Sciweavers

295 search results - page 33 / 59
» An iterative unsupervised learning method for information di...
Sort
View
ECCV
2010
Springer
14 years 17 days ago
Learning to Detect Roads in High-Resolution Aerial Images
Abstract. Reliably extracting information from aerial imagery is a difficult problem with many practical applications. One specific case of this problem is the task of automatica...
CVPR
2010
IEEE
14 years 4 months ago
Far-Sighted Active Learning on a Budget for Image and Video Recognition
Active learning methods aim to select the most informative unlabeled instances to label first, and can help to focus image or video annotations on the examples that will most impr...
Sudheendra Vijayanarasimhan, Prateek Jain, Kristen...
NIPS
2007
13 years 9 months ago
Discriminative Batch Mode Active Learning
Active learning sequentially selects unlabeled instances to label with the goal of reducing the effort needed to learn a good classifier. Most previous studies in active learning...
Yuhong Guo, Dale Schuurmans
MM
2003
ACM
84views Multimedia» more  MM 2003»
14 years 28 days ago
Temporal event clustering for digital photo collections
We present similarity-based methods to cluster digital photos by time and image content. The approach is general, unsupervised, and makes minimal assumptions regarding the structu...
Matthew L. Cooper, Jonathan Foote, Andreas Girgens...
MVA
2007
154views Computer Vision» more  MVA 2007»
13 years 9 months ago
Fisher Non-negative Matrix Factorization with Pairwise Weighting
Non-negative matrix factorization (NMF) is a powerful feature extraction method for finding parts-based, linear representations of non-negative data . Inherently, it is unsupervis...
Xi Li, Kazuhiro Fukui