Sciweavers

119 search results - page 6 / 24
» Nomograms for visualizing support vector machines
Sort
View
TOG
2012
245views Communications» more  TOG 2012»
11 years 10 months ago
How do humans sketch objects?
Humans have used sketching to depict our visual world since prehistoric times. Even today, sketching is possibly the only rendering technique readily available to all humans. This...
Mathias Eitz, James Hays, Marc Alexa
AUSAI
2008
Springer
13 years 9 months ago
Character Recognition Using Hierarchical Vector Quantization and Temporal Pooling
In recent years, there has been a cross-fertilization of ideas between computational neuroscience models of the operation of the neocortex and artificial intelligence models of mac...
John Thornton, Jolon Faichney, Michael Blumenstein...
IBPRIA
2009
Springer
14 years 10 days ago
Class Representative Visual Words for Category-Level Object Recognition
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such ...
Roberto Javier López-Sastre, Tinne Tuytelaa...
ICCV
2011
IEEE
12 years 7 months ago
Struck: Structured Output Tracking with Kernels
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
Sam Hare, Amir Saffari, Philip H.S. Torr
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