Videoader: a video advertising system based on intelligent analysis of visual content

Recent years have witnessed the prevalence of context based video advertisement. However, those advertisement systems solely take the metadata into account, such as titles, descriptions and tags. In this paper, we present a novel video advertising system called VideoAder. The system leverages the rich information from the video corpus for embedding visual content relevant ads. Given a product, we utilize content-based object retrieval technique to identify the relevant ads and their potential embedding positions in the video stream. Specifically, the "Single-Merge" and "Merge" methods are proposed to tackle the complex query. Typical Feature Intensity (TFI) is used to train a classifier to automatically deciding which method is better in one situation. Experimental results demonstrated the feasibility of the system.