# Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection

arXiv: https://arxiv.org/abs/2505.15205 · HTML: https://mlsanity.com/paper/2505.15205/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 61 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 30 of 42)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [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)
- [VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2308.11681/) (2023)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2211.15098/) (2022)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)

## Built on by (most cited first, 12 of 12)

- [Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting](https://mlsanity.com/paper/2510.02155/) (2025)
- [Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding](https://mlsanity.com/paper/2603.19054/) (2026)
- [Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models](https://mlsanity.com/paper/2605.02912/) (2026)
- [The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection](https://mlsanity.com/paper/2606.21579/) (2026)
- [TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection](https://mlsanity.com/paper/2511.00580/) (2025)
- [Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection](https://mlsanity.com/paper/2609.17211/) (2026)
- [Decision Readouts for Text-Mediated Video Anomaly Detection: An Exploratory Evaluation of Jev and Qwen](https://mlsanity.com/paper/2609.34180/) (2026)
- [Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection](https://mlsanity.com/paper/2603.13374/) (2026)
- [LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection](https://mlsanity.com/paper/2605.15054/) (2026)
- [NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection](https://mlsanity.com/paper/2609.06360/) (2026)
- [ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding](https://mlsanity.com/paper/2609.07941/) (2026)
- [PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation](https://mlsanity.com/paper/2609.33236/) (2026)

## Abstract (arXiv)

Video Anomaly Detection (VAD) automatically identifies anomalous events from video, mitigating the need for human operators in large-scale surveillance deployments. However, two fundamental obstacles hinder real-world adoption: domain dependency and real-time constraints -- requiring near-instantaneous processing of incoming video. To this end, we propose Flashback, a zero-shot and real-time video anomaly detection paradigm. Inspired by the human cognitive mechanism of instantly judging anomalies and reasoning in current scenes based on past experience, Flashback operates in two stages: Recall and Respond. In the offline recall stage, an off-the-shelf LLM builds a pseudo-scene memory of both normal and anomalous captions without any reliance on real anomaly data. In the online respond stage, incoming video segments are embedded and matched against this memory via similarity search. By eliminating all LLM calls at inference time, Flashback delivers real-time VAD even on a consumer-grade GPU. On two large datasets from real-world surveillance scenarios, UCF-Crime and XD-Violence, we achieve 87.3 AUC (+7.0 pp) and 75.1 AP (+13.1 pp), respectively, outperforming prior zero-shot VAD methods by large margins.