# ADNet: Temporal Anomaly Detection in Surveillance Videos

arXiv: https://arxiv.org/abs/2104.06653 · HTML: https://mlsanity.com/paper/2104.06653/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [Weakly Supervised Action Localization by Sparse Temporal Pooling Network](https://mlsanity.com/paper/1712.05080/) (2017)
- [AutoLoc: Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1807.08333/) (2018)
- [Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment](https://mlsanity.com/paper/1803.10699/) (2018)
- [Unsupervised Traffic Accident Detection in First-Person Videos](https://mlsanity.com/paper/1903.00618/) (2019)
- [Weakly Supervised Action Labeling in Videos Under Ordering Constraints](https://mlsanity.com/paper/1407.1208/) (2014)
- [CTAP: Complementary Temporal Action Proposal Generation](https://mlsanity.com/paper/1807.04821/) (2018)
- [Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks](https://mlsanity.com/paper/1510.00562/) (2015)
- [CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis](https://mlsanity.com/paper/1809.05782/) (2018)
- [Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video](https://mlsanity.com/paper/1901.01138/) (2019)

## Built on by (most cited first, 4 of 4)

- [Ambiguous Images With Human Judgments for Robust Visual Event Classification](https://mlsanity.com/paper/2210.03102/) (2022)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization](https://mlsanity.com/paper/2303.08463/) (2023)
- [Exploring the Impact of Outlier Variability on Anomaly Detection Evaluation Metrics](https://mlsanity.com/paper/2409.15986/) (2024)

## Abstract (arXiv)

Anomaly detection in surveillance videos is an important research problem in computer vision. In this paper, we propose ADNet, an anomaly detection network, which utilizes temporal convolutions to localize anomalies in videos. The model works online by accepting consecutive windows consisting of fixed-number of video clips. Features extracted from video clips in a window are fed to ADNet, which allows to localize anomalies in videos effectively. We propose the AD Loss function to improve abnormal segment detection performance of ADNet. Additionally, we propose to use F1@k metric for temporal anomaly detection. F1@k is a better evaluation metric than AUC in terms of not penalizing minor shifts in temporal segments and punishing short false positive temporal segment predictions. Furthermore, we extend UCF Crime dataset by adding two more anomaly classes and providing temporal anomaly annotations for all classes. Finally, we thoroughly evaluate our model on the extended UCF Crime dataset. ADNet produces promising results with respect to F1@k metric. Dataset extensions and code will be publicly available upon publishing