Sciweavers

4366 search results - page 796 / 874
» Image Recognition with Occlusions
Sort
View
NIPS
1997
15 years 7 months ago
Learning Generative Models with the Up-Propagation Algorithm
Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...
Jong-Hoon Oh, H. Sebastian Seung
CASCON
1996
72views Education» more  CASCON 1996»
15 years 7 months ago
A robot agent that can search
Object search is the task of eciently searching for a given 3D object in a given 3D environment by an agent equipped with a camera for target detection and, if the environment con...
Yiming Ye, John K. Tsotsos
CVPR
2009
IEEE
17 years 1 months ago
A Multi-View Probabilistic Model for 3D Object Classes
We propose a novel probabilistic framework for learning visual models of 3D object categories by combining appearance information and geometric constraints. Objects are represen...
Fei-Fei Li 0002, Hao Su, Min Sun, Silvio Savarese
CVPR
2009
IEEE
17 years 1 months ago
Monitoring, Recognizing and Discovering Social Networks
This work addresses the important problem of the discovery and analysis of social networks from surveillance video. A computer vision approach to this problem is made possible b...
Ting Yu, Ser Nam Lim, Kedar A. Patwardhan, Nils Kr...
CVPR
2009
IEEE
17 years 1 months ago
Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to se...
Peter V. Gehler, Sebastian Nowozin