Sciweavers

171 search results - page 10 / 35
» Selection of Scale-Invariant Parts for Object Class Recognit...
Sort
View
ICCV
2011
IEEE
13 years 11 months ago
Segmentation as Selective Search for Object Recognition
Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/ For object recognition, the current state-of-the-art is based on exhaustive search. However, to ...
K van de Sande, J Uijlings, T Gevers, A Smeulders
CVPR
2008
IEEE
15 years 11 months ago
Unsupervised feature selection via distributed coding for multi-view object recognition
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem...
Chris Mario Christoudias, Raquel Urtasun, Trevor D...
NIPS
2004
14 years 11 months ago
Conditional Random Fields for Object Recognition
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
Ariadna Quattoni, Michael Collins, Trevor Darrell
MVA
1990
101views Computer Vision» more  MVA 1990»
14 years 11 months ago
Recognition of Parametrised Models from 3D Data
This paper describes work done as part of the Oxford AGV (Autonomous Guided Vehicle) project [2] towards recognition of classes of objects to be encountered in a factory environme...
Ian D. Reid
ICCV
2011
IEEE
13 years 9 months ago
Informative Feature Selection for Object Recognition via Sparse PCA
Bag-of-words (BoW) methods are a popular class of object recognition methods that use image features (e.g., SIFT) to form visual dictionaries and subsequent histogram vectors to r...
Nikhil Naikal, Allen Y. Yang, S. Shankar Sastry