Sciweavers

185 search results - page 21 / 37
» Automatic Image Annotation Using Maximum Entropy Model
Sort
View
DAGM
2008
Springer
13 years 9 months ago
Learning Visual Compound Models from Parallel Image-Text Datasets
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...
SSPR
2004
Springer
14 years 27 days ago
Adaptive Context for a Discrete Universal Denoiser
Abstract. Statistical analysis of spatially uniform signal contexts allows Discrete Universal Denoiser (DUDE) to effectively correct signal errors caused by a discrete symmetric me...
Georgy L. Gimel'farb
CORR
2011
Springer
301views Education» more  CORR 2011»
12 years 11 months ago
Human Activity Detection from RGBD Images
Being able to detect and recognize human activities is important for making personal assistant robots useful in performing assistive tasks. The challenge is to develop a system th...
Jaeyong Sung, Colin Ponce, Bart Selman, Ashutosh S...
MM
2003
ACM
132views Multimedia» more  MM 2003»
14 years 24 days ago
On image auto-annotation with latent space models
Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of t...
Florent Monay, Daniel Gatica-Perez
LREC
2008
99views Education» more  LREC 2008»
13 years 9 months ago
Evaluating and Extending the Coverage of HPSG Grammars: A Case Study for German
In this work, we examine and attempt to extend the coverage of a German HPSG grammar. We use the grammar to parse a corpus of newspaper text and evaluate the proportion of sentenc...
Jeremy Nicholson, Valia Kordoni, Yi Zhang 0003, Ti...