Sciweavers

372 search results - page 24 / 75
» The Tower of Knowledge Scheme for Learning in Computer Visio...
Sort
View
CVPR
2006
IEEE
14 years 10 months ago
Automatic Discovery of Action Taxonomies from Multiple Views
We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...
Daniel Weinland, Rémi Ronfard, Edmond Boyer
CVPR
2012
IEEE
11 years 11 months ago
Pose pooling kernels for sub-category recognition
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
Ning Zhang, Ryan Farrell, Trevor Darrell
ICPR
2006
IEEE
14 years 9 months ago
Robust Recursive Learning for Foreground Region Detection in Videos with Quasi-Stationary Backgrounds
Detecting regions of interest in video sequences is the most important task in many high level video processing applications. In this paper a robust technique based on recursive l...
Alireza Tavakkoli, George Bebis, Mircea Nicolescu
ICMCS
2009
IEEE
415views Multimedia» more  ICMCS 2009»
13 years 6 months ago
A new localized superpixel Markov random field for image segmentation
In this paper, we present a novel localized Markov random field (MRF) method based on superpixels for region segmentation. Early vision problems could be formulated as pixel label...
Xiaofeng Wang, Xiao-Ping Zhang
CVPR
2009
IEEE
15 years 3 months ago
Active Learning for Large Multi-class Problems
Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. Unfortunately, existing active learning methods ...
Prateek Jain (University of Texas at Austin), Ashi...