Sciweavers

3074 search results - page 111 / 615
» A Boundary-Fragment-Model for Object Detection
Sort
View
SPIEVIP
2010
15 years 8 months ago
Automatic scene activity modeling for improving object classification
In video surveillance, automatic methods for scene understanding and activity modeling can exploit the high redundancy of object trajectories observed over a long period of time. ...
Samuel Foucher, Marc Lalonde, Langis Gagnon
CLOR
2006
15 years 8 months ago
An Implicit Shape Model for Combined Object Categorization and Segmentation
We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure-ground segmentation is available prior...
Bastian Leibe, Ales Leonardis, Bernt Schiele
TROB
2008
118views more  TROB 2008»
15 years 6 months ago
A New Kalman-Filter-Based Framework for Fast and Accurate Visual Tracking of Rigid Objects
The best of Kalman-filter-based frameworks reported in the literature for rigid object tracking work well only if the object motions are smooth (which allows for tight uncertainty ...
Youngrock Yoon, Akio Kosaka, Avinash C. Kak
3DOR
2010
15 years 1 months ago
Learning the Compositional Structure of Man-Made Objects for 3D Shape Retrieval
While approaches based on local features play a more and more important role for 3D shape retrieval, the problems of feature selection and similarity measurement between sets of l...
Raoul Wessel, Reinhard Klein
PAKDD
2009
ACM
103views Data Mining» more  PAKDD 2009»
16 years 1 months ago
Hot Item Detection in Uncertain Data
Abstract. An object o of a database D is called a hot item, if there is a sufficiently large population of other objects in D that are similar to o. In other words, hot items are ...
Thomas Bernecker, Hans-Peter Kriegel, Matthias Ren...