A gaze prediction technique for open signed video content using a track before detect algorithm

SJC Davies; D Agrafiotis; CN Canagarajah; DR Bull

doi:10.1109/ICIP.2008.4711852

A gaze prediction technique for open signed video content using a track before detect algorithm

SJC Davies
, D Agrafiotis
, CN Canagarajah
, DR Bull

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

4 Citations (Scopus)

817 Downloads (Pure)

Abstract

This paper proposes a gaze prediction model for open signed video content. A face detection algorithm is used to locate faces across each frame in both profile and frontal orientations. A grid-based likelihood ratio track before detect routine is used to predict the orientation of the signer's head, which allows the gaze location to be localised to either the signer or the inset. The face detections are then used to narrow down the gaze prediction further. The gaze predictor is able to predict the results of an eye tracking study with up to 95% accuracy, and an average accuracy of over 80%

Translated title of the contribution	A gaze prediction technique for open signed video content using a track before detect algorithm
Original language	English
Title of host publication	15th IEEE International Conference on Image Processing, 2008 (ICIP 2008)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	705 - 708
Number of pages	4
ISBN (Print)	9781424417650
DOIs	https://doi.org/10.1109/ICIP.2008.4711852
Publication status	Published - Oct 2008
Event	15th International Conference on Image Processing - San Diego, CA, United States Duration: 1 Oct 2008 → …

Publication series

Name
ISSN (Print)	15224880

Conference

Conference	15th International Conference on Image Processing
Country/Territory	United States
City	San Diego, CA
Period	1/10/08 → …

Bibliographical note

Rose publication type: Conference contribution

Additional information: With accompanying conference presentation

Sponsorship: This work was funded by the British Broadcasting Corporation (BBC)

Terms of use: Copyright © 2008 IEEE. Reprinted from IEEE 15th International Conference on Image Processing, 2008 (ICIP 2008).

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected].

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Keywords

video contexts
video coding
gaze tracking

Access to Document

10.1109/ICIP.2008.4711852

Conference paperAccepted author manuscript, 394 KB
Accompanying conference presentationAccepted author manuscript, 3.8 MB

http://hdl.handle.net/1983/1545

Handle.net

Persistent link

Cite this

@inproceedings{a726989bd4f74bd69427e699171f06b1,

title = "A gaze prediction technique for open signed video content using a track before detect algorithm",

abstract = "This paper proposes a gaze prediction model for open signed video content. A face detection algorithm is used to locate faces across each frame in both profile and frontal orientations. A grid-based likelihood ratio track before detect routine is used to predict the orientation of the signer's head, which allows the gaze location to be localised to either the signer or the inset. The face detections are then used to narrow down the gaze prediction further. The gaze predictor is able to predict the results of an eye tracking study with up to 95\% accuracy, and an average accuracy of over 80\%",

keywords = "video contexts, video coding, gaze tracking",

author = "SJC Davies and D Agrafiotis and CN Canagarajah and DR Bull",

note = "Rose publication type: Conference contribution Additional information: With accompanying conference presentation Sponsorship: This work was funded by the British Broadcasting Corporation (BBC) Terms of use: Copyright {\textcopyright} 2008 IEEE. Reprinted from IEEE 15th International Conference on Image Processing, 2008 (ICIP 2008). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. ; 15th International Conference on Image Processing ; Conference date: 01-10-2008",

year = "2008",

month = oct,

doi = "10.1109/ICIP.2008.4711852",

language = "English",

isbn = "9781424417650",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "705 -- 708",

booktitle = "15th IEEE International Conference on Image Processing, 2008 (ICIP 2008)",

address = "United States",

}

Davies, SJC, Agrafiotis, D, Canagarajah, CN & Bull, DR 2008, A gaze prediction technique for open signed video content using a track before detect algorithm. in 15th IEEE International Conference on Image Processing, 2008 (ICIP 2008). Institute of Electrical and Electronics Engineers (IEEE), pp. 705 - 708, 15th International Conference on Image Processing, San Diego, CA, United States, 1/10/08. https://doi.org/10.1109/ICIP.2008.4711852

A gaze prediction technique for open signed video content using a track before detect algorithm. / Davies, SJC; Agrafiotis, D; Canagarajah, CN et al.
15th IEEE International Conference on Image Processing, 2008 (ICIP 2008). Institute of Electrical and Electronics Engineers (IEEE), 2008. p. 705 - 708.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - A gaze prediction technique for open signed video content using a track before detect algorithm

AU - Davies, SJC

AU - Agrafiotis, D

AU - Canagarajah, CN

AU - Bull, DR

N1 - Rose publication type: Conference contribution Additional information: With accompanying conference presentation Sponsorship: This work was funded by the British Broadcasting Corporation (BBC) Terms of use: Copyright © 2008 IEEE. Reprinted from IEEE 15th International Conference on Image Processing, 2008 (ICIP 2008). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

PY - 2008/10

Y1 - 2008/10

N2 - This paper proposes a gaze prediction model for open signed video content. A face detection algorithm is used to locate faces across each frame in both profile and frontal orientations. A grid-based likelihood ratio track before detect routine is used to predict the orientation of the signer's head, which allows the gaze location to be localised to either the signer or the inset. The face detections are then used to narrow down the gaze prediction further. The gaze predictor is able to predict the results of an eye tracking study with up to 95% accuracy, and an average accuracy of over 80%

AB - This paper proposes a gaze prediction model for open signed video content. A face detection algorithm is used to locate faces across each frame in both profile and frontal orientations. A grid-based likelihood ratio track before detect routine is used to predict the orientation of the signer's head, which allows the gaze location to be localised to either the signer or the inset. The face detections are then used to narrow down the gaze prediction further. The gaze predictor is able to predict the results of an eye tracking study with up to 95% accuracy, and an average accuracy of over 80%

KW - video contexts

KW - video coding

KW - gaze tracking

U2 - 10.1109/ICIP.2008.4711852

DO - 10.1109/ICIP.2008.4711852

M3 - Conference Contribution (Conference Proceeding)

SN - 9781424417650

SP - 705

EP - 708

BT - 15th IEEE International Conference on Image Processing, 2008 (ICIP 2008)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 15th International Conference on Image Processing

Y2 - 1 October 2008

ER -

A gaze prediction technique for open signed video content using a track before detect algorithm

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this