Sciweavers

659 search results - page 55 / 132
» Object Labelling from Human Action Recognition
Sort
View
CVPR
2012
IEEE
13 years 6 months ago
Action bank: A high-level representation of activity in video
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Sreemanananth Sadanand, Jason J. Corso
CIRA
2007
IEEE
152views Robotics» more  CIRA 2007»
15 years 10 months ago
Probabilistic Semantic Mapping with a Virtual Sensor for Building/Nature detection
Abstract— In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We believe that access to semantic maps will make it poss...
Martin Persson, Tom Duckett, Christoffer Valgren, ...
ICIP
2002
IEEE
16 years 5 months ago
Model-driven statistical analysis of human gait motion
We describe a new method for analyzing and extracting human gait motion by combining statistical methods with image processing. The periodic motion of human gait is modeled by tri...
Jang-Hee Yoo, Mark S. Nixon, Chris J. Harris
ICIP
2003
IEEE
16 years 5 months ago
On automatic annotation of meeting databases
In this paper, we discuss meetings as an application domain for multimedia content analysis. Meeting databases are a rich data source suitable for a variety of audio, visual and m...
Daniel Gatica-Perez, Hervé Bourlard, Iain M...
ISVC
2010
Springer
15 years 1 months ago
Egocentric Visual Event Classification with Location-Based Priors
We present a method for visual classification of actions and events captured from an egocentric point of view. The method tackles the challenge of a moving camera by creating defor...
Sudeep Sundaram, Walterio W. Mayol-Cuevas