Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications.
Francesco SemeraroJon CarberryAngelo CangelosiPublished in: CoRR (2023)
Keyphrases
- activity recognition
- multi user
- deep learning
- human robot
- training data
- single user
- human robot interaction
- virtual environment
- unsupervised learning
- dialogue system
- virtual world
- human activities
- machine learning
- humanoid robot
- augmented reality
- action recognition
- multiple users
- action selection
- learning algorithm
- decision trees
- user interface
- data sets
- training set
- supervised learning
- prior knowledge
- mental models
- human users
- transfer learning
- semi supervised learning
- robotic systems
- weakly supervised
- virtual reality
- multi modal
- labeled data
- natural language
- collaborative activities
- computer vision