Sciweavers

2295 search results - page 364 / 459
» Learning Overcomplete Representations
Sort
View
WWW
2007
ACM
14 years 10 months ago
Web page classification with heterogeneous data fusion
Web pages are more than text and they contain much contextual and structural information, e.g., the title, the meta data, the anchor text, etc., each of which can be seen as a dat...
Zenglin Xu, Irwin King, Michael R. Lyu
CHI
2005
ACM
14 years 10 months ago
Polymorphic letters: transforming pen movements to extend written expression
We are developing a digital writing tool, Polymorphic Letters (PL), to investigate hand and pen movements as they may extend and enrich expression in written language. PL recogniz...
Andrea Taylor, Zoltan Foley-Fisher, Carol Stroheck...
CVPR
2010
IEEE
14 years 6 months ago
Automatic Discovery of Meaningful Object Parts with Latent CRFs
Object recognition is challenging due to high intra-class variability caused, e.g., by articulation, viewpoint changes, and partial occlusion. Successful methods need to strike a...
Paul Schnitzspan, Stefan Roth, Bernt Schiele
CVPR
2010
IEEE
14 years 5 months ago
Multi-View Object Class Detection With a 3D Geometric Model
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
Joerg Liebelt, Cordelia Schmid
CVPR
2010
IEEE
14 years 5 months ago
Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object s...
Leo Zhu, Yuanhao Chen, Antonio Torralba, William F...