@conference {Borji_etal12aaai,
	title = {An Object-based Bayesian Framework for Top-down Visual Attention},
	booktitle = {Proc. Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI-12), Toronto, Canada},
	year = {2012},
	month = {Aug},
	abstract = {<p>We introduce a new task-independent framework to model top-down overt visual attention based on graphical models for probabilistic inference and reasoning. We describe a Dynamic Bayesian Network (DBN) that infers probability distributions over attended objects and spatial locations directly from observed data. Probabilistic inference in our model is performed over object-related functions which are fed from manual an- notations of objects in video scenes or by state-of-the-art object detection models. Evaluating over appx. 3 hours (appx. 315,000 eye fixations and 12,600 saccades) of observers playing 3 video games (time-scheduling, driving, and flight combat), we show that our approach is significantly more predictive of eye fixations com- pared to: 1) simpler classifier-based models also developed here that map a signature of a scene (multi-modal information from gist, bottom-up saliency, physical actions, and events) to eye positions, 2) 14 state-of-the-art bottom-up saliency models, and 3) brute-force algo- rithms such as mean eye position. Our results show that the proposed model is more effective in employing and reasoning over spatio-temporal visual data.</p>},
	author = {Ali Borji and Dicky N. Sihite and Laurent Itti}
}