ADNet: A Deep Network for Detecting Adverts
This addresses the need for automated advert detection in online video advertising to improve efficiency for marketing agencies and content providers.
The paper tackles the problem of manually detecting advertisement frames in videos for product placement by proposing ADNet, a deep-learning architecture that automatically detects adverts in video frames, achieving state-of-the-art results on a public dataset.
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.