MSAHTA: Mixed Spatial Attention and Hierarchical Temporal Aggregation for Action Recognition.
Jinyuan FengDan YangYongxin GeXiaolei QinYida ChenYuangan WangPublished in: SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI (2019)
Keyphrases
- action recognition
- temporal aggregation
- spatial temporal
- spatio temporal
- human actions
- temporal databases
- activity recognition
- bag of words
- computer vision
- human detection
- spatial and temporal
- body parts
- recognition of human actions
- recognizing human actions
- action classification
- spatial data
- temporal data
- recognizing actions
- static images
- bag of features
- depth sensors
- view invariant
- human pose
- spatial information
- human activities
- space time
- action detection
- databases
- query optimization
- action recognition in videos