Sciweavers

342 search results - page 20 / 69
» Learning from Ambiguously Labeled Images
Sort
View
CVPR
2008
IEEE
13 years 8 months ago
Joint multi-label multi-instance learning for image classification
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both ...
Zheng-Jun Zha, Xian-Sheng Hua, Tao Mei, Jingdong W...
IJCV
2007
157views more  IJCV 2007»
13 years 8 months ago
Recovering Surface Layout from an Image
Humans have an amazing ability to instantly grasp the overall 3D structure of a scene – ground orientation, relative positions of major landmarks, etc – even from a single ima...
Derek Hoiem, Alexei A. Efros, Martial Hebert

Publication
922views
15 years 3 months ago
Multi-Class Active Learning for Image Classification
One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
Ajay J. Joshi, Fatih Porikli, Nikolaos Papanikolop...
ICPR
2008
IEEE
14 years 9 months ago
Extraction of shoe-print patterns from impression evidence using Conditional Random Fields
Impression evidence in the form of shoe-prints are commonly found in crime scenes. A critical step in automatic shoe-print identification is extraction of the shoe-print pattern. ...
Sargur N. Srihari, Veshnu Ramakrishnan
EMMCVPR
2005
Springer
14 years 2 months ago
Learning Hierarchical Shape Models from Examples
Abstract. We present an algorithm for automatically constructing a decompositional shape model from examples. Unlike current approaches to structural model acquisition, in which on...
Alex Levinshtein, Cristian Sminchisescu, Sven J. D...