AI Paper Atlas

Research map / Video / Video segmentation and tracking

CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection

MYOUNG-CHUL KIM, Junhee Lee, ChaeBeen Bang, MyeongAh Cho

ECCV 2026 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 0 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
use all three clues (Action, Environment, Object) instead of two (ablation)CLUE-VAD · UCF-CrimeAUC (%): 86.89 -> 88.34Improved
use all three clues instead of a single clue (ablation)CLUE-VAD · UCF-CrimeAUC (%): 85.82 -> 88.34Improved
category-aware CLUE weighting instead of self-attention fusion (ablation)CLUE-VAD Detective module · UCF-CrimeAUC (%): 86.89 -> 88.34Improved
category-aware CLUE weighting instead of graph-based fusion (ablation)CLUE-VAD Detective module · UCF-CrimeAUC (%): 86.13 -> 88.34Improved
category-aware CLUE weighting instead of pairwise inter-CLUE fusion (ablation)CLUE-VAD Detective module · UCF-CrimeAUC (%): 87.46 -> 88.34Improved
add visual features to text-only CLUE model (ablation)CLUE-VAD · UCF-CrimeAUC (%): 88.34 -> 89.47Improved
add visual features to text-only CLUE model (ablation)CLUE-VAD · XD-ViolenceAP (%): 87.77 -> 88.24Improved
add textual CLUE features to visual-only model (ablation)CLUE-VAD · UCF-CrimeAUC (%): 87.46 -> 89.47Improved
add textual CLUE features to visual-only model (ablation)CLUE-VAD · XD-ViolenceAP (%): 86.35 -> 88.24Improved
ground InternVL2-2B explanations with CLUE tokens (2B vs 8B InternVL2)InternVL2 · UCFA anomaly explanation generationBLEU-4 / CIDEr: BLEU-4 0.0339 -> 0.0739; CIDEr 0.0713 -> 0.0423Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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