# Transformer Based Self-Context Aware Prediction for Few-Shot Anomaly Detection in Videos

arXiv: https://arxiv.org/abs/2503.00670 · HTML: https://mlsanity.com/paper/2503.00670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Continual Learning for Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/2004.07941/) (2020)
- [Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction](https://mlsanity.com/paper/2011.02763/) (2020)
- [Real-Time Anomaly Detection With HMOF Feature](https://mlsanity.com/paper/1812.04980/) (2018)

## Abstract (arXiv)

Anomaly detection in videos is a challenging task as anomalies in different videos are of different kinds. Therefore, a promising way to approach video anomaly detection is by learning the non-anomalous nature of the video at hand. To this end, we propose a one-class few-shot learning driven transformer based approach for anomaly detection in videos that is self-context aware. Features from the first few consecutive non-anomalous frames in a video are used to train the transformer in predicting the non-anomalous feature of the subsequent frame. This takes place under the attention of a self-context learned from the input features themselves. After the learning, given a few previous frames, the video-specific transformer is used to infer if a frame is anomalous or not by comparing the feature predicted by it with the actual. The effectiveness of the proposed method with respect to the state-of-the-art is demonstrated through qualitative and quantitative results on different standard datasets. We also study the positive effect of the self-context used in our approach.