# Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness

arXiv: https://arxiv.org/abs/2607.20780 · HTML: https://mlsanity.com/paper/2607.20780/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2308.11681/) (2023)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2212.05136/) (2022)
- [Open-Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2311.07042/) (2023)
- [Advancing Video Anomaly Detection: A Concise Review and a New Dataset](https://mlsanity.com/paper/2402.04857/) (2024)
- [Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2404.08531/) (2024)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts](https://mlsanity.com/paper/2408.05905/) (2024)
- [Delving into CLIP latent space for Video Anomaly Recognition](https://mlsanity.com/paper/2310.02835/) (2023)
- [Towards Open Set Video Anomaly Detection](https://mlsanity.com/paper/2208.11113/) (2022)
- [Cross-Domain Video Anomaly Detection without Target Domain Adaptation](https://mlsanity.com/paper/2212.07010/) (2022)
- [PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer](https://mlsanity.com/paper/2509.26386/) (2025)
- [AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM](https://mlsanity.com/paper/2503.04504/) (2025)
- [Anomize: Better Open Vocabulary Video Anomaly Detection](https://mlsanity.com/paper/2503.18094/) (2025)
- [Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera](https://mlsanity.com/paper/2405.19794/) (2024)
- [Language-guided Open-world Video Anomaly Detection under Weak Supervision](https://mlsanity.com/paper/2503.13160/) (2025)

## Built on by (most cited first, 2 of 2)

- [A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection](https://mlsanity.com/paper/2608.21244/) (2026)
- [Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluated](https://mlsanity.com/paper/2608.21854/) (2026)

## Abstract (arXiv)

Open-world video anomaly detection (OWVAD) aims to localize anomalous events in videos according to a user-specified definition. An OWVAD detector should therefore use the supplied definition to decide what is anomalous. We call this behavior definition following, and its failure definition blindness. However, existing temporal evaluation protocols may obscure this distinction, making strong generic anomaly detection appear to reflect definition following. For example, Drift@5 and the customizable VAD protocol treat both normal frames and anomalies outside the current definition as negatives. Across the three benchmarks used in our study, normal frames account for 78.6%-96.4% of these negatives. As a result, the reported score can be driven largely by target-versus-normal separation rather than target-versus-other-anomaly separation. Consistent with this diagnosis, a LaGoVAD branch that never receives the anomaly definition nearly matches the full model under Drift@5. We therefore introduce three complementary definition-conditioned evaluations that separate definition following from generic anomaly detection. Applying them to VAD systems and general vision-language models on UCF-Crime, XD-Violence, and MSAD reveals that strong performance under existing evaluation can coexist with weak definition following. Motivated by these results, we introduce Definition-Contrastive Scoring (DeCoS), which reduces anomaly evidence shared across competing definitions and improves definition following across the three benchmarks. Our results show that generic anomaly detection and definition following are distinct capabilities and should be evaluated separately in OWVAD.