Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
We present an efficient matching method for generalized geometric graphs. Such graphs consist of vertices in space connected by curves and can represent many real world structures such as road networks in remote sensing, or vessel networks in medical imaging. Graph matching can be used for very fast and possibly multimodal registration of images of these structures. We formulate the matching problem as a single player game solved using Monte Carlo Tree Search, which automatically balances exploring new possible matches and extending existing matches. Our method can handle partial matches, topological differences, geometrical distortion, does not use appearance information and does not require an initial alignment. Moreover, our method is very efficient-it can match graphs with thousands of nodes, which is an order of magnitude better than the best competing method, and the matching only takes a few seconds.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2016.2636200 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Semi-supervised graph learning for underwater source localization using ship-of-opportunity spectrograms.
J Acoust Soc Am
September 2025
Centre de Vision Numérique, CentraleSupélec, Université Paris-Saclay, Inria, Gif-Sur-Yvette, France.
Conventional techniques for underwater source localization have traditionally relied on optimization methods, matched-field processing, beamforming, and, more recently, deep learning. However, these methods often fall short to fully exploit the data correlation crucial for accurate source localization. This correlation can be effectively captured using graphs, which consider the spatial relationship among data points through edges.
View Article and Find Full Text PDFGIMS: Image matching system based on adaptive graph construction and graph neural network.
Neural Netw
August 2025
Faculty of Applied Science, University of British Columbia, Kelowna, Canada. Electronic address:
Feature-based image matching has extensive applications in computer vision. Keypoints detected in images can be naturally represented as graph structures, and Graph Neural Networks (GNNs) have been shown to outperform traditional deep learning techniques. Consequently, the paradigm of image matching via GNNs has gained significant prominence in recent academic research.
View Article and Find Full Text PDFA graph theory-based algorithm for the reduction of atmospheric chemical mechanisms.
PNAS Nexus
September 2025
Department of Chemical Engineering, Columbia University, New York, NY 10027, USA.
The atmospheric chemistry of volatile organic compounds (VOC) has a major influence on atmospheric pollutants and particle formation. Accurate modeling of this chemistry is essential for air quality models. Complete representations of VOC oxidation chemistry are far too large for spatiotemporal simulations of the atmosphere, necessitating reduced mechanisms.
View Article and Find Full Text PDFSpectrum Alignment for Robust 3D Point Cloud Correspondences Estimation.
IEEE Trans Vis Comput Graph
September 2025
Estimating dense point-to-point correspondences between two isometric shapes represented as 3D point clouds is a fundamental problem in geometry processing, with applications in texture and motion transfer. However, this task becomes particularly challenging when the shapes undergo non-rigid transformations, as is often the case with approximately isometric point clouds. Most existing algorithms address this challenge by establishing correspondences between functions defined on the shapes, rather than directly between points, because function mappings admit a linear representation in the spectral domain.
View Article and Find Full Text PDFCross-Reactivity of SARS-CoV-2 Antibodies With Typhoid Flagellar-H Protein.
Trop Med Int Health
September 2025
ImmunoCure - Center for Inflammatory Diseases, Karachi, Pakistan.
Background: Antigen cross-reactivity in infections may induce heterologous immunity, leading to immunological protection against widely divergent organisms. We hypothesised that this may be a factor in the varying intensity of COVID-19 infection globally.
Methods: During the COVID-19 pandemic, we tested 46 symptomatic patients for both COVID-19 antibodies and the Typhidot test.