Lightweight Vision Transformer Framework for Real-Time Human–Object Interaction Recognition

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autor principal: Michael Turner¹, Olivia Reed², Ethan Walker³
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901836255985664
author Michael Turner¹, Olivia Reed², Ethan Walker³
author_facet Michael Turner¹, Olivia Reed², Ethan Walker³
contents <p><strong><em><span>Human–Object Interaction (HOI) recognition is a fundamental task in intelligent computing systems, enabling machines to understand how humans engage with surrounding objects in real-time environments. Traditional deep learning approaches for HOI rely heavily on convolutional architectures, which often struggle with long-range dependencies and are computationally expensive for edge deployment. This paper proposes a Lightweight Vision Transformer Framework (LVTF) designed specifically for efficient and accurate real-time HOI recognition. The framework employs a patch-based visual encoder combined with optimized multi-head attention mechanisms to capture global contextual relationships between humans and objects. A lightweight decoder further refines these representations to generate interaction labels with minimal latency. Experimental evaluations conducted on benchmark HOI datasets demonstrate that the LVTF achieves competitive accuracy while reducing computational complexity by nearly 40% compared to conventional transformer and CNN-based models. The reduced model footprint and low inference delay make the proposed approach highly suitable for real-time intelligent applications, including smart surveillance, assistive robotics, and human–computer interaction systems.</span></em></strong></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17753367
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Lightweight Vision Transformer Framework for Real-Time Human–Object Interaction Recognition
Michael Turner¹, Olivia Reed², Ethan Walker³
Vision transformer, human–object interaction, real-time recognition, lightweight architecture, attention mechanism, intelligent systems.
<p><strong><em><span>Human–Object Interaction (HOI) recognition is a fundamental task in intelligent computing systems, enabling machines to understand how humans engage with surrounding objects in real-time environments. Traditional deep learning approaches for HOI rely heavily on convolutional architectures, which often struggle with long-range dependencies and are computationally expensive for edge deployment. This paper proposes a Lightweight Vision Transformer Framework (LVTF) designed specifically for efficient and accurate real-time HOI recognition. The framework employs a patch-based visual encoder combined with optimized multi-head attention mechanisms to capture global contextual relationships between humans and objects. A lightweight decoder further refines these representations to generate interaction labels with minimal latency. Experimental evaluations conducted on benchmark HOI datasets demonstrate that the LVTF achieves competitive accuracy while reducing computational complexity by nearly 40% compared to conventional transformer and CNN-based models. The reduced model footprint and low inference delay make the proposed approach highly suitable for real-time intelligent applications, including smart surveillance, assistive robotics, and human–computer interaction systems.</span></em></strong></p>
title Lightweight Vision Transformer Framework for Real-Time Human–Object Interaction Recognition
topic Vision transformer, human–object interaction, real-time recognition, lightweight architecture, attention mechanism, intelligent systems.
url https://doi.org/10.5281/zenodo.17753367