AI Paper Atlas

Research map / Video / Video segmentation and tracking

Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection

Giacomo D' Amicantonio, Snehashis Majhi, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond, Egor Bondarev

ICCV 2025 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Temporal Gaussian Splatting loss to the UR-DMU baseline (ablation)UR-DMU · UCF-CrimeAUC (%): 86.97 -> 87.84Improved
add class-specific expert models (ablation)GS-MoE · UCF-CrimeAUC (%): 87.84 -> 89.53Improved
add gate model combining expert scores with task-aware features (ablation)GS-MoE · UCF-CrimeAUC (%): 89.53 -> 91.58Improved
add TGS to the baseline on XD-Violence AUC (ablation)UR-DMU · XD-ViolenceAUC (%): 94.07 -> 94.13No clear effect
feed task-aware features into the gate model (ablation)GS-MoE gate · XD-ViolenceAP_A (%): 81.45 -> 85.74Improved
use class experts instead of K-means cluster experts (ablation)GS-MoE · UCF-CrimeAUC (%): 88.58 -> 91.58Improved
use gate model instead of soft-MoE (ablation)GS-MoE · UCF-CrimeAUC (%): 90.14 -> 91.58Improved
set peak prominence threshold to 0.2 rather than 0.1 or 0.3 (ablation)TGS · UCF-CrimeAUC (%): 90.34 / 90.75 -> 91.58No clear effect
mask a class expert at the gate (ablation)GS-MoE · UCF-Crime per-classclass-wise AUC (%): 86.37 -> 50.02 (Abuse)Hurt
use per-scene experts on UBnormal instead of cluster experts (ablation)GS-MoE · UBnormalAUC (%): 69.28 -> 65.95Hurt
add GS-MoE experts and gate over single UR-DMU modelUR-DMU · UCF-CrimeFPS: 110.09 -> 9.57Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy