@inproceedings{Khadhouri:2005,
author = {Khadhouri, B and Demiris, Y},
pages = {1458--1463},
publisher = {International Joint Conferences on Artificial Intelligence},
title = {Compound effects of top-down and bottom-up influences on visual attention during action recognition},
url = {http://ijcai.org/Past%20Proceedings/IJCAI-05/IJCAI-05%20CONTENT.htm},
year = {2005}
}

Download

TY  - CPAPER
AB  - The limited visual and computational resources available during the perception of a human action makes a visual attention mechanism essential. In this paper we propose an attention mechanism that combines the saliency of top-down (or goal-directed) elements, based on multiple hypotheses about the demonstrated action, with the saliency of bottom-up (or stimulus-driven) components. Furthermore, we use the bottom-up part to initialise the top-down, hence resulting in a selection of the behaviours that rightly require the limited computational resources. This attention mechanism is then combined with an action understanding model and implemented on a robot, where we examine its performance during the observation of object-directed human actions.
AU  - Khadhouri,B
AU  - Demiris,Y
EP  - 1463
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2005///
SP  - 1458
TI  - Compound effects of top-down and bottom-up influences on visual attention during action recognition
UR  - http://ijcai.org/Past%20Proceedings/IJCAI-05/IJCAI-05%20CONTENT.htm
UR  - http://hdl.handle.net/10044/1/12701
ER  - 

Download