Sciweavers

3982 search results - page 220 / 797
» Learning to Recognize Objects
Sort
View
MVA
2002
146views Computer Vision» more  MVA 2002»
15 years 4 months ago
Motion segmentation and pose recognition with motion history gradients
This paper uses a simple method for representing motion in successively layered silhouettes that directly encode system time termed the timed Motion History Image (tMHI). This rep...
Gary R. Bradski, James W. Davis
135
Voted
VR
2010
IEEE
108views Virtual Reality» more  VR 2010»
15 years 3 months ago
Twinkle: Interacting with physical surfaces using handheld projector
We propose a novel interface called Twinkle for interacting with an arbitrary physical surface using a handheld projector and a camera. When a user flashes a projection light on ...
Takumi Yoshida, Yuki Hirobe, Hideaki Nii, Naoki Ka...
CVPR
2012
IEEE
13 years 7 months ago
Semantic segmentation using regions and parts
We address the problem of segmenting and recognizing objects in real world images, focusing on challenging articulated categories such as humans and other animals. For this purpos...
Pablo Arbelaez, Bharath Hariharan, Chunhui Gu, Sau...
ICMLA
2004
15 years 6 months ago
Satisficing Q-learning: efficient learning in problems with dichotomous attributes
In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and whic...
Michael A. Goodrich, Morgan Quigley
ICCV
2009
IEEE
1425views Computer Vision» more  ICCV 2009»
16 years 7 months ago
Fast Ray Features for Learning Irregular Shapes
We introduce a new class of image features, the Ray feature set, that consider image characteristics at distant contour points, capturing information which is difficult to repre...
Kevin Smith, Alan Carleton, Vincent Lepetit