Advertising based on users´ photos

In this paper, we tackle the problem of learning a user´s interest from his photo collections and suggesting relevant ads. We address two key challenges in this work: 1) understanding a user´s photos to detect his interest, and 2) bridging the lexical and semantic gap between the vocabulary of ads and that of general users´ photos. We solve the first problem by employing a data-driven image annotation approach to annotate each photo and modeling a group of photos, and tackle the second problem by learning and matching the topics of users´ photos and ads. The experiments based on real flicker data showed the effectiveness of the approach.