Sciweavers

46 search results - page 2 / 10
» A novel framework to elucidate core classes in a dataset
Sort
View
PRL
2007
166views more  PRL 2007»
13 years 4 months ago
Boosted Landmarks of Contextual Descriptors and Forest-ECOC: A novel framework to detect and classify objects in cluttered scene
In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-...
Sergio Escalera, Oriol Pujol, Petia Radeva
CVPR
2012
IEEE
11 years 7 months ago
RALF: A reinforced active learning formulation for object class recognition
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Sandra Ebert, Mario Fritz, Bernt Schiele
CVPR
2007
IEEE
14 years 7 months ago
Multiple Class Segmentation Using A Unified Framework over Mean-Shift Patches
Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class objec...
Lin Yang, Peter Meer, David J. Foran
CVPR
2006
IEEE
14 years 7 months ago
A Conic Section Classifier and its Application to Image Datasets
Many problems in computer vision involving recognition and/or classification can be posed in the general framework of supervised learning. There is however one aspect of image dat...
Arunava Banerjee, Santhosh Kodipaka, Baba C. Vemur...
FPGA
2007
ACM
124views FPGA» more  FPGA 2007»
13 years 11 months ago
A practical FPGA-based framework for novel CMP research
Chip-multiprocessors are quickly gaining momentum in all segments of computing. However, the practical success of CMPs strongly depends on addressing the difficulty of multithread...
Sewook Wee, Jared Casper, Njuguna Njoroge, Yuriy T...