# Learning Causality-inspired Representation Consistency for Video Anomaly Detection

arXiv: https://arxiv.org/abs/2308.01537 · HTML: https://mlsanity.com/paper/2308.01537/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2023.

## Built on by (most cited first, 17 of 17)

- [Hume: Introducing System-2 Thinking in Visual-Language-Action Model](https://mlsanity.com/paper/2505.21432/) (2025)
- [Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts](https://mlsanity.com/paper/2408.05905/) (2024)
- [Networking Systems for Video Anomaly Detection: A Tutorial and Survey](https://mlsanity.com/paper/2405.10347/) (2024)
- [De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts](https://mlsanity.com/paper/2403.19539/) (2024)
- [Privacy-Preserving Video Anomaly Detection: A Survey](https://mlsanity.com/paper/2411.14565/) (2024)
- [Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2408.03888/) (2024)
- [Foundation Models and Transformers for Anomaly Detection: A Survey](https://mlsanity.com/paper/2507.15905/) (2025)
- [IPAD: Industrial Process Anomaly Detection Dataset](https://mlsanity.com/paper/2404.15033/) (2024)
- [Self-Cooperation Knowledge Distillation for Novel Class Discovery](https://mlsanity.com/paper/2407.01930/) (2024)
- [CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis](https://mlsanity.com/paper/2409.19942/) (2024)
- [Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning](https://mlsanity.com/paper/2503.19503/) (2025)
- [EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis](https://mlsanity.com/paper/2506.10002/) (2025)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [Cross-channel Perception Learning for H&E-to-IHC Virtual Staining](https://mlsanity.com/paper/2506.07559/) (2025)
- [M2S2L: Mamba-based Multi-Scale Spatial-temporal Learning for Video Anomaly Detection](https://mlsanity.com/paper/2511.05564/) (2025)
- [CalFuse: Multi-Modal Continual Learning via Feature Calibration and Parameter Fusion](https://mlsanity.com/paper/2503.18672/) (2025)
- [Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection](https://mlsanity.com/paper/2603.26745/) (2026)

## Abstract (arXiv)

Video anomaly detection is an essential yet challenging task in the multimedia community, with promising applications in smart cities and secure communities. Existing methods attempt to learn abstract representations of regular events with statistical dependence to model the endogenous normality, which discriminates anomalies by measuring the deviations to the learned distribution. However, conventional representation learning is only a crude description of video normality and lacks an exploration of its underlying causality. The learned statistical dependence is unreliable for diverse regular events in the real world and may cause high false alarms due to overgeneralization. Inspired by causal representation learning, we think that there exists a causal variable capable of adequately representing the general patterns of regular events in which anomalies will present significant variations. Therefore, we design a causality-inspired representation consistency (CRC) framework to implicitly learn the unobservable causal variables of normality directly from available normal videos and detect abnormal events with the learned representation consistency. Extensive experiments show that the causality-inspired normality is robust to regular events with label-independent shifts, and the proposed CRC framework can quickly and accurately detect various complicated anomalies from real-world surveillance videos.