We apply multilayer bootstrap network (MBN), a recent proposed unsupervised learning method, to unsupervised speaker recognition. The proposed method first extracts supervectors from an unsupervised universal background model, then reduces the dimension of the high-dimensional supervectors by multilayer bootstrap network, and finally conducts unsupervised speaker recognition by clustering the l...

This paper presents a self-supervised framework for perceptual learning based upon correlations in different sensory modalities. We demonstrate this with a system that has learned the vowel structure of American English – i.e., the number of vowels and their phonetic descriptions – by simultaneously watching and listening to someone speak. It is highly non-parametric, knowing neither the number...

Complex networks have shown to be promising mechanisms to represent several aspects of nature, since their topological and structural features help in the understanding of relations, properties and intrinsic characteristics of the data. In this context, we propose to build music networks in order to find community structures of music genres. Our main contributions are twofold: 1) Define a total...

Key frames and previews are two forms of a video abstract, widely used for various applications in video browsing and retrieval systems. We propose in this paper a novel method for generating these two abstract forms for an arbitrary video sequence. The underlying principle of the proposed method is the removal of the visual-content redundancy among video frames. This is done by first applying ...

In this article we learn significant local appearance features for visual classes. Generic feature detectors are obtained by unsupervised learning using clustering. The resulting clusters, referred to as “classtons”, identify the significant class characteristics from a small set of sample images. The classton channels mark these characteristics reliably using a probabilistic cluster representa...

In this paper, we present a graph-based multi-resolution approach for mitosis extraction in breast cancer histological whole slide images. The proposed segmentation uses a multi-resolution approach which reproduces the slide examination done by a pathologist. Each resolution level is analyzed with a focus of attention resulting from a coarser resolution level analysis. At each resolution level,...

Current approaches to document-level sentiment analysis rely on local information, e.g., the words within the given document. We try to achieve better performance by incorporating global context of the sentiment target (e.g., a movie or a product). We assume that sentiment labels of reviews about the same target are often consistent in some way. We model this consistency by Dirichlet distributi...

Polarity classification of opinionated sentences with both positive and negative sentiments1 is a key challenge in sentiment analysis. This paper presents a novel unsupervised method for discovering intra-sentence level discourse relations for eliminating polarity ambiguities. Firstly, a discourse scheme with discourse constraints on polarity was defined empirically based on Rhetorical Structur...

Most clustering algorithmspartition a &fa set based on a dissimilarity relation expressed in t e m of some distance function. When the nature of this relation is conceptual rather than mehic, distance finctions may fail to adequately model dissimilarity. For this reason, we propose to extract dissimilarify relations directlyfrom the data. We exploit some pairs of paffems with known dissimilarit...

A new algorithm is proposed for the variation of independent component analysis (ICA) in which there are several mixing matrices and, for each set of independent components, one of the matrices is randomly chosen to mix the components. The algorithm utilizes high-order moments and can obtain consistent estimators even if the true probability density function of independent components is not obt...