Sciweavers

2183 search results - page 125 / 437
» Algorithmic issues in modeling motion
Sort
View
BMVC
1998
15 years 7 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
15 years 11 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
15 years 11 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
16 years 10 days 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»
15 years 3 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