SOAR: Scene-debiasing Open-set Action Recognition.
Yuanhao ZhaiZiyi LiuZhenyu WuYi WuChunluan ZhouDavid S. DoermannJunsong YuanGang HuaPublished in: CoRR (2023)
Keyphrases
- action recognition
- motion features
- static images
- human actions
- bag of words
- human detection
- activity recognition
- action classification
- d scene
- computer vision
- video sequences
- body parts
- recognition of human actions
- three dimensional
- dynamic scenes
- recognizing human actions
- bag of features
- view invariant
- image sequences
- human activities
- depth sensors
- human pose
- input image
- action recognition in videos
- recognizing actions
- action detection
- video dataset
- video images
- scene classification
- machine learning
- single image
- object recognition
- moving objects
- high resolution
- range data