Sciweavers

835 search results - page 140 / 167
» Optimal Linear Representations of Images for Object Recognit...
Sort
View
ICCV
2009
IEEE
16 years 4 months ago
Image Segmentation with A Bounding Box Prior
User-provided object bounding box is a simple and popular interaction paradigm considered by many existing interactive image segmentation frameworks. However, these frameworks t...
Victor Lempitsky, Pushmeet Kohli, Carsten Rother, ...
ICCV
2007
IEEE
16 years 1 months ago
A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting
An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper. The proposed technique is based on the optimal, linear time, co...
Xue Bai, Guillermo Sapiro
ICCV
2007
IEEE
16 years 1 months ago
Vector Quantizing Feature Space with a Regular Lattice
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
Tinne Tuytelaars, Cordelia Schmid
GMP
2006
IEEE
118views Solid Modeling» more  GMP 2006»
15 years 5 months ago
Computing a Family of Skeletons of Volumetric Models for Shape Description
Skeletons are important shape descriptors in object representation and recognition. Typically, skeletons of volumetric models are computed using iterative thinning. However, tradi...
Tao Ju, Matthew L. Baker, Wah Chiu
PRL
2007
131views more  PRL 2007»
14 years 11 months ago
A new look at discriminative training for hidden Markov models
ct 7 Discriminative training for hidden Markov models (HMMs) has been a central theme in speech recognition research for many years. 8 One most popular technique is minimum classiï...
Xiaodong He, Li Deng