# A Discriminative Framework for Anomaly Detection in Large Videos

arXiv: https://arxiv.org/abs/1609.08938 · HTML: https://mlsanity.com/paper/1609.08938/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2016.

## Built on by (most cited first, 25 of 25)

- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection](https://mlsanity.com/paper/2111.09099/) (2021)
- [Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2303.12369/) (2023)
- [Latent Outlier Exposure for Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2202.08088/) (2022)
- [SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection](https://mlsanity.com/paper/2207.08003/) (2022)
- [Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors](https://mlsanity.com/paper/2306.12041/) (2023)
- [Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection](https://mlsanity.com/paper/2209.12148/) (2022)
- [Learning Not to Reconstruct Anomalies](https://mlsanity.com/paper/2110.09742/) (2021)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [ASC-Net : Adversarial-based Selective Network for Unsupervised Anomaly Segmentation](https://mlsanity.com/paper/2103.03664/) (2021)
- [Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach](https://mlsanity.com/paper/2311.16514/) (2023)
- [PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies](https://mlsanity.com/paper/2303.10704/) (2023)
- [A Modular and Unified Framework for Detecting and Localizing Video Anomalies](https://mlsanity.com/paper/2103.11299/) (2021)
- [Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks](https://mlsanity.com/paper/2511.19474/) (2025)
- [Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies](https://mlsanity.com/paper/2103.10502/) (2021)
- [Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation](https://mlsanity.com/paper/2211.15597/) (2022)
- [CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2408.03014/) (2024)
- [Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings](https://mlsanity.com/paper/2104.14945/) (2021)
- [Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests](https://mlsanity.com/paper/2108.02356/) (2021)
- [ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network](https://mlsanity.com/paper/2112.09135/) (2021)
- [Look at Adjacent Frames: Video Anomaly Detection without Offline Training](https://mlsanity.com/paper/2207.13798/) (2022)
- [Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection](https://mlsanity.com/paper/2105.06649/) (2021)
- [Generalized One-Class Learning Using Pairs of Complementary Classifiers](https://mlsanity.com/paper/2106.13272/) (2021)
- [On the Connection of Generative Models and Discriminative Models for Anomaly Detection](https://mlsanity.com/paper/2211.08910/) (2022)
- [TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision Models](https://mlsanity.com/paper/2512.14141/) (2025)

## Abstract (arXiv)

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets.