# Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detection

arXiv: https://arxiv.org/abs/2601.18135 · HTML: https://mlsanity.com/paper/2601.18135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free](https://mlsanity.com/paper/2505.06708/) (2025)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos](https://mlsanity.com/paper/1903.03295/) (2019)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Video Event Restoration Based on Keyframes for Video Anomaly Detection](https://mlsanity.com/paper/2304.05112/) (2023)
- [Local-Global Context Aware Transformer for Language-Guided Video Segmentation](https://mlsanity.com/paper/2203.09773/) (2022)
- [Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection](https://mlsanity.com/paper/2303.13051/) (2023)
- [Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection](https://mlsanity.com/paper/2207.10948/) (2022)
- [Making Reconstruction-based Method Great Again for Video Anomaly Detection](https://mlsanity.com/paper/2301.12048/) (2023)
- [Updated version: A Video Anomaly Detection Framework based on Appearance-Motion Semantics Representation Consistency](https://mlsanity.com/paper/2303.05109/) (2023)
- [PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies](https://mlsanity.com/paper/2303.10704/) (2023)
- [VADMamba: Exploring State Space Models for Fast Video Anomaly Detection](https://mlsanity.com/paper/2503.21169/) (2025)
- [Bidirectional skip-frame prediction for video anomaly detection with intra-domain disparity-driven attention](https://mlsanity.com/paper/2407.15424/) (2024)
- [Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation](https://mlsanity.com/paper/2211.15597/) (2022)
- [Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detection](https://mlsanity.com/paper/2409.17608/) (2024)
- [Prior Knowledge Guided Network for Video Anomaly Detection](https://mlsanity.com/paper/2309.01682/) (2023)

## Abstract (arXiv)

As a crucial element of public security, video anomaly detection (VAD) aims to measure deviations from normal patterns for various events in real-time surveillance systems. However, most existing VAD methods rely on large-scale models to pursue extreme accuracy, limiting their feasibility on resource-limited edge devices. Moreover, mainstream prediction-based VAD detects anomalies using only single-frame future prediction errors, overlooking the richer constraints from longer-term temporal forward information. In this paper, we introduce FoGA, a lightweight VAD model that performs Forward consistency learning with Gated context Aggregation, containing about 2M parameters and tailored for potential edge devices. Specifically, we propose a Unet-based method that performs feature extraction on consecutive frames to generate both immediate and forward predictions. Then, we introduce a gated context aggregation module into the skip connections to dynamically fuse encoder and decoder features at the same spatial scale. Finally, the model is jointly optimized with a novel forward consistency loss, and a hybrid anomaly measurement strategy is adopted to integrate errors from both immediate and forward frames for more accurate detection. Extensive experiments demonstrate the effectiveness of the proposed method, which substantially outperforms state-of-the-art competing methods, running up to 155 FPS. Hence, our FoGA achieves an excellent trade-off between performance and the efficiency metric.