# ADS-ME: Anomaly Detection System for Micro-expression Spotting

## TL;DR

This paper introduces ADS-ME, a novel anomaly detection system for micro-expression spotting that models normal facial behaviors to identify rare micro-expressions using probabilistic and deep learning techniques.

## Contribution

It presents a new probabilistic model combined with a recurrent convolutional autoencoder for effective micro-expression detection, outperforming previous methods.

## Key findings

- System achieves higher detection accuracy than prior approaches.
- Probabilistic modeling effectively distinguishes micro-expressions from normal facial behaviors.
- Adaptive thresholding improves micro-expression identification robustness.

## Abstract

Micro-expressions (MEs) are infrequent and uncontrollable facial events that can highlight emotional deception and appear in a high-stakes environment. This paper propose an algorithm for spatiotemporal MEs spotting. Since MEs are unusual events, we treat them as abnormal patterns that diverge from expected Normal Facial Behaviour (NFBs) patterns. NFBs correspond to facial muscle activations, eye blink/gaze events and mouth opening/closing movements that are all facial deformation but not MEs. We propose a probabilistic model to estimate the probability density function that models the spatiotemporal distributions of NFBs patterns. To rank the outputs, we compute the negative log-likelihood and we developed an adaptive thresholding technique to identify MEs from NFBs. While working only with NFBs data, the main challenge is to capture intrinsic spatiotemoral features, hence we design a recurrent convolutional autoencoder for feature representation. Finally, we show that our system is superior to previous works for MEs spotting.