Holistic-Guided Disentangled Learning With Cross-Video Semantics Mining for Concurrent First-Person and Third-Person Activity Recognition.
Tianshan LiuRui ZhaoWenqi JiaKin-Man LamJun KongPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- activity recognition
- human activities
- daily activities
- human activity recognition
- activities of daily living
- learning algorithm
- sensory data
- learning process
- video sequences
- human actions
- visual surveillance
- reinforcement learning
- action recognition
- knowledge discovery
- event detection
- smart environments
- feature selection