ADNet: A Deep Network for Detecting Adverts
Abstract
Online video advertising gives content providers the ability to deliver compelling content, reach a growing audience, and generate additional revenue from online media. Recently, advertising strategies are designed to look for original advert(s) in a video frame, and replacing them with new adverts. These strategies, popularly known as product placement or embedded marketing, greatly help the marketing agencies to reach out to a wider audience. However, in the existing literature, such detection of candidate frames in a video sequence for the purpose of advert integration, is done manually. In this paper, we propose a deep-learning architecture called ADNet, that automatically detects the presence of advertisements in video frames. Our approach is the first of its kind that automatically detects the presence of adverts in a video frame, and achieves state-of-the-art results on a public dataset.
Keywords
Cite
@article{arxiv.1811.04115,
title = {ADNet: A Deep Network for Detecting Adverts},
author = {Murhaf Hossari and Soumyabrata Dev and Matthew Nicholson and Killian McCabe and Atul Nautiyal and Clare Conran and Jian Tang and Wei Xu and François Pitié},
journal= {arXiv preprint arXiv:1811.04115},
year = {2018}
}
Comments
Published in Proc. 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2018), First two authors contributed equally to this work