Publications

ADNet: A Deep Network for Detecting Adverts. Hossari, Murhaf, Dev, Soumyabrata, Nicholson, Matthew, McCabe, Killian, Nautiyal, Atul, Conran, Clare, Tang, Jian, Xu, Wei and Pitie, Fran\c cois (2018) . (demo)

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.

Bibtex entry

@INPROCEEDINGS { hossari_adnet:_2018,
    TITLE = { {ADNet}: {A} {Deep} {Network} for {Detecting} {Adverts} },
    COPYRIGHT = { All rights reserved },
    SHORTTITLE = { {ADNet} },
    URL = { http://arxiv.org/abs/1811.04115 },
    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. },
    URLDATE = { 2018-12-12 },
    AUTHOR = { Hossari, Murhaf and Dev, Soumyabrata and Nicholson, Matthew and McCabe, Killian and Nautiyal, Atul and Conran, Clare and Tang, Jian and Xu, Wei and Piti{\'e}, Fran{\c c}ois },
    MONTH = { dec },
    YEAR = { 2018 },
    NOTE = { arXiv: 1811.04115 },
    KEYWORDS = { Computer Science - Machine Learning, Computer Science - Multimedia },
    FILE = { arXiv\:1811.04115 PDF:/Users/fpitie/Zotero/storage/2WKYYP5B/Hossari et al. - 2018 - ADNet A Deep Network for Detecting Adverts.pdf:application/pdf;arXiv.org Snapshot:/Users/fpitie/Zotero/storage/UGD4669L/1811.html:text/html },
}

Page last modified on March 14, 2019