Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1458-1462.
Abstract
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 goaldirected) 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.
@inproceedings{ijcai2005p162,
title = {Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition},
author = {Khadhouri, Bassam and Demiris, Yiannis},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1458--1462},
year = {2005},
url = {https://ijcai.org/proceedings/2005/162},
}
TY - CPAPER TI - Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition AU - Khadhouri, Bassam AU - Demiris, Yiannis T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1458 EP - 1462 UR - https://ijcai.org/proceedings/2005/162 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
