Sciweavers

221 search results - page 9 / 45
» Capturing the Human Action Semantics using a Query-By-Exampl...
Sort
View
CVPR
2007
IEEE
15 years 11 months ago
Learning Motion Categories using both Semantic and Structural Information
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal in...
Shu-Fai Wong, Tae-Kyun Kim, Roberto Cipolla
ICAPR
2005
Springer
15 years 3 months ago
3D Action Modeling and Reconstruction for 2D Human Body Tracking
In this paper we present a technique for predicting the 2D human body joints and limbs position in monocular image sequences, and reconstructing its corresponding 3D postures using...
Ignasi Rius, Daniel Rowe, Jordi Gonzàlez, F...
IJCV
2002
219views more  IJCV 2002»
14 years 9 months ago
View-Invariant Representation and Recognition of Actions
Analysis of human perception of motion shows that information for representing the motion is obtained from the dramatic changes in the speed and direction of the trajectory. In thi...
Cen Rao, Alper Yilmaz, Mubarak Shah
ICPR
2002
IEEE
15 years 11 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
CVPR
2010
IEEE
15 years 6 months ago
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Adriana Kovashka, Kristen Grauman