Sciweavers

664 search results - page 105 / 133
» Unsupervised Category Modeling, Recognition, and Segmentatio...
Sort
View
CVPR
2006
IEEE
14 years 11 months ago
Incremental learning of object detectors using a visual shape alphabet
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
Andreas Opelt, Axel Pinz, Andrew Zisserman
ICCV
2011
IEEE
12 years 9 months ago
Kinecting the dots: Particle Based Scene Flow from depth sensors
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
Simon Hadfield, Richard Bowden
DAGM
2004
Springer
14 years 18 days ago
The Perceptual Influence of Spatiotemporal Noise on the Reconstruction of Shape from Dynamic Occlusion
Abstract. When an object moves, it covers and uncovers texture in the background. This pattern of change is sufficient to define the object's shape, velocity, relative depth, ...
Theresa Cooke, Douglas W. Cunningham, Heinrich H. ...
AND
2009
13 years 6 months ago
Discovering voter preferences in blogs using mixtures of topic models
In this paper we propose a new approach to capture the inclination towards a certain election candidate from the contents of blogs and to explain why that inclination may be so. T...
Pradipto Das, Rohini K. Srihari, Smruthi Mukund
JCDL
2009
ACM
139views Education» more  JCDL 2009»
14 years 3 months ago
Topic model methods for automatically identifying out-of-scope resources
Recent years have seen the rise of subject-themed digital libraries, such as the NSDL pathways and the Digital Library for Earth System Education (DLESE). These libraries often ne...
Steven Bethard, Soumya Ghosh, James H. Martin, Tam...