Sciweavers

116 search results - page 11 / 24
» Recognizing Action Events from Multiple Viewpoints
Sort
View
ICCV
2009
IEEE
13 years 5 months ago
Incremental action recognition using feature-tree
Action recognition methods suffer from many drawbacks in practice, which include (1)the inability to cope with incremental recognition problems; (2)the requirement of an intensive...
Kishore K. Reddy, Jingen Liu, Mubarak Shah
DSRT
2005
IEEE
14 years 1 months ago
A Multi-Formalism Modeling Composability Framework: Agent and Discrete-Event Models
It is common practice to build complex systems from disparate sub-systems. Model composability is concerned with techniques for developing a whole model of a system from the model...
Hessam S. Sarjoughian, Dongping Huang
CLOR
2006
13 years 11 months ago
What and Where: 3D Object Recognition with Accurate Pose
Abstract. Many applications of 3D object recognition, such as augmented reality or robotic manipulation, require an accurate solution for the 3D pose of the recognized objects. Thi...
Iryna Gordon, David G. Lowe
MM
2009
ACM
252views Multimedia» more  MM 2009»
14 years 2 months ago
Localizing volumetric motion for action recognition in realistic videos
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge ca...
Xiao Wu, Chong-Wah Ngo, Jintao Li, Yongdong Zhang
CLOR
2006
13 years 11 months ago
3D Object Modeling and Recognition from Photographs and Image Sequences
This chapter proposes a representation of rigid three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between ...
Fred Rothganger, Svetlana Lazebnik, Cordelia Schmi...