Sciweavers

3424 search results - page 358 / 685
» Building Diverse Computer Systems
Sort
View
133
Voted
ECCV
2010
Springer
15 years 9 months ago
Tracklet Descriptors  for Action Modeling and Video Analysis
We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
Michalis Raptis , Stefano Soatto
96
Voted
ISWC
2003
IEEE
15 years 9 months ago
Using Multiple Sensors for Mobile Sign Language Recognition
We build upon a constrained, lab-based Sign Language recognition system with the goal of making it a mobile assistive technology. We examine using multiple sensors for disambiguat...
Helene Brashear, Thad Starner, Paul Lukowicz, Holg...
128
Voted
SPEECH
2002
91views more  SPEECH 2002»
15 years 3 months ago
Large vocabulary continuous speech recognition of Broadcast News - The Philips/RWTH approach
Automatic speech recognition of real-live broadcast news (BN) data (Hub-4) has become a challenging research topic in recent years. This paper summarizes our key efforts to build ...
Peter Beyerlein, Xavier L. Aubert, Reinhold Haeb-U...
118
Voted
NCA
2010
IEEE
14 years 10 months ago
Composable continuous-space programs for robotic swarms
Programmability is an increasingly important barrier to the deployment of multi-robot systems, as no prior approach allows routine composition and reuse of general aggregate behavi...
Jonathan Bachrach, Jacob Beal, James McLurkin
119
Voted
CHI
2008
ACM
16 years 4 months ago
Personal inventories: toward durable human-product relationships
In this paper, I build on perspectives in HumanComputer Interaction (HCI) and design literature to develop a theoretical lens to conduct personal inventories of human-product rela...
William Odom