Search For:

Displaying 1-9 out of 9 total
Convex shape decomposition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hairong Liu, Wenyu Liu, Longin Jan Latecki
Issue Date:June 2010
pp. 97-104
In this paper, we propose a new shape decomposition method, called convex shape decomposition. We formalize the convex decomposition problem as an integer linear programming problem, and obtain approximate optimal solution by minimizing the total cost of d...
 
Visual Curvature
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By HaiRong Liu, Longin Jan Latecki, WenYu Liu, Xiang Bai
Issue Date:June 2007
pp. 1-8
In this paper, we propose a new definition of curvature, called visual curvature. It is based on statistics of the extreme points of the height functions computed over all directions. By gradually ignoring relatively small heights, a single parameter multi...
 
Dense Subgraph Partition of Positive Hypergraph
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hairong Liu,Longin Jan Latecki,Shuicheng Yan
Issue Date:August 2014
pp. 1
In this paper, we present a novel partition framework, called dense subgraph partition (DSP), to automatically, precisely and efficiently decompose a positive hypergraph into dense subgraphs. A positive hypergraph is a graph or hypergraph whose edges, exce...
 
Fast Detection of Dense Subgraphs with Iterative Shrinking and Expansion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hairong Liu,L. J. Latecki, Shuicheng Yan
Issue Date:September 2013
pp. 2131-2142
In this paper, we propose an efficient algorithm to detect dense subgraphs of a weighted graph. The proposed algorithm, called the shrinking and expansion algorithm (SEA), iterates between two phases, namely, the expansion phase and the shrink phase, until...
 
Efficient structure detection via random consensus graph
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Hairong Liu, Shuicheng Yan
Issue Date:June 2012
pp. 574-581
In this paper, we propose an efficient method to detect the underlying structures in data. The same as RANSAC, we randomly sample MSSs (minimal size samples) and generate hypotheses. Instead of analyzing each hypothesis separately, the consensus informatio...
 
Automated assembly of shredded pieces from multiple photos
Found in: Multimedia and Expo, IEEE International Conference on
By Shengjiao Cao, Hairong Liu, Shuicheng Yan
Issue Date:July 2010
pp. 358-363
In this paper, we investigate the problem of automated assembly of shredded pieces from multiple photos. We first establish candidate matchings between fragments by using both shape and appearance information. A weighted graph whose vertices represent shre...
 
Common visual pattern discovery via spatially coherent correspondences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hairong Liu, Shuicheng Yan
Issue Date:June 2010
pp. 1609-1616
We investigate how to discover all common visual patterns within two sets of feature points. Common visual patterns generally share similar local features as well as similar spatial layout. In this paper these two types of information are integrated and en...
 
Large-scale multilabel propagation based on efficient sparse graph construction
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Hairong Liu, Shuicheng Yan, Tat-Seng Chua, Xiangyu Chen, Yadong Mu, Yong Rui
Issue Date:December 2013
pp. 1-20
With the popularity of photo-sharing websites, the number of web images has exploded into unseen magnitude. Annotating such large-scale data will cost huge amount of human resources and is thus unaffordable. Motivated by this challenging problem, we propos...
     
Towards efficient sparse coding for scalable image annotation
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Jialie Shen, Junshi Huang, Shuicheng Yan, Hairong Liu
Issue Date:October 2013
pp. 947-956
Nowadays, content-based retrieval methods are still the development trend of the traditional retrieval systems. Image labels, as one of the most popular approaches for the semantic representation of images, can fully capture the representative information ...
     
 1