Saved in:
Bibliographic Details
Main Authors: Baroutian, Bita, Aghaei, Atefe, Moghaddam, Mohsen Ebrahimi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.04536
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917124589486080
author Baroutian, Bita
Aghaei, Atefe
Moghaddam, Mohsen Ebrahimi
author_facet Baroutian, Bita
Aghaei, Atefe
Moghaddam, Mohsen Ebrahimi
contents Alcohol consumption is a significant public health concern and a major cause of accidents and fatalities worldwide. This study introduces a novel video-based facial sequence analysis approach dedicated to the detection of alcohol intoxication. The method integrates facial landmark analysis via a Graph Attention Network (GAT) with spatiotemporal visual features extracted using a 3D ResNet. These features are dynamically fused with adaptive prioritization to enhance classification performance. Additionally, we introduce a curated dataset comprising 3,542 video segments derived from 202 individuals to support training and evaluation. Our model is compared against two baselines: a custom 3D-CNN and a VGGFace+LSTM architecture. Experimental results show that our approach achieves 95.82% accuracy, 0.977 precision, and 0.97 recall, outperforming prior methods. The findings demonstrate the model's potential for practical deployment in public safety systems for non-invasive, reliable alcohol intoxication detection.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04536
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Model
Baroutian, Bita
Aghaei, Atefe
Moghaddam, Mohsen Ebrahimi
Computer Vision and Pattern Recognition
Artificial Intelligence
Alcohol consumption is a significant public health concern and a major cause of accidents and fatalities worldwide. This study introduces a novel video-based facial sequence analysis approach dedicated to the detection of alcohol intoxication. The method integrates facial landmark analysis via a Graph Attention Network (GAT) with spatiotemporal visual features extracted using a 3D ResNet. These features are dynamically fused with adaptive prioritization to enhance classification performance. Additionally, we introduce a curated dataset comprising 3,542 video segments derived from 202 individuals to support training and evaluation. Our model is compared against two baselines: a custom 3D-CNN and a VGGFace+LSTM architecture. Experimental results show that our approach achieves 95.82% accuracy, 0.977 precision, and 0.97 recall, outperforming prior methods. The findings demonstrate the model's potential for practical deployment in public safety systems for non-invasive, reliable alcohol intoxication detection.
title Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.04536