Computer vision applications for 3D scene understanding in underwater environments remain challenging due to the lack of high-quality 3D data and the inability of surface-trained models to generalize to underwater scenes. To address this challenge, an emerging trend is to employ generative models to close the data doma...
Joaquín Figueira, Camile Lendering, Manfred González-Hernández et al.· 0 citations
Frame-level area under the ROC curve (AUC) is the dominant evaluation metric for weakly supervised video anomaly detection (WSVAD). Its standard form measures whether an anomalous frame outranks a normal frame drawn from anywhere in the test set. We refer to this comparison as pooled AUC, since it aggregates frame pair...
SST-WSVADL is proposed, a sparse spatio-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization and is competitive with prior methods across benchmarks while enabling localization and patch-level auditability of scene bias, providing a reproducible foundation for interpretabili...
S. Abdulaziz, A. Al Abri, Giacomo D'Amicantonio et al.· 1 citation
ReFP-AD (Rectified Flow Preconditioning for Anomaly Detection), which learns a geometric reparameterization that maps high-dimensional embeddings into a well-conditioned latent space via an optimal transport (OT)-coupled rectified flow, enables stable persistent contrastive divergence with preconditioned Stochastic Gra...
Camile Lendering, Erkut Akdag, Joaquín Figueira et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
