Name
Abstract | ||
|---|---|---|
In this paper, we propose a novel framework for modeling image-dependent contextual relationships using graph-based context model. This approach enables us to selectively utilize the contextual relationships suitable for an input query image. We introduce a context link view of contextual knowledge, where the relationship between a pair of annotated regions is represented as a context link on a similarity graph of regions. Link analysis techniques are used to estimate the pairwise context scores of all pairs of unlabeled regions in the input image. Our system integrates the learned context scores into a Markov Random Field (MRF) framework in the form of pairwise cost and infers the semantic segmentation result by MRF optimization. Experimental results on object class segmentation show that the proposed graph-based context model outperforms the current state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/CVPR.2012.6247995 | CVPR |
Keywords | Field | DocType |
context score,context link,link analysis technique,pairwise context score estimation,random processes,contextual relationship,learning (artificial intelligence),semantic segmentation,graph-based context model,link analysis,image segmentation,similarity graph,contextual knowledge,estimation theory,image-dependent contextual relationship,pairwise context score,image retrieval,object class segmentation,proposed graph-based context model,markov random field optimization,graph theory,object relationship learning,annotated region,image-dependent contextual relationship modeling,object relationship,markov processes,image querying,context link view,visualization,context modeling,learning artificial intelligence | Markov random field,Computer science,Link analysis,Image retrieval,Image segmentation,Context model,Artificial intelligence,Graph theory,Computer vision,Pairwise comparison,Pattern recognition,Segmentation,Machine learning | Conference |
Volume | Issue | ISSN |
2012 | 1 | 1063-6919 E-ISBN : 978-1-4673-1227-1 |
ISBN | Citations | PageRank |
978-1-4673-1227-1 | 12 | 0.60 |
References | Authors | |
22 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Heesoo Myeong | 1 | 23 | 1.79 |
| Ju Yong Chang | 2 | 105 | 9.64 |
| Kyoung Mu Lee | 3 | 3228 | 153.84 |