Sciweavers

2030 search results - page 21 / 406
» Extremal Problems of Information Combining
Sort
View
ICPR
2000
IEEE
14 years 9 days ago
Vectorization in Graphics Recognition: To Thin or Not to Thin
Vectorization, i.e. raster–to–vector conversion, is a central part of graphics recognition problems. In this paper, we discuss the pros and the cons of basing one’s vectoriz...
Karl Tombre, Salvatore Tabbone
ICITA
2005
IEEE
14 years 1 months ago
Combining Diversity-Based Active Learning with Discriminant Analysis in Image Retrieval
Small-sample learning in image retrieval is a pertinent and interesting problem. Relevance feedback is an active area of research that seeks to find algorithms that are robust wi...
Charlie K. Dagli, ShyamSundar Rajaram, Thomas S. H...
CLEF
2008
Springer
13 years 9 months ago
Combining Logic and Machine Learning for Answering Questions
Abstract. LogAnswer is a logic-oriented question answering system developed by the AI research group at the University of Koblenz-Landau and by the IICS at the University of Hagen....
Ingo Glöckner, Björn Pelzer
ECCV
2010
Springer
14 years 29 days ago
Object, Scene and Actions: Combining Multiple Features for Human Action Recognition
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
JAIR
2007
159views more  JAIR 2007»
13 years 7 months ago
Combination Strategies for Semantic Role Labeling
This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model...
Mihai Surdeanu, Lluís Màrquez, Xavie...