Sciweavers

60 search results - page 6 / 12
» Exploiting Human Actions and Object Context for Recognition ...
Sort
View
CHI
2005
ACM
14 years 7 months ago
Breaking the laws of action in the user interface
Fitts' law, Steering law and Law of crossing, collectively known as the laws of action, model the speed-accuracy tradeoffs in common HCI tasks. These laws impose a certain sp...
Per Ola Kristensson
ICRA
2010
IEEE
185views Robotics» more  ICRA 2010»
13 years 5 months ago
MOPED: A scalable and low latency object recognition and pose estimation system
— The latency of a perception system is crucial for a robot performing interactive tasks in dynamic human environments. We present MOPED, a fast and scalable perception system fo...
Manuel Martinez, Alvaro Collet, Siddhartha S. Srin...
MM
2010
ACM
146views Multimedia» more  MM 2010»
13 years 6 months ago
Making computers look the way we look: exploiting visual attention for image understanding
Human Visual attention (HVA) is an important strategy to focus on specific information while observing and understanding visual stimuli. HVA involves making a series of fixations ...
Harish Katti, Subramanian Ramanathan, Mohan S. Kan...
ICCV
2011
IEEE
12 years 6 months ago
Understanding Egocentric Activities
We present a method to analyze daily activities, such as meal preparation, using video from an egocentric camera. Our method performs inference about activities, actions, hands, a...
Alireza Fathi, Ali Farhadi, James M. Rehg
ICRA
2009
IEEE
208views Robotics» more  ICRA 2009»
13 years 4 months ago
Affordance based word-to-meaning association
Abstract-- This paper presents a method to associate meanings to words in manipulation tasks. We base our model on an affordance network, i.e., a mapping between robot actions, rob...
Verica Krunic, Giampiero Salvi, Alexandre Bernardi...