In this paper we propose a new method to deal with the problem of automatic human skin segmentation in RGB color space model. The problem is modeled as a minimum cost graph cut problem on a graph whose vertices represent the image color characteristics. Skin and non-skin elements are assigned by evaluating label costs of vertices associated to the weight edges of the graph. A novel approach bas...

We prove that if the vertices of a complete graph are labeled with the elements of an arithmetic progression, then for any given vertex there is a Hamiltonian path starting at this vertex such that the absolute values of the differences of consecutive vertices along the path are pairwise distinct. In another extreme case where the label set has small additive energy, we show that the graph actu...

The D-eigenvalues {µ1,…,µp} of a graph G are the eigenvalues of its distance matrix D and form its D-spectrum. The D-energy, ED(G) of G is given by ED (G) =∑i=1p |µi|. Two non cospectral graphs with respect to D are said to be D-equi energetic if they have the same D-energy. In this paper we show that if G is an r-regular graph on p vertices with 2r ≤ p - 1, then the complements of iterated lin...

We present an approach for computing dense scene flow from two large displacement RGB-D images. When dealing with large displacements the crucial step is to estimate the overall motion correctly. While state-of-the-art approaches focus on RGB information to establish guiding correspondences, we explore the power of depth edges. To achieve this, we present a new graph matching technique that bri...

Graph neural networks (GNNs) have emerged as effective approaches for graph analysis, especially in the scenario of semi-supervised learning. Despite its success, GNN often suffers from over-smoothing and over-fitting problems, which affects performance on node classification tasks. We analyze that an alternative method, label propagation algorithm (LPA), avoids aforementioned problems thus it ...

With the recent advances in graph neural networks, there is a rising number of studies on graph-based multi-label classification with consideration object dependencies within visual data. Nevertheless, representations can become indistinguishable due to complex nature label relationships. We propose image framework based transformer networks fully exploit inter-label interactions. The paper pre...

Label Propagation Algorithm (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification, but LPA propagates label information across edges graph, while GCN transforms feature information. However, conceptually similar, theoretical relationship between has not yet been systematically investigated. Moreover, it is u...