MAR: Masked Autoencoders for Efficient Action Recognition.
Zhiwu QingShiwei ZhangZiyuan HuangXiang WangYuehuan WangYiliang LvChangxin GaoNong SangPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- bag of words
- computer vision
- activity recognition
- human detection
- view invariant
- action classification
- spatial temporal
- bag of features
- recognition of human actions
- recognizing human actions
- mid level
- human pose
- body parts
- static images
- human activities
- human body
- action primitives
- three dimensional
- depth sensors
- object recognition
- recognizing actions