Shradha Mahadev Naik

Meta-learning guided weakly supervised video anomaly detection with dual memory and temporal attention

A meta-learning framework that combines Model-Agnostic Meta-Learning (MAML) with a dual-memory, transformer-based architecture and a dual memory backbone is proposed, providing a useful proof of concept where MAML has been shown to learn generalized anomaly and non-anomaly representations with a transformer based archi...