Sciweavers

100 search results - page 7 / 20
» Shape of error surfaces in SpikeProp
Sort
View
EMNLP
2010
13 years 5 months ago
Minimum Error Rate Training by Sampling the Translation Lattice
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
Samidh Chatterjee, Nicola Cancedda
JVCA
2010
75views more  JVCA 2010»
13 years 5 months ago
Image-based detail reconstruction of non-Lambertian surfaces
This paper presents a novel optimization framework for estimating the static or dynamic surfaces with details. The proposed method uses dense depths from a structuredlight system ...
I-Chen Lin, Wen-Hsing Chang, Yung-Sheng Lo, Jen-Yu...
CAD
2006
Springer
13 years 7 months ago
Incremental reconstruction of sharp edges on mesh surfaces
Limited by the regular grids in computing, many modelling approaches (e.g., field-based methods) sample 3D shape insensitive to sharp features therefore exhibit aliasing errors, b...
Charlie C. L. Wang
SIGGRAPH
1992
ACM
13 years 11 months ago
Variational surface modeling
We present a new approachto interactive modeling of freeform surfaces. Instead of a fixed mesh of control points, the model presented to the user is that of an infinitely malleabl...
William Welch, Andrew P. Witkin
SMI
2005
IEEE
111views Image Analysis» more  SMI 2005»
14 years 1 months ago
Rational Spherical Splines for Genus Zero Shape Modeling
Traditional approaches for modeling a closed manifold surface with either regular tensor-product or triangular splines (defined over an open planar domain) require decomposing th...
Ying He 0001, Xianfeng Gu, Hong Qin