Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yadav, Kuldeep Singh, Kumar, Lalan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.09311
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918241033519104
author Yadav, Kuldeep Singh
Kumar, Lalan
author_facet Yadav, Kuldeep Singh
Kumar, Lalan
contents Suspiciousness estimation is critical for proactive threat detection and ensuring public safety in complex environments. This work introduces a large-scale annotated dataset, USE50k, along with a computationally efficient vision-based framework for real-time suspiciousness analysis. The USE50k dataset contains 65,500 images captured from diverse and uncontrolled environments, such as airports, railway stations, restaurants, parks, and other public areas, covering a broad spectrum of cues including weapons, fire, crowd density, abnormal facial expressions, and unusual body postures. Building on this dataset, we present DeepUSEvision, a lightweight and modular system integrating three key components, i.e., a Suspicious Object Detector based on an enhanced YOLOv12 architecture, dual Deep Convolutional Neural Networks (DCNN-I and DCNN-II) for facial expression and body-language recognition using image and landmark features, and a transformer-based Discriminator Network that adaptively fuses multimodal outputs to yield an interpretable suspiciousness score. Extensive experiments confirm the superior accuracy, robustness, and interpretability of the proposed framework compared to state-of-the-art approaches. Collectively, the USE50k dataset and the DeepUSEvision framework establish a strong and scalable foundation for intelligent surveillance and real-time risk assessment in safety-critical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance
Yadav, Kuldeep Singh
Kumar, Lalan
Computer Vision and Pattern Recognition
Cryptography and Security
Suspiciousness estimation is critical for proactive threat detection and ensuring public safety in complex environments. This work introduces a large-scale annotated dataset, USE50k, along with a computationally efficient vision-based framework for real-time suspiciousness analysis. The USE50k dataset contains 65,500 images captured from diverse and uncontrolled environments, such as airports, railway stations, restaurants, parks, and other public areas, covering a broad spectrum of cues including weapons, fire, crowd density, abnormal facial expressions, and unusual body postures. Building on this dataset, we present DeepUSEvision, a lightweight and modular system integrating three key components, i.e., a Suspicious Object Detector based on an enhanced YOLOv12 architecture, dual Deep Convolutional Neural Networks (DCNN-I and DCNN-II) for facial expression and body-language recognition using image and landmark features, and a transformer-based Discriminator Network that adaptively fuses multimodal outputs to yield an interpretable suspiciousness score. Extensive experiments confirm the superior accuracy, robustness, and interpretability of the proposed framework compared to state-of-the-art approaches. Collectively, the USE50k dataset and the DeepUSEvision framework establish a strong and scalable foundation for intelligent surveillance and real-time risk assessment in safety-critical applications.
title Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2512.09311