Sciweavers

7431 search results - page 63 / 1487
» Temporal Information Extraction
Sort
View
ICPR
2010
IEEE
13 years 12 months ago
Recognizing Human Actions Using Key Poses
In this paper, we explore the idea of using only pose, without utilizing any temporal information, for human action recognition. In contrast to the other studies using complex acti...
Sermetcan Baysal, Mehmet Can Kurt, Pinar Duygulu
ICMCS
2005
IEEE
89views Multimedia» more  ICMCS 2005»
14 years 3 months ago
Interactivity and Multimodality in the IMIX Demonstrator
It is generally acknowledged that many experts and almost all lay persons have difficulty in formulating requests for information in such a manner that conventional off-line Infor...
Lou Boves, Els den Os
FGR
2008
IEEE
208views Biometrics» more  FGR 2008»
14 years 4 months ago
Unsupervised learning from local features for video-based face recognition
This paper presents an unsupervised learning approach to video-based face recognition that does not make any assumptions about the pose, expressions or prior localization of landm...
Ajmal Mian
HUMO
2007
Springer
14 years 4 months ago
Human Action Recognition Using Distribution of Oriented Rectangular Patches
We describe a “bag-of-rectangles” method for representing and recognizing human actions in videos. In this method, each human pose in an action sequence is represented by orien...
Nazli Ikizler, Pinar Duygulu
ICDE
2006
IEEE
156views Database» more  ICDE 2006»
14 years 11 months ago
Extracting Objects from the Web
Extracting and integrating object information from the Web is of great significance for Web data management. The existing Web information extraction techniques cannot provide sati...
Zaiqing Nie, Fei Wu, Ji-Rong Wen, Wei-Ying Ma