern search
- body parts
- human pose
- motion features
- video database
- human activity recognition
- video data
- multi modal
- atomic actions
- feature space