AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment

Wenti Yin, Huaxin Zhang, Xiang Wang, Yuqing Lu, Yicheng Zhang, Bingquan Gong, Jialong Zuo, Li Yu, Changxin Gao, Nong Sang

AAAI 2026 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 6 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 text Adapter to VadCLIP baseline (ablation)VadCLIP · XD-ViolenceAP / average mAP: 84.51 -> 85.00 AP; 24.70 -> 28.15 AVGImproved
add Self-Guided Normality Modeling on top of Adapter (ablation)VadCLIP + Adapter · XD-ViolenceAP / average mAP: 85.00 -> 85.94 AP; 28.15 -> 28.39 AVGImproved
add Decoupled Contrastive Semantic Alignment on top of Adapter (ablation)VadCLIP + Adapter · XD-ViolenceAP / average mAP: 85.00 -> 85.67 AP; 28.15 -> 28.25 AVGImproved
add both SG-NM and DCSA to Adapter model (full DSANet) (ablation)VadCLIP + Adapter · XD-ViolenceAP / average mAP: 85.00 -> 86.95 AP; 28.15 -> 28.87 AVGImproved
use Adapter text tuning instead of frozen text encoder (ablation)DSANet · XD-ViolenceAP: 81.57 -> 86.95Improved
use manual prompt instead of frozen class labels (ablation)DSANet text encoder · XD-ViolenceAP / average mAP: 81.57 -> 81.05 AP; 27.60 -> 28.05 AVGMixed
use learnable prompt instead of frozen class labels (ablation)DSANet text encoder · XD-ViolenceAP / average mAP: 81.57 -> 82.88 AP; 27.60 -> 28.26 AVGImproved
DSANet versus best prior method on fine-grained detectionDSANet · UCF-Crimeaverage mAP: 9.62 -> 13.01Improved
decoupled background prototype aligned to normal classDSANet vs VadCLIP · UCF-Crimebackground alignment accuracy: 87.63% -> 99.63%Improved

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