Sciweavers

27 search results - page 4 / 6
» Using the Geometrical Distribution of Prototypes for Trainin...
Sort
View
ICCV
2005
IEEE
14 years 9 months ago
A Maximum Entropy Framework for Part-Based Texture and Object Recognition
This paper presents a probabilistic part-based approach for texture and object recognition. Textures are represented using a part dictionary found by quantizing the appearance of ...
Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
PRL
2006
106views more  PRL 2006»
13 years 7 months ago
Invariances in kernel methods: From samples to objects
This paper presents a general method for incorporating prior knowledge into kernel methods such as Support Vector Machines. It applies when the prior knowledge can be formalized b...
Alexei Pozdnoukhov, Samy Bengio
ICASSP
2011
IEEE
12 years 11 months ago
Improving text-independent phonetic segmentation based on the Microcanonical Multiscale Formalism
In an earlier work, we proposed a novel phonetic segmentation method based on speech analysis under the Microcanonical Multiscale Formalism (MMF). The latter relies on the computa...
Vahid Khanagha, Khalid Daoudi, Oriol Pont, Hussein...

Publication
173views
12 years 6 months ago
Max-Flow Segmentation of the Left Ventricle by Recovering Subject-Specific Distributions via a Bound of the Bhattacharyya Measur
This study investigates fast detection of the left ventricle (LV) endo- and epicardium boundaries in a cardiac magnetic resonance (MR) sequence following the optimization of two or...
Ismail Ben Ayed, Hua-mei Chen, Kumaradevan Punitha...
VRST
2003
ACM
14 years 21 days ago
Time-critical collision detection using an average-case approach
We present a novel, generic framework and algorithm for hierarchical collision detection, which allows an application to balance speed and quality of the collision detection. We p...
Jan Klein, Gabriel Zachmann