Sciweavers

128 search results - page 19 / 26
» On the Optimal Choice of Quality Metric in Image Compression
Sort
View
CVPR
2008
IEEE
14 years 10 months ago
Learning class-specific affinities for image labelling
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
Dhruv Batra, Rahul Sukthankar, Tsuhan Chen
ICIP
1998
IEEE
14 years 10 months ago
An Efficient Motion Estimation Algorithm based on Tracing Techniques on Large Search Windows
Motion estimation represents the most computationally intensive task for all efficient motion compensated compression standards. This fact, despite the several eflorts aiming at r...
Marco Mattavelli, Giorgio Zoia
TMI
2010
112views more  TMI 2010»
13 years 7 months ago
Regularized Interpolation for Noisy Images
Abstract—Interpolation is the means by which a continuouslydefined model is fit to discrete data samples. When the data samples are exempt of noise, it seems desirable to build...
Sathish Ramani, Philippe Thévenaz, Michael ...
CVPR
2011
IEEE
13 years 4 months ago
From Region Similarity to Category Discovery
The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed i...
Carolina Galleguillos, Brian McFee, Serge Belongie...
CIVR
2007
Springer
119views Image Analysis» more  CIVR 2007»
14 years 2 months ago
An in-memory relevance feedback technique for high-performance image retrieval systems
Content-based image retrieval with relevant feedback has been widely adopted as the query model of choice for improved effectiveness in image retrieval. The effectiveness of thi...
Ning Yu, Khanh Vu, Kien A. Hua