DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition.
Umar AsifDeval MehtaStefan von CavallarJianbin TangStefan HarrerPublished in: CoRR (2020)
Keyphrases
- action recognition
- motion features
- body parts
- human actions
- activity recognition
- bag of words
- computer vision
- action classification
- spatio temporal
- spatial information
- action detection
- human activities
- spatial relations
- human body
- facial expressions
- video data
- motion analysis
- face images
- object segmentation
- motion patterns
- optical flow
- three dimensional
- multimedia