A single contrastive action encoder with diffusion-based motion augmentation performs few-shot human action anomaly detection on HumanAct12 with an average AUC of 86.9%, including three categories excluded from encoder training.
Madgan: Unsupervised medical anomaly detection gan us- ing multiple adjacent brain mri slice reconstruction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework
A single contrastive action encoder with diffusion-based motion augmentation performs few-shot human action anomaly detection on HumanAct12 with an average AUC of 86.9%, including three categories excluded from encoder training.