AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition.
Yue MengRameswar PandaChung-Ching LinPrasanna SattigeriLeonid KarlinskyKate SaenkoAude OlivaRogério FerisPublished in: CoRR (2021)
Keyphrases
- action recognition
- spatial temporal
- computer vision
- human detection
- bag of words
- activity recognition
- action classification
- human actions
- recognizing human actions
- motion history images
- independent subspace analysis
- body parts
- spatial and temporal
- recognizing actions
- static images
- video dataset
- recognition of human actions
- view invariant
- bag of features
- depth cameras
- temporal reasoning
- wireless sensor networks
- object recognition
- image sequences