This work proposes SVLA, a novel π -adaptive strategy to dynamically estimate shot-level anomaly density, replacing rigid selection with calibrated supervision, and employs a shot-conditioned temporal encoder to respect video hierarchy and adopt a dual-path contextual adapter to resolve semantic ambiguity.
Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vision-language models enable training-free inference, existing approaches mostly rely on holistic inference over sampled video and may miss context-specific anomaly cues. In this paper, we present CSI-VAD, a training-free video anomaly detector that identifies abnormal events across diverse contexts. The key idea is to decompose each video into three distinct contexts (environment, objects, time) and perform context-specific inference in separate branches. Because we ground anomaly judgments solely in context-specific visual cues, we do not require predefined text prompts describing abnormal events or dataset-specific tuning. 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.· 0 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) 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.· Advances in Neural Informati...· 4 citations
Zero-shot anomaly detection (ZSAD) aims to detect and localize anomalies in unseen categories without access to target-specific training data. Although recent CLIP-based methods have demonstrated promising generalization through vision-language alignment, they remain limited in capturing diverse anomaly semantics and subtle local variations. To address these limitations, we propose VFAD, a unified framework that combines variational semantic prompting with frequency-adaptive representation learning. Specifically, we introduce a Variational Semantic Prompt Extractor (VSPE), which adaptively aggregates anomaly-relevant local semantics from dense patch tokens and regularizes them through a variational information bottleneck, thereby incorporating fine-grained visual cues and enabling more precise cross-modal alignment. Furthermore, we develop a Frequency-Adaptive Representation Aggregation (FARA) module that leverages wavelet-based frequency decomposition and frequency-specific expert aggregation to enhance anomaly-discriminative visual representations. By jointly strengthening semantic guidance and visual representation learning, VFAD improves both anomaly discrimination and fine-grained localization. Extensive experiments on 13 industrial and medical benchmarks demonstrate that VFAD consistently outperforms existing state-of-the-art ZSAD methods across diverse anomaly scenarios. The code will be publicly available upon publication.
This work proposes Self-SiMS, a self-similarity-based Moment Proposal and Scoring that exploits intrinsic relationships within videos, enabling robust span generation and scoring and introduces a query-aware MLLM-based reasoning stage to further sharpen alignment between text and video.
Jihyun Lee, Cheol-Ho Cho, Woojin Jun et al.· 0 citations
Weakly supervised video anomaly detection (WSVAD) is important in intelligent surveillance. Existing methods often overemphasize salient abnormal segments, overlook subtle clues, and model temporal dependencies ineffectively. To address these issues, we propose TASG-VAD, an efficient anomaly detection framework. The proposed method is developed along two main directions: dual-scale temporal modeling and subtle anomaly discovery. Specifically, Temporal Variation Attention (TVA) amplifies anomaly related dynamic changes through second-order temporal differences while suppressing interference from static backgrounds. In addition, the Dual-Scale Temporal Encoder (DSTE) combines a dual-branch structure, a parameter-free attention mechanism, and dual-scale temporal convolutions to simultaneously capture local fine-grained fluctuations and long range global dependencies. Furthermore, to alleviate the model’s reliance on dominant anomalous segments, TASG-VAD introduces an Adaptive Saliency Guidance (ASG) strategy, which performs intra-video saliency ranking and dynamic masking to guide the model toward overlooked subtle anomalies. Experimental results show that TASG-VAD achieves AUCs of 88.21% and 98.38% on UCF-Crime and ShanghaiTech, respectively, and an AP of 84.60% on XD-Violence. With only about 1.7M parameters, it maintains high accuracy and excellent inference efficiency, and significantly outperforms existing methods.
Lihu Pan, Mingkai Hu, Linliang Zhang et al.· International journal of pat...· 0 citations