Sciweavers

791 search results - page 91 / 159
» A structure from motion inequality
Sort
View
132
Voted
CVPR
1999
IEEE
16 years 8 months ago
Factorization as a Rank 1 Problem
Tomasi and Kanade [1] introduced the factorization method for recovering 3D structure from 2D video. In their formulation, the 3D shape and 3D motion are computed by using an SVD ...
Pedro M. Q. Aguiar, José M. F. Moura
179
Voted
JMIV
2000
141views more  JMIV 2000»
15 years 6 months ago
Critical Motions for Auto-Calibration When Some Intrinsic Parameters Can Vary
Auto-calibration is the recovery of the full camera geometry and Euclidean scene structure from several images of an unknown 3D scene, using rigidity constraints and partial knowl...
Fredrik Kahl, Bill Triggs, Kalle Åström
MM
1996
ACM
148views Multimedia» more  MM 1996»
15 years 10 months ago
A Multimedia System for Authoring Motion Pictures
MAD (Movie Authoring and Design) is a novel design and authoring system that facilitates the process of creating dynamic visual presentations such as motion pictures and lecture-d...
Ronald Baecker, Alan J. Rosenthal, Naomi Friedland...
ICCV
2011
IEEE
14 years 6 months ago
Dynamic Manifold Warping for View Invariant Action Recognition
We address the problem of learning view-invariant 3D models of human motion from motion capture data, in order to recognize human actions from a monocular video sequence with arbi...
Dian Gong, Gerard Medioni
MMDB
2004
ACM
153views Multimedia» more  MMDB 2004»
15 years 11 months ago
A PCA-based similarity measure for multivariate time series
Multivariate time series (MTS) datasets are common in various multimedia, medical and financial applications. We propose a similarity measure for MTS datasets, Eros (Extended Fro...
Kiyoung Yang, Cyrus Shahabi