Sciweavers

324 search results - page 24 / 65
» Attention can improve a simple model for object recognition
Sort
View
CVPR
2012
IEEE
13 years 2 days ago
Pose pooling kernels for sub-category recognition
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
Ning Zhang, Ryan Farrell, Trevor Darrell
EMNLP
2008
14 years 11 months ago
Understanding the Value of Features for Coreference Resolution
In recent years there has been substantial work on the important problem of coreference resolution, most of which has concentrated on the development of new models and algorithmic...
Eric Bengtson, Dan Roth
DAGM
2005
Springer
15 years 3 months ago
Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Estimation
Abstract. This paper presents the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Having a 3D surface model of an ob...
Thomas Brox, Bodo Rosenhahn, Joachim Weickert
IUI
2010
ACM
15 years 6 months ago
The why UI: using goal networks to improve user interfaces
People interact with interfaces to accomplish goals, and knowledge about human goals can be useful for building intelligent user interfaces. We suggest that modeling high, human-l...
Dustin Arthur Smith, Henry Lieberman
CVPR
2011
IEEE
14 years 5 months ago
Sharing Features Between Objects and Their Attributes
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
Sung Ju Hwang, Fei Sha, Kristen Grauman