Sciweavers

129 search results - page 24 / 26
» Video-Based Motion Capturing for Skeleton-Based 3D Models
Sort
View
ICPR
2002
IEEE
14 years 7 months ago
Quasi-Invariants for Human Action Representation and Recognition
Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...
Vasu Parameswaran, Rama Chellappa
ICCV
2005
IEEE
13 years 11 months ago
On the Spatial Statistics of Optical Flow
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
Stefan Roth, Michael J. Black
ICDM
2006
IEEE
137views Data Mining» more  ICDM 2006»
14 years 2 days ago
Mining Complex Time-Series Data by Learning Markovian Models
In this paper, we propose a novel and general approach for time-series data mining. As an alternative to traditional ways of designing specific algorithm to mine certain kind of ...
Yi Wang, Lizhu Zhou, Jianhua Feng, Jianyong Wang, ...
ICCV
2005
IEEE
14 years 8 months ago
Identifying Individuals in Video by Combining "Generative" and Discriminative Head Models
The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
Mark Everingham, Andrew Zisserman
ICIP
2007
IEEE
14 years 10 days ago
Dynamic Audio-Visual Mapping using Fused Hidden Markov Model Inversion Method
Realistic audio-visual mapping remains a very challenging problem. Having short time delay between inputs and outputs is also of great importance. In this paper, we present a new ...
Le Xin, Jianhua Tao, Tieniu Tan