Sciweavers

59 search results - page 7 / 12
» How Good are Local Features for Classes of Geometric Objects
Sort
View
CVPR
2003
IEEE
14 years 9 months ago
The Optimal Distance Measure for Object Detection
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
Shyjan Mahamud, Martial Hebert
CVPR
2006
IEEE
14 years 9 months ago
Reciprocal Image Features for Uncalibrated Helmholtz Stereopsis
Helmholtz stereopsis is a surface reconstruction method that exploits reciprocity for the recovery of 3D shape without an assumed BRDF model, and it has been shown to yield high q...
Todd Zickler
BMVC
2010
13 years 5 months ago
Improving bag-of-features action recognition with non-local cues
Local space-time features have recently shown promising results within Bag-of-Features (BoF) approach to action recognition in video. Pure local features and descriptors, however,...
Muhammad Muneeb Ullah, Sobhan Naderi Parizi, Ivan ...
ICCV
2009
IEEE
1022views Computer Vision» more  ICCV 2009»
15 years 15 days ago
Kernelized Locality-Sensitive Hashing for Scalable Image Search
Fast retrieval methods are critical for large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance fun...
Brian Kulis, Kristen Grauman
TIP
2011
255views more  TIP 2011»
13 years 2 months ago
Dictionary Learning for Stereo Image Representation
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
Ivana Tosic, Pascal Frossard