STRNet: Triple-stream Spatiotemporal Relation Network for Action Recognition.
Zhi-Wei XuXiao-Jun WuJosef KittlerPublished in: Int. J. Autom. Comput. (2021)
Keyphrases
- action recognition
- bag of words
- human actions
- activity recognition
- human detection
- recognition of human actions
- action classification
- spatial temporal
- body parts
- static images
- computer vision
- mid level
- view invariant
- data streams
- recognizing human actions
- video dataset
- spatio temporal
- spatial and temporal
- space time
- action recognition in videos
- independent subspace analysis
- action detection
- action primitives
- multi view
- recognizing actions