SphereVAD performs training-free video anomaly detection by recasting anomaly discrimination as von Mises-Fisher likelihood-ratio geodesic inference on the unit hypersphere using intermediate MLLM features, with Frechet mean centering, holistic scene attention, and spherical geodesic pulling.
Intrinsic statistics on riemannian manifolds: Basic tools for geometric measurements
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper reviews theories, algorithms, and applications of geodesic centroidal Voronoi tessellations on manifold meshes, highlighting their use for efficient search and indexing in computer vision and graphics.
citing papers explorer
-
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
SphereVAD performs training-free video anomaly detection by recasting anomaly discrimination as von Mises-Fisher likelihood-ratio geodesic inference on the unit hypersphere using intermediate MLLM features, with Frechet mean centering, holistic scene attention, and spherical geodesic pulling.
-
Geodesic Centroidal Voronoi Tessellations: Theories, Algorithms and Applications
The paper reviews theories, algorithms, and applications of geodesic centroidal Voronoi tessellations on manifold meshes, highlighting their use for efficient search and indexing in computer vision and graphics.