Abstract | ||
---|---|---|
This paper presents a nonparametric approach to semantic parsing using small patches and simple gradient, color and location features. We learn the relevance of individual feature channels at test time using a locally adaptive distance metric. To further improve the accuracy of the nonparametric approach, we examine the importance of the retrieval set used to compute the nearest neighbours using a novel semantic descriptor to retrieve better candidates. The approach is validated by experiments on several datasets used for semantic parsing demonstrating the superiority of the method compared to the state of art approaches. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPR.2013.405 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
image colour analysis,image segmentation,adaptive feature relevance,color features,gradient features,individual feature channels,locally adaptive distance metric,location features,nearest neighbours,nonparametric scene parsing,semantic context,semantic descriptor,semantic parsing,semantic segmentation,feature relevance,scene understanding,semantic segmentation | Semantic similarity,Computer vision,Pattern recognition,Computer science,Metric (mathematics),Communication channel,Image segmentation,Semantic context,Nonparametric statistics,Artificial intelligence,Feature relevance,Parsing | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
42 | 1.02 | 30 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gautam Singh | 1 | 103 | 9.31 |
Jana Kosecká | 2 | 1523 | 129.85 |