Sciweavers

CVPR
2012
IEEE
11 years 7 months ago
Segmentation using superpixels: A bipartite graph partitioning approach
Grouping cues can affect the performance of segmentation greatly. In this paper, we show that superpixels (image segments) can provide powerful grouping cues to guide segmentation...
Zhenguo Li, Xiao-Ming Wu, Shih-Fu Chang
COMSNETS
2012
222views more  COMSNETS 2012»
12 years 23 days ago
Exploring the design space of social network-based Sybil defenses
—Recently, there has been significant research interest in leveraging social networks to defend against Sybil attacks. While much of this work may appear similar at first glanc...
Bimal Viswanath, Mainack Mondal, Allen Clement, Pe...
ASUNAM
2011
IEEE
12 years 5 months ago
Content-based Modeling and Prediction of Information Dissemination
—Social and communication networks across the world generate vast amounts of graph-like data each day. The modeling and prediction of how these communication structures evolve ca...
Kathy Macropol, Ambuj K. Singh
JAIR
2011
173views more  JAIR 2011»
12 years 8 months ago
Analyzing Search Topology Without Running Any Search: On the Connection Between Causal Graphs and h+
The ignoring delete lists relaxation is of paramount importance for both satisficing and optimal planning. In earlier work, it was observed that the optimal relaxation heuristic ...
J. Hoffmann
COMPGEOM
2011
ACM
12 years 8 months ago
Reeb graphs: approximation and persistence
Given a continuous function f : X → IR on a topological space X, its level set f−1 (a) changes continuously as the real value a changes. Consequently, the connected components...
Tamal K. Dey, Yusu Wang
AIPS
2011
12 years 8 months ago
Where Ignoring Delete Lists Works, Part II: Causal Graphs
The ignoring delete lists relaxation is of paramount importance for both satisficing and optimal planning. In earlier work (Hoffmann 2005), it was observed that the optimal relax...
Joerg Hoffmann
TSP
2011
197views more  TSP 2011»
12 years 12 months ago
Group Object Structure and State Estimation With Evolving Networks and Monte Carlo Methods
—This paper proposes a technique for motion estimation of groups of targets based on evolving graph networks. The main novelty over alternative group tracking techniques stems fr...
Amadou Gning, Lyudmila Mihaylova, Simon Maskell, S...
ICMCS
2010
IEEE
227views Multimedia» more  ICMCS 2010»
13 years 2 months ago
Interactive viewpoint-space navigation for visual-audio exhibition of painting
In this paper, we present a system for exhibiting a Chinese landscape painting about 900 years old. There are three parts in our system: (1) we allocate a voice dubbing or backgro...
Wei Ma, Yang Liu, Yizhou Wang, Yingqing Xu, Hongbi...
ICMLA
2009
13 years 2 months ago
Exact Graph Structure Estimation with Degree Priors
We describe a generative model for graph edges under specific degree distributions which admits an exact and efficient inference method for recovering the most likely structure. T...
Bert Huang, Tony Jebara
JVCA
2007
132views more  JVCA 2007»
13 years 4 months ago
Interactive and flexible motion transition
In this paper, we present an example-based motion synthesis technique. Users can interactively control the virtual character to perform desired actions in any order. The desired a...
Jen-Yu Peng, I-Chen Lin, Jui-Hsiang Chao, Yan-Ju C...