Sciweavers

479 search results - page 47 / 96
» From a Set of Shapes to Object Discovery
Sort
View
ICRA
1999
IEEE
155views Robotics» more  ICRA 1999»
15 years 6 months ago
3-D Cueing: A Data Filter for Object Recognition
This paper presents a novel method for quickly filtering range data points to make object recognition in large 3D data sets feasible. The general approach, called "3D cueing,...
Owen T. Carmichael, Martial Hebert
ICCV
2007
IEEE
16 years 3 months ago
Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification
We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images ...
Andrea Frome, Yoram Singer, Fei Sha, Jitendra Mali...
SSD
2001
Springer
128views Database» more  SSD 2001»
15 years 6 months ago
Creating Representations for Continuously Moving Regions from Observations
Recently there is much interest in moving objects databases, and data models and query languages have been proposed offering data types such as moving point and moving region toge...
Erlend Tøssebro, Ralf Hartmut Güting
EMMCVPR
2005
Springer
15 years 7 months ago
Edge Strength Functions as Shape Priors in Image Segmentation
Many applications of computer vision requires segmenting out of an object of interest from a given image. Motivated by unlevel-sets formulation of Raviv, Kiryati and Sochen [8] and...
Erkut Erdem, Aykut Erdem, Sibel Tari
BMVC
2010
14 years 12 months ago
Improving object classification using semantic attributes
This paper shows how semantic attribute features can be used to improve object classification performance. The semantic attributes used fall into five groups: scene (e.g. `road�...
Yu Su, Moray Allan, Frédéric Jurie