@techreport{TD:101129,
	att_abstract={{Estimating geographic location from images is a challenging
problem that is receiving recent attention. In contrast
to many existing methods that primarily model discriminative
information corresponding to different locations,
we propose joint learning of information that images
across locations share and vary upon. Starting with generative
and discriminative subspaces pertaining to domains,
which are obtained by a hierarchical grouping of images
from adjacent locations, we present a top-down approach
that first models cross-domain information transfer by utilizing
the geometry of these subspaces, and then encodes the
model results onto individual images to infer their location.
We report competitive results for location recognition and
clustering on two public datasets, im2GPS and San Francisco,
and empirically validate the utility of various design
choices involved in the approach.}},
	att_authors={rg4675},
	att_categories={C_CCF.10},
	att_copyright={{IEEE}},
	att_copyright_notice={{This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in 2013.{{, 2013-06-25}}
}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={},
	att_techdoc={true},
	att_techdoc_key={TD:101129},
	att_url={http://web1.research.att.com:81/techdocs_downloads/TD:101129_DS1_2013-03-05T19:43:29.451Z.pdf},
	author={Raghuraman Gopalan},
	institution={{IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2013.}},
	month={June},
	title={{Learning Cross-domain Information Transfer for Location Recognition and
Clustering}},
	year=2013,
}