Sciweavers

44 search results - page 3 / 9
» Learning What and How of Contextual Models for Scene Labelin...
Sort
View
IJCV
2008
151views more  IJCV 2008»
13 years 5 months ago
Describing Visual Scenes Using Transformed Objects and Parts
We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed...
Erik B. Sudderth, Antonio Torralba, William T. Fre...
ICCV
2011
IEEE
12 years 5 months ago
Annotator Rationales for Visual Recognition
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
Jeff Donahue, Kristen Grauman
JMLR
2010
104views more  JMLR 2010»
13 years 11 days ago
How to Explain Individual Classification Decisions
After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the...
David Baehrens, Timon Schroeter, Stefan Harmeling,...
NIPS
2004
13 years 7 months ago
Contextual Models for Object Detection Using Boosted Random Fields
We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which use boos...
Antonio Torralba, Kevin P. Murphy, William T. Free...
CCIA
2005
Springer
13 years 11 months ago
Classifying Natural Objects on Outdoor Scenes
We propose an hybrid and probabilistic classification of image regions belonging to scenes primarily containing natural objects, e.g. sky, trees, etc. as a first step in solving ...
Anna Bosch, Xavier Muñoz, Joan Martí...