32 search results - page 4 / 7 » Detect2Rank: Combining Object Detectors Using Learning to Ra... |
CVPR
2008
IEEE
16 years 11 days ago
2008
IEEE
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
114
click to vote
CVPR
2004
IEEE
16 years 11 days ago
2004
IEEE
This paper introduces BoostMap, a method that can significantly reduce retrieval time in image and video database systems that employ computationally expensive distance measures, ...
VLDB
1990
ACM
15 years 2 months ago
1990
ACM
A probabilistic learning model for vague queries and missing or imprecise information in databases is described. Instead of retrieving only a set of answers, our approach yields a...
103
click to vote
WWW
2011
ACM
14 years 5 months ago
2011
ACM
Our objective is to improve the performance of keyword based image search engines by re-ranking their baseline results. To this end, we address three limitations of existing searc...
72
Voted
WWW
2009
ACM
15 years 11 months ago
2009
ACM
Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, a...