Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AdVision: An efficient and effective deep learning based advertisement detector for printed media
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). Media Research AB, Ă–stersund.ORCID iD: 0000-0001-6418-2876
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-3774-4850
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-8661-7578
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-8607-4083
Show others and affiliations
2025 (English)In: Machine Learning with Applications, E-ISSN 2666-8270, Vol. 21, article id 100686Article in journal (Refereed) Published
Abstract [en]

Automated advertisement detection in newspapers is a challenging task due to the diversity in print layouts, formats, and design styles. This task has critical applications in media monitoring, content analysis, and advertising analytics. To address these challenges, we introduce AdVision, a deep-learning-based solution that treats advertisements as unique visual objects. We provide a comparative study of various detection architectures, including one-stage, two-stage, and transformer-based detectors, to identify the most effective approach for detecting advertisements. Our results are validated through extensive experiments conducted under different conditions and metrics. Newspapers from four different countries - Denmark, Norway, Sweden, and the UK - were selected to demonstrate the variety of languages and print formats. Additionally, we conduct a cross-analysis to show how training on one language can generalize to another. To enhance the explainability of our results, we employ GradCAM++ (Chattopadhay et al., 2018) heatmaps. Our experiments demonstrate that the YOLOv8 model achieves superior performance, balancing high precision and recall with minimal inference latency, making it particularly suitable for high-throughput advertisement detection.

Place, publisher, year, edition, pages
Elsevier BV , 2025. Vol. 21, article id 100686
Keywords [en]
Cross-linguistic advertisement detection, Deep learning, Newspaper image analysis, Object detection, YOLO, Model generalization
National Category
Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:miun:diva-55187DOI: 10.1016/j.mlwa.2025.100686ISI: 001519891500001Scopus ID: 2-s2.0-105027912698OAI: oai:DiVA.org:miun-55187DiVA, id: diva2:1985109
Available from: 2025-07-22 Created: 2025-07-22 Last updated: 2026-10-07

Open Access in DiVA

fulltext(3127 kB)169 downloads
File information
File name FULLTEXT01.pdfFile size 3127 kBChecksum SHA-512
9facb25f811686d44959c63e89e2af1a297d7deb9536d47a2fea0928e5016cf9fc9943ceede7fb87c130c4fafe11e380c66eafe3527ef636e8f9056012d9d31f
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Zakaryapour Sayyad, FaezeShallari, IridaSeyed Jalaleddin, MousaviradO'Nils, Mattias

Search in DiVA

By author/editor
Zakaryapour Sayyad, FaezeShallari, IridaSeyed Jalaleddin, MousaviradO'Nils, Mattias
By organisation
Department of Computer and Electrical Engineering (2023-)
In the same journal
Machine Learning with Applications
Computer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar
Total: 170 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 424 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf