StNet: Local and Global Spatial-Temporal Modeling for Action Recognition.
Dongliang HeZhichao ZhouChuang GanFu LiXiao LiuYandong LiLimin WangShilei WenPublished in: CoRR (2018)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- activity recognition
- computer vision
- action classification
- human object interactions
- human activities
- spatial and temporal
- bag of features
- recognizing human actions
- recognizing actions
- machine learning
- video shots
- spatio temporal
- view invariant
- recognition of human actions
- spatial information
- temporal information
- multi modal
- object recognition
- three dimensional