Sciweavers

114 search results - page 16 / 23
» The Pascal Visual Object Classes (VOC) Challenge
Sort
View
CVPR
2007
IEEE
14 years 9 months ago
Using Segmentation to Verify Object Hypotheses
We present an approach for object recognition that combines detection and segmentation within a efficient hypothesize/test framework. Scanning-window template classifiers are the ...
Deva Ramanan
ICCV
2007
IEEE
14 years 9 months ago
Proximity Distribution Kernels for Geometric Context in Category Recognition
We propose using the proximity distribution of vectorquantized local feature descriptors for object and category recognition. To this end, we introduce a novel "proximity dis...
Haibin Ling, Stefano Soatto
ICCV
2011
IEEE
12 years 7 months ago
Multi-hypothesis Motion Planning for Visual Object Tracking
In this paper, we propose a long-term motion model for visual object tracking. In crowded street scenes, persistent occlusions are a frequent challenge for tracking algorithm and ...
Haifeng Gong, Jack Sim, Maxim Likhachev, Jianbo Sh...
CVPR
2012
IEEE
11 years 9 months ago
Meta-class features for large-scale object categorization on a budget
In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
Alessandro Bergamo, Lorenzo Torresani
SPIESR
2004
117views Database» more  SPIESR 2004»
13 years 8 months ago
Image database clustering with SVM-based class personalization
To allow efficient browsing of large image collections, we have to provide a summary of its visual content. We present in this paper a robust approach to organize image databases:...
Bertrand Le Saux, Nozha Boujemaa