Sciweavers

382 search results - page 47 / 77
» Using Maximum Entropy for Automatic Image Annotation
Sort
View
COLING
2000
13 years 9 months ago
A Hybrid Japanese Parser with Hand-crafted Grammar and Statistics
This paper describes a hybrid parsing method for Japanese which uses both a hand-crafted grammar and a statistical technique. The key feature of our system is that in order to est...
Hiroshi Kanayama, Kentaro Torisawa, Yutaka Mitsuis...
ANLP
2000
97views more  ANLP 2000»
13 years 9 months ago
Trainable Methods for Surface Natural Language Generation
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Adwait Ratnaparkhi
IBPRIA
2003
Springer
14 years 1 months ago
Comparison of Log-linear Models and Weighted Dissimilarity Measures
Abstract. We compare two successful discriminative classification algorithms on three databases from the UCI and STATLOG repositories. The two approaches are the log-linear model ...
Daniel Keysers, Roberto Paredes, Enrique Vidal, He...
CVPR
2012
IEEE
11 years 10 months ago
Large-scale knowledge transfer for object localization in ImageNet
ImageNet is a large-scale database of object classes with millions of images. Unfortunately only a small fraction of them is manually annotated with bounding-boxes. This prevents ...
Matthieu Guillaumin, Vittorio Ferrari
MM
2006
ACM
179views Multimedia» more  MM 2006»
14 years 1 months ago
ZooMICSS: a zoomable map image collection sensemaking system (the Katrina Rita context)
Access to devices that integrate Global Positioning data with image and sound acquisition becomes more common, enabling people to build large collections of locative multimedia. A...
Ross Graeber, Andruid Kerne, M. Kathryn Henderson