A Semantic Approach to Recommending Text Advertisements for Images

In recent years, more and more images have been upload-ed and published on the Web. Along with text Web pages, images have been becoming important media to place rele-vant advertisements. Visual contextual advertising, a young research area, refers to finding relevant text advertisements for a target image without any textual information (e.g., tags). There are two existing approaches, advertisement search based on image annotation, and more recently, adver-tisement matching based on feature translation between im-ages and texts. However, the state of the art fails to achieve satisfactory results due to the fact that recommended adver-tisements are syntactically matched but semantically mis-matched. In this paper, we propose a semantic approach to improving the performance of visual contextual advertis-ing. More specifically, we exploit a large high-quality image knowledge base (ImageNet) and a widely-used text knowl-edge base (Wikipedia) to build a bridge between target im-ages and advertisements. The image-advertisement match is built by mapping images and advertisements into the re-spective knowledge bases and then finding semantic matches between the two knowledge bases. The experimental results show that semantic match outperforms syntactic match sig-nificantly using test images from Flickr. We also show that our approach gives a large improvement of 16.4 % on the pre-cision of the top 10 matches over previous work, with more semantically relevant advertisements recommended