Abstract | ||
---|---|---|
We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely
to be good segmentations of different objects. Our key objectives are completeness and diversity: every object should have
at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations
by performing graph cuts based on a seed region and a learned affinity function. Then, the regions are ranked using structured
learning based on various cues. Our experiments on BSDS and PASCAL VOC 2008 demonstrate our ability to find most objects within
a small bag of proposed regions.
|
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15555-0_42 | European Conference on Computer Vision |
Keywords | Field | DocType |
category independent object proposal,affinity function,seed region,proposed region,good segmentation,small bag,category-independent method,PASCAL VOC,good proposed region,top-ranked region,diverse set | Cut,Computer vision,Ranking,Pattern recognition,Computer science,Structured prediction,Active appearance model,Artificial intelligence,Completeness (statistics),Machine learning | Conference |
Volume | ISSN | ISBN |
6315 | 0302-9743 | 3-642-15554-5 |
Citations | PageRank | References |
67 | 10.59 | 24 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ian Endres | 1 | 188 | 17.33 |
Derek Hoiem | 2 | 4998 | 302.66 |