The paper investigates how weakly supervised video anomaly detectors, trained with only video‑level labels, are evaluated using frame‑level metrics such as Micro‑AUROC and AP. It shows that these metrics largely measure a detector’s ability to separate different videos rather than correctly ordering anomalous moments within a single video, a phenomenon termed temporal dilution. Experiments demonstrate that a detector can achieve high pooled scores even when it assigns the same score to every frame in a video, indicating that current evaluation practices may overstate temporal localization performance.
By Inpyo Song, Jangwon Lee
The paper introduces an adaptive temporal modeling framework for weakly supervised video anomaly detection that addresses the limitations of rigid Multiple Instance Learning approaches. It presents a Temporal Refinement Module using dynamic positional encoding and a learnable class token to capture long‑range dependencies, and an Event Segmentation Module that identifies event boundaries via temporal discontinuity analysis to produce discriminative event‑level representations. An adaptive similarity‑based fusion strategy replaces fixed top‑k heuristics, dynamically integrating snippet‑level and event‑level anomaly scores into video‑level predictions, and the method outperforms state‑of‑the‑art baselines on two benchmarks.
By Changyi Li, Yu Xiao
The paper investigates whether detailed articulated human pose provides more discriminative power than coarse spatial relationships for early violence detection. By fixing the downstream pipeline and comparing five interaction representations—including bounding‑box geometry, handcrafted pose analogues, enriched pose descriptors, and a learned joint encoder—the study finds that pose‑based representations do not outperform coarse geometry. When visual encoders are frozen and evaluated on larger datasets, person‑crop appearance and whole‑frame context outperform geometry, but cropping to interacting people offers no advantage over encoding the entire frame. The authors further demonstrate that pre‑onset frames contain source‑related artifacts (e.g., title cards, watermarks) that contribute significantly to discrimination, suggesting that benchmark performance may reflect these artifacts rather than true event evidence.
By Parishruthi Ganesh
Efficient Zero‑Shot Video Anomaly Detection via Signal‑Aware Adaptive Fusion (SAAF) introduces a framework that leverages dual‑signal adaptive sampling—delta and drift signals—to detect sudden and gradual anomalies without training data. It employs a threshold‑gated cascaded architecture that first applies lightweight frame‑level scoring before invoking costly video‑level analysis only when needed, and a signal‑aware weighted fusion mechanism that adapts score combination based on the triggering signal. Across four benchmarks, SAAF achieves state‑of‑the‑art accuracy on XD‑Violence, MSAD, and ShanghaiTech while delivering significant throughput improvements over prior zero‑shot methods.
By Khaled Waleed Dawoud, Muhammad Haris Khan
Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with the scale of real-world video...
Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries from target-domain annotations but require substantial in-domain data.
Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neglecting their spatial extent within frames. Yet, spatial localization is essential for interpretability and practical deployment in real-world settings.
MS2CAST is a semi‑supervised video anomaly detection framework that fuses multi‑scale cross‑attention between a vision transformer (MViTv2‑S) and a CNN (ConvNeXt‑T) for spatial encoding, and replaces optical flow with two interchangeable spatiotemporal modules—SwinLSTM and VMRNN—operating in latent space. The training objective combines L1 loss, Gradient Difference Loss, and Multi‑Scale SSIM to enforce pixel‑level accuracy, sharpness, and structural fidelity. Experiments on UCSD Ped2, CUHK Avenue, and ShanghaiTech show competitive ROC‑AUC scores while using less than 1 GB of GPU memory.
By Ali Safaei, Mohammad Kazemi
The paper proposes a lightweight federated multiple‑instance learning (MIL) framework that trains only a compact MIL scorer across distributed clients while using a frozen vision‑language model (VLM) to verify high‑scoring video segments post‑hoc. Two VLM feedback interfaces are explored: a parsed text‑generation interface and a logit‑based interface that derives a continuous anomaly score from next‑token Yes/No probabilities. Experiments on UCF‑Crime with InternVL3.5‑2B and Qwen3‑VL‑2B‑Instruct show that the logit interface consistently improves frame‑level AUC and AP over the MIL baseline without requiring temporal post‑processing, whereas the text‑generation interface is more sensitive to prompts, parsers, and model choice.
By S\'ebastien Thuau, Amira Gran, Siba Haidar, Rachid Chelouah
CoRE is a weakly supervised framework that learns fine-grained temporal and entity support for perceived risk in driving videos using only coarse video-level judgments. It first trains a video-level predictor, freezes it, and then uses structured interventions over candidate temporal regions or entity tracks to generate graded prediction-effect targets. These targets train a student model that can predict temporal and entity support directly from the original video, enabling fine-grained evidence localization without requiring detailed annotations.
By Kaiser Hamid, Can Cui, Nade Liang
arXiv:2610.28560v1 Announce Type: new
Abstract: Visual anomaly detection aims to detect abnormal objects, while anomaly samples are often scarce during model training. Assembling multiple pretrained...
By Shangquan Sun, Wenjun Luo, Xu He, Yoonsoo Lee, Shijian Lu
MoG-VLM is a motion‑guided vision‑language model designed for efficient video anomaly detection. It uses a lightweight motion signal, Temporal Gradient Magnitude, to perform content‑aware sampling and activates dense multi‑frame VLM reasoning only around frames with high anomaly likelihood via a hierarchical dual‑stream design. The method achieves state‑of‑the‑art AUC‑ROC scores on four benchmarks and delivers a 1.31× inference speedup on XD‑Violence.
By Khaled Waleed Dawoud, Muhammad Zaigham Zaheer, Khan Muhammad, Muhammad Haris Khan