# MuST-VAD: Mutual Structured Learning for Video Anomaly Detection

arXiv: https://arxiv.org/abs/2608.06913 · HTML: https://mlsanity.com/paper/2608.06913/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly](https://mlsanity.com/paper/2405.00181/) (2024)
- [Delving into CLIP latent space for Video Anomaly Recognition](https://mlsanity.com/paper/2310.02835/) (2023)
- [Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment](https://mlsanity.com/paper/2511.10334/) (2025)

## Built on by (most cited first, 1 of 1)

- [Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis](https://mlsanity.com/paper/2610.16324/) (2026)

## Abstract (arXiv)

In this paper, we propose MuST-VAD, a mutual structured learning framework for weakly supervised video anomaly detection (VAD) in which an anomaly detector and a large vision-language model (LVLM) exchange their acquired knowledge. Detectors in weakly supervised VAD learn anomaly scores from features extracted by a fixed, task-agnostic backbone. These fixed features bound the achievable detection accuracy. Recent methods therefore transfer LVLM semantics into the detector as richer features. However, this transfer is one-way: what the detector learns about the target videos never returns to the LVLM. MuST-VAD extends the one-way transfer into a bidirectional learning loop. In this loop, the latest detector predictions supervise the LVLM adaptation, and the adapted LVLM returns updated representations that retrain the detector; the two models alternate these updates over small video groups. Both models train on detector-selected key clips, while confidence weighting and annotation-anchored question answering keep the exchanged supervision reliable. On UCF-Crime, our mutual learning improves the one-pass transfer baseline from 88.15% to 88.63% AUROC and from 37.25% to 42.46% average precision (AP), outperforming the state-of-the-art method in AP by 4.13 points.