Sciweavers

2183 search results - page 125 / 437
» Algorithmic issues in modeling motion
Sort
View
BMVC
1998
13 years 11 months ago
A Method for Dynamic Clustering of Data
This paper describes a method for the segmentation of dynamic data. It extends well known algorithms developed in the context of static clustering (e.g., the c-means algorithm, Ko...
Arnaldo J. Abrantes, Jorge S. Marques
SCVMA
2004
Springer
14 years 3 months ago
A Generative Model of Dense Optical Flow in Layers
We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, varia...
Anitha Kannan, Brendan J. Frey, Nebojsa Jojic
CA
2003
IEEE
14 years 2 months ago
Expressive Gesture Animation Based on Non Parametric Learning of Sensory-Motor Models
This paper presents an efficient method of learning motion control for autonomous animated characters. The method uses a non parametric learning approach which identifies non line...
Sylvie Gibet, Pierre-Francois Marteau
ICIP
2006
IEEE
14 years 3 months ago
Discontinuity-Adaptive De-Interlacing Scheme Using Markov Random Field Model
— In this paper, a de-interlacing algorithm to find the optimal deinterlaced results given accuracy-limited motion information is proposed. The de-interlacing process is formula...
Min Li, Truong Q. Nguyen
CORR
2010
Springer
94views Education» more  CORR 2010»
13 years 7 months ago
Using virtual human for an interactive customer-oriented constrained environment design
: For industrial product design, it is very important to take into account assembly/disassembly and maintenance operations during the conceptual and prototype design stage. For the...
Liang Ma, Ruina Ma, Damien Chablat, Fouad Bennis