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.
Experiments on UCF-Crime and UBnormal show that CSI-VAD consistently improves over the direct holistic baseline and achieves competitive performance against existing methods, showing the advantage of structured context decomposition for training-free video anomaly detection.
Dongjun Kim, Changjae Oh, Andrea Cavallaro et al.· arXiv.org· 0 citations
This work proposes a novel Text-Driven Video Anomaly Detection (TD-VAD) approach, which utilizes video-like text descriptions with temporal characteristics generated by LLM to train a VAD model, without any reliance on target-domain anomaly data.
Shuang-Qing Zhang, Lei-Lei Ma, Zhao Wang et al.· 0 citations
Weakly supervised video anomaly detection (WSAD) aims to localise anomalous events in untrimmed videos using only video-level labels. Existing multiple instance learning (MIL) methods often suffer from poor generalisation to unseen anomaly types, unstable temporal attention, and limited adaptability when only a few labelled examples are available. To address these challenges, we propose a meta-learning framework that combines Model-Agnostic Meta-Learning (MAML) with a dual-memory, transformer-based architecture. The model incorporates a dual-branch temporal attention module that captures both long-range semantic dependencies and local temporal proximity, separate memory banks for normal and abnormal prototypes with gated inhibition, metric-learning constraints, and variational latent regularisation. MAML explicitly trains the model for rapid adaptation across heterogeneous anomaly distributions, forcing it to acquire task-invariant representations rather than memorising static training statistics. Extensive experiments on two standard benchmarks yield competitive frame-level AUC of 93.60% on XD-Violence and 86.10% on UCF-Crime. One of our main contributions is the demonstration of very good metrics for zero and few-shot cross dataset transfer experiments, using only a handful of weakly labelled videos. We thus provide a useful proof of concept where MAML has been shown to learn generalized anomaly and non-anomaly representations with a transformer based architecture and a dual memory backbone. A t-SNE analysis of the memory prototypes confirms that MAML produces well-separated normal and abnormal clusters, while without meta-learning the memory banks collapse into entangled representations. The model is also shown to be computationally efficient, confirming its practical value for real-world surveillance deployment.
Shradha Mahadev Naik, Suja Palaniswamy, Nicola Conci· Journal of King Saud Univers...· 0 citations
Video Anomaly Detection (VAD) aims to identify abnormal frames from discrete events within video sequences. Existing VAD methods suffer from heavy annotation burdens in fully-supervised paradigm, insensitivity to subtle anomalies in semi-supervised paradigm, and vulnerability to noise in weakly-supervised paradigm. To address these limitations, we propose a novel paradigm: Single-Frame supervised VAD (SF-VAD), which uses a single annotated abnormal frame per abnormal video. SF-VAD ensures annotation efficiency while offering precise anomaly reference, facilitating robust anomaly modeling, and enhancing the detection of subtle anomalies in complex visual contexts. To validate its effectiveness, we construct three SF-VAD benchmarks by manually re-annotating the ShanghaiTech, UCF-Crime, and XD-Violence datasets in a practical procedure. Further, we devise Frame-guided Progressive Learning (FPL), to generalize sparse frame supervision to event-level anomaly understanding. FPL first leverages evidential learning to estimate anomaly relevance guided by annotated frames. Then it extends anomaly supervision by mining discrete abnormal events based on anomaly relevance and feature similarity. Meanwhile, FPL decouples normal patterns by isolating distinct normal frames outside abnormal events, reducing false alarms. Extensive experiments show SF-VAD achieves state-of-the-art detection results while offering a favorable trade-off between performance and annotation cost. The benchmarks and code are available at https://github.com/Junxi-Chen/SF-VAD .
Junxi Chen, Liang Li, Yunbin Tu et al.· Neural Information Processin...· 4 citations
Weakly supervised video anomaly detection (WS-VAD) localizes anomalous events in untrimmed videos using only video-level annotations. While CLIP-based methods have advanced this task through vision–language alignment, widely adopted approaches construct text prototypes from short category-name prompts of at most five words, leaving the CLIP text encoder not fully exploited. We propose SETAS-VAD, which addresses this gap through a Category Semantic Alignment (CSA) loss function: for each anomaly category, a large language model generates multi-sentence descriptions covering complementary semantic aspects, encoded once offline into frozen prototype vectors. An InfoNCE contrastive objective pulls attention-weighted anomaly features toward ground-truth category prototypes at zero additional inference overhead (prototype generation and encoding are performed once offline as a preprocessing step, not at test time). Under fully reproducible conditions on UCF-Crime and XD-Violence, SETAS-VAD achieves state-of-the-art temporal localization (30.45% mAP on XD-Violence, 12.16% on UCF-Crime), with per-threshold gains increasing at stricter IoU values, indicating improved boundary precision rather than coarse detection sensitivity.
Video anomaly detection (VAD) is critical for automation systems and security surveillance. Recently, multimodal vision–language models (MLLMs) have attracted increasing attention due to their rich pre-trained knowledge and strong explainability. However, existing MLLM-based approaches struggle to adapt to real-world settings where anomaly definitions are complex: they either rely on the model’s built-in knowledge and mainly capture only generic anomalies, or require anomalous samples for supervised fine-tuning—which are often rare and may raise legal or privacy concerns. To address this challenge, we propose a Sparsity-Controllable Vision-Language Model (SCVLM) for scenario-related anomaly detection. SCVLM learns normality from unlabeled normal data by jointly reconstructing multimodal representations and summarizing textual descriptions, thus enabling anomalies to be detected as deviations from the learned normal patterns. We introduce a Sparsity-Controllable Memory Block (SCMB) to improve memory addressing mechanism for pretrained multimodal representations. During inference, anomalies are detected by fusing two modality-specific reconstruction-errors with an LLM-based textual anomaly scoring mechanism. Meanwhile, we fuse the interpretable cues from each detection branch to derive anomaly reasoning consistent with human commonsense. Extensive experiments on challenging benchmarks demonstrate that SCVLM achieves state-of-the-art detection performance. Our code is available at https://github.com/SCVLM/SCVLM
Jiangyun Chen, Yuanjie Dang, Peng Chen et al.· IEEE Transactions on Informa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
