CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World

• URL: http://arxiv.org/abs/2511.00613v1
• Date: Sat, 01 Nov 2025 16:29:35 GMT
• Title: CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World
• Abstract summary: We introduce CueBench, the first of its kind Benchmark devoted to context-aware video anomalies.<n>We propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation.<n>We further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards.
• Score: 23.48765196513229
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or comprehending anomalous events with interpretable descriptions. However, they exhibit only a superficial comprehension of real-world anomalies, with limited breadth in complex principles and subtle context that distinguish the anomalies from normalities, e.g., climbing cliffs with safety gear vs. without it. To this end, we introduce CueBench, the first of its kind Benchmark, devoted to Context-aware video anomalies within a Unified Evaluation framework. We comprehensively establish an event-centric hierarchical taxonomy that anchors two core event types: 14 conditional and 18 absolute anomaly events, defined by their refined semantics from diverse contexts across 174 scenes and 198 attributes. Based on this, we propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation. This also serves as a rigorous and fair probing evaluation suite for generative-discriminative as well as generalized-specialized vision-language models (VLMs). To address the challenges underlying CueBench, we further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards in a unified generative manner. Extensive results on CueBench reveal that, existing VLMs are still far from satisfactory real-world anomaly understanding, while our Cue-R1 surpasses these state-of-the-art approaches by over 24% on average.

Related papers

• TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding [24.101948294850107]
  Video anomaly understanding (VAU) seeks to endow models with a similar capability.<n>We introduce TAU-Bench, a benchmark for evaluating anomaly instance tracking and fine-grained anomaly understanding.<n>We show that models producing plausible anomaly interpretations may still fail to localize and track the correct instance reliably.
  arXiv  Detail & Related papers  (2026-08-06T07:43:17Z)
• Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference [54.774686416991386]
  We argue that multimodal anomaly detection should be reframed as a cross-modal contextual inference problem.<n>This perspective has implications for model design, evaluation protocols, and benchmark construction.
  arXiv  Detail & Related papers  (2026-04-14T19:32:55Z)
• Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment [47.507511439028754]
  We propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects.<n>At the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes.<n>At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components.
  arXiv  Detail & Related papers  (2025-11-13T14:06:48Z)
• Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection [7.435598538875321]
  Video Anomaly Detection (VAD) is a challenging task due to the variability of anomalous events and the limited availability of labeled data.<n>We propose a novel framework that employs a set of expert models, each specialized in capturing specific anomaly types.<n>Our approach achieves state-of-the-art performance, with a 91.58% AUC on the UCF-Crime dataset, and demonstrates superior results on XD-Violence and MSAD datasets.
  arXiv  Detail & Related papers  (2025-08-08T13:48:48Z)
• VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning [12.293826084601115]
  Video anomaly understanding is essential for smart cities, security surveillance, and disaster alert systems.<n>Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events.<n>We introduce VAU-R1, a data-efficient framework built upon Multimodal Large Language Models (MLLMs), which enhances anomaly reasoning through Reinforcement Fine-Tuning (RFT)
  arXiv  Detail & Related papers  (2025-05-29T14:48:10Z)
• CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos [40.63347505454772]
  Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community.<n>Previous methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner.<n>We propose Causal Consistency Representation Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning.
  arXiv  Detail & Related papers  (2025-03-24T15:50:19Z)
• Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly [12.896651217314744]
  We introduce a benchmark for Exploring the Causation of Video Anomalies (ECVA)<n>Our benchmark is meticulously designed, with each video accompanied by detailed human annotations.<n>We propose AnomEval, a specialized evaluation metric crafted to align closely with human judgment criteria for ECVA.
  arXiv  Detail & Related papers  (2024-12-10T04:41:44Z)
• Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection [56.57122939745213]
  Anomaly detection focuses on identifying samples that deviate from the norm.<n>Recent self-supervised methods have successfully learned such representations by employing prior knowledge about anomalies to create synthetic outliers during training.<n>We address this limitation with our new approach Con$$, which leverages prior knowledge about symmetries in normal samples to observe the data in different contexts.
  arXiv  Detail & Related papers  (2024-05-29T07:59:06Z)
• Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection [16.77262005540559]
  A novel framework is proposed to guide the learning of suspected anomalies from event prompts. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC.
  arXiv  Detail & Related papers  (2024-03-02T10:42:47Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Sensing Anomalies like Humans: A Hominine Framework to Detect Abnormal Events from Unlabeled Videos [48.15740415466055]
  Video anomaly detection (VAD) has constantly been a vital topic in video analysis. We are inspired by how humans sense anomalies and propose a hominine framework that enables both unsupervised and end-to-end VAD.
  arXiv  Detail & Related papers  (2021-08-04T11:31:57Z)
• Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features [8.407188666535506]
  Most existing methods use an autoencoder to learn to reconstruct normal videos. We propose an implicit two-path AE (ITAE), a structure in which two encoders implicitly model appearance and motion features. For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features. NF models intensify ITAE performance by learning normality through implicitly learned features.
  arXiv  Detail & Related papers  (2020-10-15T05:02:02Z)
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video [120.18562044084678]
  Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. We propose a background-agnostic framework that learns from training videos containing only normal events.
  arXiv  Detail & Related papers  (2020-08-27T18:39:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.