Sciweavers

514 search results - page 47 / 103
» Contour-Based Learning for Object Detection
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
Decomposition, discovery and detection of visual categories using topic models
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Mario Fritz, Bernt Schiele
IJRR
2010
214views more  IJRR 2010»
13 years 5 months ago
Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation
Over the last years, object detection has become a more and more active field of research in robotics. An important problem in object detection is the need for sufficient labeled ...
Kevin Lai, Dieter Fox
IJCV
2008
226views more  IJCV 2008»
13 years 7 months ago
LabelMe: A Database and Web-Based Tool for Image Annotation
We seek to build a large collection of images with ground truth labels to be used for object detection and recognition research. Such data is useful for supervised learning and qu...
Bryan C. Russell, Antonio Torralba, Kevin P. Murph...
CVPR
2009
IEEE
15 years 3 months ago
Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies
This paper deals with estimation of dense optical flow and ego-motion in a generalized imaging system by exploiting probabilistic linear subspace constraints on the flow. We dea...
Richard Roberts (Georgia Institute of Technology),...
CVPR
2007
IEEE
14 years 9 months ago
Accurate Object Localization with Shape Masks
This paper proposes an approach for object class localization which goes beyond bounding boxes, as it also determines the outline of the object. Unlike most current localization m...
Marcin Marszalek, Cordelia Schmid