A Multicue Bayesian State Estimator for Gaze Prediction in Open Signed Video

• Published in: IEEE transactions on multimedia Vol. 11; no. 1; pp. 39 - 48
• Main Authors: Davies, S.J.C., Agrafiotis, D., Nishan Canagarajah, C., Bull, D.R.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-01-2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial intelligence; Bayesian analysis; Bayesian methods; Bit rate; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Cues; Exact sciences and technology; Eye-tracking; Eyes; Face detection; Focusing; Frames; Gain; gaze prediciotn; Handicapped aids; Likelihood ratio; Multimedia; Orientation; Pattern recognition. Digital image processing. Computational geometry; Protection; Software; State estimation; Video coding; Video coding; Bayes estimation; Multimedia; Probabilistic approach; Face recognition; Gaze; face detection; Eye-tracking; Grid; Video signal; Likelihood ratio; Context aware; Pursuit eye movement; Orientation; Image coding; gaze prediciotn; Facies; Frontal; Localization; State estimation; Content analysis
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2008.2008916

We propose a multicue gaze prediction framework for open signed video content, the benefits of which include coding gains without loss of perceived quality. We investigate which cues are relevant for gaze prediction and find that shot changes, facial orientation of the signer and face locations are the most useful. We then design a face orientation tracker based upon grid-based likelihood ratio trackers, using profile and frontal face detections. These cues are combined using a grid-based Bayesian state estimation algorithm to form a probability surface for each frame. We find that this gaze predictor outperforms a static gaze prediction and one based on face locations within the frame.