• Sorted by Date • Classified by Publication Type • Sorted by First Author Last Name • Classified by Author Last Name •
P. Viswanathan, D. Meger, T. Southey, S. Helmer, S. McCann, M. Muja, M Dockrey, M. Joya, D. G. Lowe, J. J. Little, and Alan K. Mackworth. Combining Automated Visual Search and Place Categorization. In CVPR Workshop on Visual Place Categorization, 2009. Invited Paper
(unavailable)
Places in an environment can be described by the objectsthey contain. This paper discusses the completelyautomated integration of object detection and place classificationin a single system. We first perform automatedlearning of object-place relations from an online annotateddatabase. We then train object detectors on some of themost frequently occurring objects. Finally we use detectionscores as well as learned object-place relations to performplace classification of images. We also discuss areasfor improvement and the application of this work to informedvisual search. As a whole, the system demonstratesthe automated acquisition of training data containing labeledinstances (i.e. bounding boxes) and the performanceof a state-of-the-art object detection technique trained onthis data to perform place classification of realistic indoorscenes.
@InProceedings{PoojaCVPR09,
author = {P. Viswanathan and D. Meger and T. Southey and S. Helmer and S. McCann and M. Muja and M Dockrey and M. Joya and D. G. Lowe and J. J. Little and Alan K. Mackworth},
title = {Combining Automated Visual Search and Place Categorization},
year = {2009},
booktitle = {CVPR Workshop on Visual Place Categorization},
note = {{Invited Paper}},
abstract = {Places in an environment can be described by the objects
they contain. This paper discusses the completely
automated integration of object detection and place classification
in a single system. We first perform automated
learning of object-place relations from an online annotated
database. We then train object detectors on some of the
most frequently occurring objects. Finally we use detection
scores as well as learned object-place relations to perform
place classification of images. We also discuss areas
for improvement and the application of this work to informed
visual search. As a whole, the system demonstrates
the automated acquisition of training data containing labeled
instances (i.e. bounding boxes) and the performance
of a state-of-the-art object detection technique trained on
this data to perform place classification of realistic indoor
scenes.
},
bib2html_pubtype ={Refereed Conference Proceeding},
bib2html_rescat ={},
}
Generated by bib2html.pl (written by Patrick Riley ) on Mon Dec 20, 2010 13:33:03