Sciweavers

788 search results - page 143 / 158
» Two Approaches for Text Segmentation in Web Images
Sort
View
ICCV
1995
IEEE
13 years 11 months ago
Recognition Using Region Correspondences
Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estima...
Ronen Basri, David W. Jacobs
IJCV
2008
106views more  IJCV 2008»
13 years 7 months ago
Evaluation of Localized Semantics: Data, Methodology, and Experiments
We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protoc...
Kobus Barnard, Quanfu Fan, Ranjini Swaminathan, An...
SAC
2011
ACM
12 years 10 months ago
Hierarchical comments-based clustering
Information resources on the Web like videos, images, and documents are increasingly becoming more “social” through user engagement via commenting systems. These commenting sy...
Chiao-Fang Hsu, James Caverlee, Elham Khabiri
ICCV
2009
IEEE
15 years 14 days ago
Moving in Stereo: Efficient Structure and Motion Using Lines
We present a fast and robust system for estimating structure and motion using a stereo pair, with straight lines as features. Our first set of contributions are efficient algorit...
Manmohan Chandraker, Jongwoo Lim, David Kriegman
GBRPR
2005
Springer
14 years 1 months ago
Coarse-to-Fine Object Recognition Using Shock Graphs
Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper,...
Aurelie Bataille, Sven J. Dickinson