Sciweavers

93 search results - page 4 / 19
» Recognizing Activities with Multiple Cues
Sort
View
CVPR
2010
IEEE
14 years 7 months ago
Figure-Ground Segmentation Improves Handled Object Recognition in Egocentric Video
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person’s activities. An egocentric camera as worn on the body enjoys many...
Xiaofeng Ren, Chunhui Gu
IROS
2009
IEEE
193views Robotics» more  IROS 2009»
14 years 5 months ago
Active segmentation for robotics
— The semantic robots of the immediate future are robots that will be able to find and recognize objects in any environment. They need the capability of segmenting objects in th...
Ajay K. Mishra, Yiannis Aloimonos, Cornelia Ferm&u...
BMVC
2010
13 years 9 months ago
Manifold Learning for ToF-based Human Body Tracking and Activity Recognition
In this paper, we propose a method for simultaneous human full-body pose tracking and activity recognition from time-of-flight (ToF) camera images. Simple and sparse depth cues ar...
Loren Arthur Schwarz, Diana Mateus, Victor Castane...
CLEAR
2007
Springer
195views Biometrics» more  CLEAR 2007»
14 years 5 months ago
Multi-level Particle Filter Fusion of Features and Cues for Audio-Visual Person Tracking
In this paper, two multimodal systems for the tracking of multiple users in smart environments are presented. The first is a multiview particle filter tracker using foreground, c...
Keni Bernardin, Tobias Gehrig, Rainer Stiefelhagen
ICASSP
2009
IEEE
14 years 5 months ago
A speech fragment approach to localising multiple speakers in reverberant environments
Sound source localisation cues are severely degraded when multiple acoustic sources are active in the presence of reverberation. We present a binaural system for localising simult...
Heidi Christensen, Ning Ma, Stuart N. Wrigley, Jon...