Saliency Detection Using Color Spatial Variance Weighted Graph Model

2013 ◽  
Author(s):  
Xiaoyun Yan ◽  
Yuehuan Wang ◽  
Mengmeng Song ◽  
Man Jiang
Keyword(s):  
Saliency Detection ◽  
Graph Model ◽  
Weighted Graph ◽  
Spatial Variance

A Large Margin Learning Method for Matching Images of Natural Objects with Different Dimensions

2015 ◽  
pp. 323-341
Author(s):  
Haoyi Zhou ◽  
Jun Zhou ◽  
Haichuan Yang ◽  
Cheng Yan ◽  
Xiao Bai ◽  
...  
Keyword(s):  
Feature Matching ◽  
Hyperspectral Image ◽  
Graph Matching ◽  
Graph Model ◽  
Image Data ◽  
Weighted Graph ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Natural Objects ◽  
Different Dimensions

Imaging devices are of increasing use in environmental research requiring an urgent need to deal with such issues as image data, feature matching over different dimensions. Among them, matching hyperspectral image with other types of images is challenging due to the high dimensional nature of hyperspectral data. This chapter addresses this problem by investigating structured support vector machines to construct and learn a graph-based model for each type of image. The graph model incorporates both low-level features and stable correspondences within images. The inherent characteristics are depicted by using a graph matching algorithm on extracted weighted graph models. The effectiveness of this method is demonstrated through experiments on matching hyperspectral images to RGB images, and hyperspectral images with different dimensions on images of natural objects.

Community-Based Weighted Graph Model for Valence-Arousal Prediction of Affective Words

2016 ◽  
Vol 24 (11) ◽  
pp. 1957-1968 ◽  
Author(s):  
Jin Wang ◽  
Liang-Chih Yu ◽  
K. Robert Lai ◽  
Xuejie Zhang
Keyword(s):  
Graph Model ◽  
Weighted Graph ◽  
Community Based

scholarly journals Improved Bayesian Saliency Detection Based on BING and Graph Model

2015 ◽  
Vol 9 (1) ◽  
pp. 648-656
Author(s):  
Lv Jianyong ◽  
Tang Zhenmin ◽  
Xu Wei
Keyword(s):  
Saliency Detection ◽  
Graph Model

Airspace sectorisation via a weighted graph model

2014 ◽  
Vol 118 (1201) ◽  
pp. 267-274 ◽  
Author(s):  
D.F. Zhang ◽  
Y.Z. chen
Keyword(s):  
Traffic Congestion ◽  
Minimum Distance ◽  
Graph Model ◽  
Weighted Graph ◽  
Air Traffic ◽  
Geometric Constraints ◽  
Distance Constraint ◽  
Flight Delays ◽  
Traffic Demand ◽  
Bad Weather

With the development of air traffic, flight delays happen frequently due to bad weather and traffic congestion. The problem can be solved partly by certain strategies, such as changing air routes. However, rerouting leads to a global imbalance in controller workload of current sectors and to an increase in co-ordination workload, and the workloads of some sectors may be beyond the controller’s ability to manage. Thus, airspace sectorisation is expected to migrate from the current static sectors to dynamically-changing ones capable of adapting to traffic demand. Besides addressing imbalance and controlling the increase in workload, the sectorisation has to meet additional geometric constraints such as convexity, connectivity, and minimum distance constraint.

A Power Network Partitioning Method Based on Local Similarity Measure

2012 ◽  
Vol 588-589 ◽  
pp. 364-367
Author(s):  
Tao Wang ◽  
Heng Zhou ◽  
Pan Zou
Keyword(s):  
Hierarchical Clustering ◽  
Similarity Measure ◽  
Reactive Power ◽  
Graph Model ◽  
Weighted Graph ◽  
Local Similarity ◽  
Network Partitioning ◽  
Power Network ◽  
Clustering Method ◽  
Partitioning Algorithm

A power network partitioning model based on the weighed local similarity measure is presented in this paper considering the regional decoupling characteristics of reactive power. A weighted graph model of reactive power network is established and a new measurement of local similarity based on weighed graph is defined. To utilize our measurement of similarity to partition reactive power network, a partitioning algorithm based on generalized ward hierarchical clustering method is proposed. The algorithm can ensure balance of the reactive power inside partition. Applying the proposed algorithm to IEEE 39-bus system, the results show that the proposed algorithm is feasible and effective.

scholarly journals CANONICAL REPRESENTATIVES FOR DIVISOR CLASSES ON TROPICAL CURVES AND THE MATRIX–TREE THEOREM

2014 ◽  
Vol 2 ◽  
Author(s):  
YANG AN ◽  
MATTHEW BAKER ◽  
GREG KUPERBERG ◽  
FARBOD SHOKRIEH
Keyword(s):  
Equivalence Class ◽  
Theta Functions ◽  
Graph Model ◽  
Weighted Graph ◽  
Combinatorial Proof ◽  
Geometric Proof ◽  
Formula One ◽  
Dual Version ◽  
The Matrix ◽  
Integral Version

AbstractLet $\def \xmlpi #1{}\def \mathsfbi #1{\boldsymbol {\mathsf {#1}}}\let \le =\leqslant \let \leq =\leqslant \let \ge =\geqslant \let \geq =\geqslant \def \Pr {\mathit {Pr}}\def \Fr {\mathit {Fr}}\def \Rey {\mathit {Re}}\Gamma $ be a compact tropical curve (or metric graph) of genus $g$. Using the theory of tropical theta functions, Mikhalkin and Zharkov proved that there is a canonical effective representative (called a break divisor) for each linear equivalence class of divisors of degree $g$ on $\Gamma $. We present a new combinatorial proof of the fact that there is a unique break divisor in each equivalence class, establishing in the process an ‘integral’ version of this result which is of independent interest. As an application, we provide a ‘geometric proof’ of (a dual version of) Kirchhoff’s celebrated matrix–tree theorem. Indeed, we show that each weighted graph model $G$ for $\Gamma $ gives rise to a canonical polyhedral decomposition of the $g$-dimensional real torus $\mathrm{Pic}^g(\Gamma )$ into parallelotopes $C_T$, one for each spanning tree $T$ of $G$, and the dual Kirchhoff theorem becomes the statement that the volume of $\mathrm{Pic}^g(\Gamma )$ is the sum of the volumes of the cells in the decomposition.

A Large Margin Learning Method for Matching Images of Natural Objects With Different Dimensions

2019 ◽  
pp. 561-580
Author(s):  
Haoyi Zhou ◽  
Jun Zhou ◽  
Haichuan Yang ◽  
Cheng Yan ◽  
Xiao Bai ◽  
...  
Keyword(s):  
Feature Matching ◽  
Hyperspectral Image ◽  
Graph Matching ◽  
Graph Model ◽  
Image Data ◽  
Weighted Graph ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Natural Objects ◽  
Different Dimensions

Imaging devices are of increasing use in environmental research requiring an urgent need to deal with such issues as image data, feature matching over different dimensions. Among them, matching hyperspectral image with other types of images is challenging due to the high dimensional nature of hyperspectral data. This chapter addresses this problem by investigating structured support vector machines to construct and learn a graph-based model for each type of image. The graph model incorporates both low-level features and stable correspondences within images. The inherent characteristics are depicted by using a graph matching algorithm on extracted weighted graph models. The effectiveness of this method is demonstrated through experiments on matching hyperspectral images to RGB images, and hyperspectral images with different dimensions on images of natural objects.

Sign in / Sign up

Export Citation Format

Share Document