Automated Hand-Raising Detection in Classroom Videos: A View-Invariant and Occlusion-Robust Machine Learning Approach.
Babette BühlerRuikun HouEfe BozkirPatricia GoldbergPeter GerjetsUlrich TrautweinEnkelejda KasneciPublished in: AIED (2023)
Keyphrases
- view invariant
- action recognition
- machine learning
- human motion analysis
- multi view
- human actions
- single view
- human motion
- partial occlusion
- computer vision
- arbitrary viewpoint
- object detection
- spatio temporal
- viewpoint
- human detection
- cluttered background
- human pose
- active learning
- image classification
- space time
- image registration
- activity recognition
- learning process
- multiple viewpoints
- object recognition
- video sequences