---
title: "Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition"
authors:
  - "Bassam Khadhouri"
  - "Yiannis Demiris"
doi: ""
url: "https://ijcai.org/proceedings/2005/162"
pdf: "https://ijcai.org/proceedings/2005/0162.pdf"
venue: "Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence"
year: 2005
pages: "1458-1462"
track: ""
keywords:
---

# Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition

Bassam Khadhouri, Yiannis Demiris

*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.