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

Patrizia Paggio, Costanza Navarretta, Bart Jongejan, Manex Agirrezabal


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.
Anthology ID:
2021.law-1.16
Volume:
Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
DMR | EMNLP | LAW
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
151–159
Language:
URL:
https://aclanthology.org/2021.law-1.16
DOI:
10.18653/v1/2021.law-1.16
Bibkey:
Cite (ACL):
Patrizia Paggio, Costanza Navarretta, Bart Jongejan, and Manex Agirrezabal. 2021. Towards a Methodology Supporting Semiautomatic Annotation of HeadMovements in Video-recorded Conversations. In Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop, pages 151–159, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Towards a Methodology Supporting Semiautomatic Annotation of HeadMovements in Video-recorded Conversations (Paggio et al., LAW 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.law-1.16.pdf