Title :
Predicting Primary Gaze Behavior Using Social Saliency Fields
Author :
Hyun Soo Park ; Jain, Eeti ; Sheikh, Yaser
Abstract :
We present a method to predict primary gaze behavior in a social scene. Inspired by the study of electric fields, we posit "social charges"-latent quantities that drive the primary gaze behavior of members of a social group. These charges induce a gradient field that defines the relationship between the social charges and the primary gaze direction of members in the scene. This field model is used to predict primary gaze behavior at any location or time in the scene. We present an algorithm to estimate the time-varying behavior of these charges from the primary gaze behavior of measured observers in the scene. We validate the model by evaluating its predictive precision via cross-validation in a variety of social scenes.
Keywords :
motion estimation; social sciences computing; gradient field; motion estimation; primary gaze behavior prediction; social saliency fields; time-varying behavior; Computational modeling; Equations; Feature extraction; Force; Hidden Markov models; Predictive models; Three-dimensional displays; Gaze prediction; Social scene understanding;
Conference_Titel :
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location :
Sydney, NSW
DOI :
10.1109/ICCV.2013.435