Sciweavers

533 search results - page 76 / 107
» Learning to extract form labels
Sort
View
DEXA
2011
Springer
234views Database» more  DEXA 2011»
13 years 11 months ago
Learning Top-k Transformation Rules
Record linkage identifies multiple records referring to the same entity even if they are not bit-wise identical. It is thus an essential technology for data integration and data c...
Sunanda Patro, Wei Wang
ACL
2010
14 years 10 months ago
Unsupervised Ontology Induction from Text
Extracting knowledge from unstructured text is a long-standing goal of NLP. Although learning approaches to many of its subtasks have been developed (e.g., parsing, taxonomy induc...
Hoifung Poon, Pedro Domingos
CVPR
2010
IEEE
15 years 7 months ago
Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
ICCV
2011
IEEE
13 years 12 months ago
Relative Attributes
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Devi Parikh, Kristen Grauman
CVPR
2007
IEEE
16 years 1 months ago
Composite Models of Objects and Scenes for Category Recognition
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
David J. Crandall, Daniel P. Huttenlocher