Taxonomic multi-class prediction and person layout using efficient structured ranking
In computer vision efficient multi-class classification is becoming a key problem as the field develops and the number of object classes to be identified increases. Often objects might have some sort of structure such as a taxonomy in which the mis-classification score for object classes close by, u...
Auteurs principaux: | Mittal, A, Blaschko, MB, Zisserman, A, Torr, PHS |
---|---|
Format: | Conference item |
Langue: | English |
Publié: |
Springer
2012
|
Documents similaires
-
Simultaneous object detection and ranking with weak supervision
par: Blaschko, MB, et autres
Publié: (2011) -
Hand detection using multiple proposals
par: Mittal, A, et autres
Publié: (2011) -
Efficient discriminative learning of parts-based models
par: Kumar, MP, et autres
Publié: (2010) -
OBJCUT: efficient segmentation using top-down and bottom-up cues
par: Kumar, MP, et autres
Publié: (2009) -
Feature based methods for structure and motion estimation
par: Torr, PHS, et autres
Publié: (2002)