Sciweavers

45 search results - page 3 / 9
» Two-Dimensional Active Learning for image classification
Sort
View
CVPR
2010
IEEE
14 years 2 months ago
Beyond Active Noun Tagging: Modeling Contextual Interactions for Multi-Class Active Learning
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
Behjat Siddiquie, Abhinav Gupta
CVPR
2010
IEEE
14 years 2 months ago
Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
SDM
2004
SIAM
187views Data Mining» more  SDM 2004»
13 years 7 months ago
Class-Specific Ensembles for Active Learning
In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is...
Amit Mandvikar, Huan Liu
ICIP
2010
IEEE
13 years 4 months ago
Texture classification via patch-based sparse texton learning
Texture classification is a classical yet still active topic in computer vision and pattern recognition. Recently, several new texture classification approaches by modeling textur...
Jin Xie, Lei Zhang, Jane You, David Zhang
DAGM
2006
Springer
13 years 10 months ago
Handling Camera Movement Constraints in Reinforcement Learning Based Active Object Recognition
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Christian Derichs, Heinrich Niemann