the proceedings contain 23 papers. the special focus in this conference is on Data Structures and Representation. the topics include: Construction of combinatorial pyramids;on graphs with unique node labels;maximal in...
ISBN:
(纸本)354040452X
the proceedings contain 23 papers. the special focus in this conference is on Data Structures and Representation. the topics include: Construction of combinatorial pyramids;on graphs with unique node labels;maximal independent directed edge set;functional modeling of structured images;building of symbolic hierarchical graphs for feature extraction;comparison and convergence of two topological models for 3D image segmentation;tree edit distance from information theory;self-organizing graph edit distance;graph edit distance with node splitting and merging, and its application to diatom identification;orthonormal kernel kronecker product graph matching;theoretical analysis and experimental comparison of graph matching algorithms for database filtering;a comparison of three maximum common subgraph algorithms on a large database of labeled graphs;swap strategies for graph matching;graph matching using spectral seriation and string edit distance;graph polynomials, principal pivoting, and maximum independent sets;graph partition for matching;spectral clustering of graphs;comparison of distance measures for graph-based clustering of documents;some experiments on clustering a set of strings;a new median graph algorithm;graph clustering using the weighted minimum common supergraph;ACM attributed graph clustering for learning classes of images and a competitive winner-takes-all architecture for classification and patternrecognition of structures.
In this paper we try to examine recent trends on the use of graph-basedrepresentations in patternrecognition, using as a vantage point the 11th IAPR-TC15 workshop GbR2017, dedicated to this topic. A survey of the pa...
详细信息
In this paper we try to examine recent trends on the use of graph-basedrepresentations in patternrecognition, using as a vantage point the 11th IAPR-TC15 workshop GbR2017, dedicated to this topic. A survey of the paper presented at GbR2017 will give us the opportunity to reflect on the directions where the interest of the research community working on this subject is moving. (C) 2018 Elsevier B.V. All rights reserved.
the field of statistical patternrecognition is characterized by the use of feature vectors for pattern representation, while strings or, more generally, graphs are prevailing in structural patternrecognition. In thi...
详细信息
ISBN:
(纸本)9783540729020
the field of statistical patternrecognition is characterized by the use of feature vectors for pattern representation, while strings or, more generally, graphs are prevailing in structural patternrecognition. In this paper we aim at bridging the gap between the domain of feature based and graphbased object representation. We propose a general approach for transforming graphs into n-dimensional real vector spaces by means of prototype selection and graph edit distance computation. this method establishes the access to the wide range of procedures based on feature vectors without loosing the representational power of graphs. through various experimental results we show that the proposed method, using graph embedding and classification in a vector space, outperforms the tradional approach based on k-nearest neighbor classification in the graph domain.
the traveling salesman problem (TSP) is difficult to solve for input instances with large number of cities. Instead of finding the solution for an input with a large number of cities, the problem is transformed into a...
详细信息
the traveling salesman problem (TSP) is difficult to solve for input instances with large number of cities. Instead of finding the solution for an input with a large number of cities, the problem is transformed into a simpler form containing smaller number of cities, which is then solved optimally. graph pyramid solution strategies, using Boruvka's minimum spanning tree step, convert, in a bottom-up processing, a 2D Euclidean TSP problem with a large number of cities into successively smaller problems (graphs) with similar layout and solution, until the number of cities is small enough to seek the optimal solution. Expanding this tour solution in a top-down manner, to the lower levels of the pyramid, leads to an approximate solution. the new model has an adaptive spatial structure and it simulates visual acuity and visual attention. the model solves the TSP problem sequentially, by moving attention from city to city, and the quality of the solutions is similar to the solutions produced by humans. the graph pyramid data structures and processing strategies provide good methods for finding near-optimal solutions for computationally hard problems. Isolating processing used by humans to solve computationally hard problems is of general importance to psychology community and might lead to advances in patternrecognition. (C) 2008 Elsevier B.V. All rights reserved.
In this paper we propose a quadratic programming approach to computing the edit distance of graphs. Whereas the standard edit distance is defined with respect to a minimum-cost edit path between graphs, we introduce t...
详细信息
ISBN:
(纸本)9783540729020
In this paper we propose a quadratic programming approach to computing the edit distance of graphs. Whereas the standard edit distance is defined with respect to a minimum-cost edit path between graphs, we introduce the notion of fuzzy edit paths between graphs and provide a quadratic programming formulation for the minimization of fuzzy edit costs. Experiments on real-world graph data demonstrate that our proposed method is able to outperform the standard edit distance method in terms of recognition accuracy on two out of three data sets.
New technologies for shape acquisition and rendering of digital shapes have simplified the process of creating virtual scenes;nonetheless, shape annotation, recognition and manipulation of boththe complete virtual sc...
详细信息
ISBN:
(纸本)9783540729020
New technologies for shape acquisition and rendering of digital shapes have simplified the process of creating virtual scenes;nonetheless, shape annotation, recognition and manipulation of boththe complete virtual scenes and even of subparts of them are still open problems. Once the main components of a virtual scene are represented by structural descriptions, this paper deals withthe problem of comparing two (or more) sets of 3D objects, where each model is represented by an attributed graph. We will define a new distance to estimate the possible similarities among the sets of graphs and we will validate our work using a shape graph [1].
graph Neural Networks (GNNs) have achieved state-of-the-art performance on a wide range of graph-based tasks such as graph classification and node classification. this is because the unique structure of GNNs allows th...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
graph Neural Networks (GNNs) have achieved state-of-the-art performance on a wide range of graph-based tasks such as graph classification and node classification. this is because the unique structure of GNNs allows them to effectively learn embeddings for unstructured data. One important operation for graph classification tasks is downsampling or pooling, which obtains graphrepresentations from node representations. However, most GNNs are associated with global pooling, that can not learn hierarchical graphrepresentations. Meanwhile, current hierarchical pooling methods have the shortcomings of unclear node assignment and uniform aggregation. To overcome these drawbacks, we propose an attention-based differentiable pooling operation in this paper, which can learn a hard cluster assignment for nodes and aggregate nodes in each cluster differently by introducing an attention mechanism. Experiments on standard graph classification benchmarks show that our proposed approach performs better when compared with other competing methods.
We introduce a method for computing homology groups and their generators of a 2D image, using a hierarchical structure, i.e. irregular graph pyramid. Starting from an image, a hierarchy of the image is built by two op...
详细信息
We introduce a method for computing homology groups and their generators of a 2D image, using a hierarchical structure, i.e. irregular graph pyramid. Starting from an image, a hierarchy of the image is built by two operations that preserve homology of each region. Instead of computing homology generators in the base where the number of entities (cells) is large, we first reduce the number of cells by a graph pyramid. then homology generators are computed efficiently on the top level of the pyramid, since the number of cells is small. A top down process is then used to deduce homology generators in any level of the pyramid, including the base level, i.e. the initial image. the produced generators fit on the object boundaries. A unique set of generators called the minimal set, is defined and its computation is discussed. We show that the new method produces valid homology generators and present some experimental results. (C) 2008 Elsevier B.V. All rights reserved.
graphs and graph transformation are versatile tools for representing and interpreting the contents of document images. three main components are involved: a graph representing the contents of a document image at some ...
详细信息
ISBN:
(纸本)3540252703
graphs and graph transformation are versatile tools for representing and interpreting the contents of document images. three main components are involved: a graph representing the contents of a document image at some level of interpretation, a set of graph transformation rules (graph productions), and a mechanism for controlling the application of the graph productions. We review existing document analysis systems that use graph transformation, and discuss challenges and research opportunities in this area.
暂无评论