Abstract—In this paper, we argue to learn dissimilarity for interactive search in content based image retrieval. In literature, dissimilarity is often learned via the feature space by feature selection, feature weighting or by adjusting the parameters of a function of the features. Other than existing techniques, we use feedback to adjust the dissimilarity space independent of feature space. This has the great advantage that it manipulates dissimilarity directly. To create a dissimilarity space, we use the method proposed by Pekalska and Duin, selecting a set of images called prototypes and computing distances to those prototypes for all images in the collection. After the user gives feedback, we apply active learning with a one-class support vector machine to decide the movement of images such that relevant images stay close together while irrelevant ones are pushed away (the work of Guo et al.). The dissimilarity space is then adjusted accordingly. Results on a Corel dataset of 10000 images and a TrecVid collection of 43907 keyframes show that our proposed approach is not only intuitive, it also significantly improves the retrieval performance. Index Terms—Active learning, dissimilarity learning, interactive image search, visualization. I.

This paper presents novel dissimilarity space specially designed for interactive multimedia retrieval. By providing queries made of positive and negative examples, the goal consists in learning the positive class distribution. This classification problem is known to be asymmetric, i.e. the negative class does not cluster in the original feature spaces. We introduce here the idea of Query-based Dissimilarity Space (QDS) which enables to cope with the asymmetrical setup by converting it in a more classical 2-class problem. The proposed approach is evaluated on both artificial data and real image database, and compared with stateof-the-art algorithms.

Abstract not found

Representing and fusing multimedia information is a key issue to discover semantics in multimedia. In this paper we address more specifically the problem of multimedia content retrieval by first defining a novel preference-based representation particularly adapted to the fusion problem, and then, by investigating the RankBoost algorithm to combine those preferences and a learn multimodal retrieval model. The approach has been tested on annotated images and on the complete TRECVID 2005 corpus and compared with SVMbased fusion strategies. The results show that our approach equals SVM performance but, contrary to SVM, is parameter free and faster.

of multimodal dissimilarity spaces for retrieval of video documents