Automatic annotation of head velocity and acceleration in Anvil

Bart Jongejan

Automatic annotation of head velocity and acceleration in Anvil

Centre for Language Technology

3048 Downloads (Pure)

Abstract

We describe an automatic face tracker plugin for the ANVIL annotation tool. The face tracker produces data for velocity and for acceleration in two dimensions. We compare the annotations generated by the face tracking algorithm with independently made manual annotations for head movements. The annotations are a useful supplement to manual annotations and may help human annotators to quickly and reliably determine onset of head movements and to suggest which kind of head movement is taking place.

Original language	English
Title of host publication	Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
Number of pages	8
Publisher	European Language Resources Association
Publication date	23 May 2012
Pages	201-208
ISBN (Electronic)	978-2-9517408-7-7
Publication status	Published - 23 May 2012
Event	International Conference on Language Resources and Evaluation - Istanbul, Turkey Duration: 23 May 2012 → 25 May 2012 Conference number: 8

Conference

Conference	International Conference on Language Resources and Evaluation
Number	8
Country/Territory	Turkey
City	Istanbul
Period	23/05/2012 → 25/05/2012

Keywords

Faculty of Humanities

Access to Document

Automatic annotation of face velocity and acceleration in AnvilFinal published version, 851 KB
Automatic annotation of face velocity and acceleration in Anvil (Poster)Accepted author manuscript, 539 KB

http://www.lrec-conf.org/proceedings/lrec2012/pdf/193_Paper.pdf

Cite this

Jongejan, B 2012, Automatic annotation of head velocity and acceleration in Anvil. in Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12). European Language Resources Association, pp. 201-208, International Conference on Language Resources and Evaluation, Istanbul, Turkey, 23/05/2012. <http://www.lrec-conf.org/proceedings/lrec2012/pdf/193_Paper.pdf>

@inproceedings{18c5a45b248e4af7926f66743bbe178a,

title = "Automatic annotation of head velocity and acceleration in Anvil",

abstract = "We describe an automatic face tracker plugin for the ANVIL annotation tool. The face tracker produces data for velocity and for acceleration in two dimensions. We compare the annotations generated by the face tracking algorithm with independently made manual annotations for head movements. The annotations are a useful supplement to manual annotations and may help human annotators to quickly and reliably determine onset of head movements and to suggest which kind of head movement is taking place.",

keywords = "Faculty of Humanities, corpus, discourse annotation, Information extraction, Information retrieval , Processing, representation",

author = "Bart Jongejan",

year = "2012",

month = may,

day = "23",

language = "English",

pages = "201--208",

booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)",

publisher = "European Language Resources Association",

note = "International Conference on Language Resources and Evaluation, LREC '12 ; Conference date: 23-05-2012 Through 25-05-2012",

}

TY - GEN

T1 - Automatic annotation of head velocity and acceleration in Anvil

AU - Jongejan, Bart

N1 - Conference code: 8

PY - 2012/5/23

Y1 - 2012/5/23

N2 - We describe an automatic face tracker plugin for the ANVIL annotation tool. The face tracker produces data for velocity and for acceleration in two dimensions. We compare the annotations generated by the face tracking algorithm with independently made manual annotations for head movements. The annotations are a useful supplement to manual annotations and may help human annotators to quickly and reliably determine onset of head movements and to suggest which kind of head movement is taking place.

AB - We describe an automatic face tracker plugin for the ANVIL annotation tool. The face tracker produces data for velocity and for acceleration in two dimensions. We compare the annotations generated by the face tracking algorithm with independently made manual annotations for head movements. The annotations are a useful supplement to manual annotations and may help human annotators to quickly and reliably determine onset of head movements and to suggest which kind of head movement is taking place.

KW - Faculty of Humanities

KW - corpus

KW - discourse annotation

KW - Information extraction

KW - Information retrieval

KW - Processing

KW - representation

M3 - Article in proceedings

SP - 201

EP - 208

BT - Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

PB - European Language Resources Association

T2 - International Conference on Language Resources and Evaluation

Y2 - 23 May 2012 through 25 May 2012

ER -