Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations. / Paggio, Patrizia; Navarretta, Costanza; Jongejan, Bart; Aguirrezabal Zabaleta, Manex.

Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop. Association for Computational Linguistics, 2021. s. 151-159.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Paggio, P, Navarretta, C, Jongejan, B & Aguirrezabal Zabaleta, M 2021, Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations. i Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop. Association for Computational Linguistics, s. 151-159. <https://aclanthology.org/2021.law-1.16.pdf>

APA

Paggio, P., Navarretta, C., Jongejan, B., & Aguirrezabal Zabaleta, M. (2021). Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations. I Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop (s. 151-159). Association for Computational Linguistics. https://aclanthology.org/2021.law-1.16.pdf

Vancouver

Paggio P, Navarretta C, Jongejan B, Aguirrezabal Zabaleta M. Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations. I Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop. Association for Computational Linguistics. 2021. s. 151-159

Author

Paggio, Patrizia ; Navarretta, Costanza ; Jongejan, Bart ; Aguirrezabal Zabaleta, Manex. / Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations. Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop. Association for Computational Linguistics, 2021. s. 151-159

Bibtex

@inproceedings{aec5688487584986a31e9a6ae02716f5,
title = "Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations",
abstract = "We present a method to support the annotation of head movements in video-recorded conversations. Head movement segments from annotated multimodal data are used to train a model to detect head movements in unseen data. The resulting predicted movement sequences are uploaded to the ANVIL tool for post-annotation editing. The automatically identified head movements and the original annotations are compared to assess the overlap between the two. This analysis showed that movement onsets were more easily detected than offsets, and pointed at a number of patterns in the mismatches between original annotations and model predictions that could be dealt with in general terms in post-annotation guidelines.",
author = "Patrizia Paggio and Costanza Navarretta and Bart Jongejan and {Aguirrezabal Zabaleta}, Manex",
year = "2021",
language = "English",
pages = "151--159",
booktitle = "Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop",
publisher = "Association for Computational Linguistics",

}

RIS

TY - GEN

T1 - Towards a Methodology Supporting Semiautomatic Annotation of Head Movements in Video-recorded Conversations

AU - Paggio, Patrizia

AU - Navarretta, Costanza

AU - Jongejan, Bart

AU - Aguirrezabal Zabaleta, Manex

PY - 2021

Y1 - 2021

N2 - We present a method to support the annotation of head movements in video-recorded conversations. Head movement segments from annotated multimodal data are used to train a model to detect head movements in unseen data. The resulting predicted movement sequences are uploaded to the ANVIL tool for post-annotation editing. The automatically identified head movements and the original annotations are compared to assess the overlap between the two. This analysis showed that movement onsets were more easily detected than offsets, and pointed at a number of patterns in the mismatches between original annotations and model predictions that could be dealt with in general terms in post-annotation guidelines.

AB - We present a method to support the annotation of head movements in video-recorded conversations. Head movement segments from annotated multimodal data are used to train a model to detect head movements in unseen data. The resulting predicted movement sequences are uploaded to the ANVIL tool for post-annotation editing. The automatically identified head movements and the original annotations are compared to assess the overlap between the two. This analysis showed that movement onsets were more easily detected than offsets, and pointed at a number of patterns in the mismatches between original annotations and model predictions that could be dealt with in general terms in post-annotation guidelines.

M3 - Article in proceedings

SP - 151

EP - 159

BT - Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

PB - Association for Computational Linguistics

ER -

ID: 284176309