EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Temporal Video Segmentation Approach for Peruvian Sign Language

Summy Farfan iD, Juan J Choquehuanca-Zevallos iD, Ana Aguilera iD, Irvin Dongo iD, Yudith Cardinale iD

Sensors · 2025

DOI: 10.3390/s25175217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Summy Farfan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Electrical and Electronics Engineering Department, Universidad Católica San Pablo, Arequipa 04001, Peru. Hauptthemen laut MEDLINE: Sign Language, Video Recording. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PROCIENCIA-CONCYTEC, PROCIENCIA, ANID, Chile.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Continuous Sign Language Recognition is a task that involves the recognition of complete sequences of Sign Language videos and translating them into spoken or written language. This task is particularly challenging due to the complex temporal structure and variability in signing styles. In this context, temporal video segmentation emerges to distinguish individual signs from transitions in continuous video streams. Despite its importance, temporal segmentation for Sign Language has not yet fully benefited from recent advancements in Machine Learning. Many existing approaches still rely on outdated architecture. This study aims to learn the characteristics that distinguish signs from transitions, which are fundamental elements of Sign Language. To this end, we adapt two current temporal segmentation models, DiffAct and MS-TCN, and apply them to our own precisely annotated datasets for Peruvian Sign Language. We explore three training strategies—baseline, data augmentation, and multi-dataset. Results suggest that they can enhance the scores for both models but at the cost of increased variability across splits. Notably, the diffusion-based model showcased its ability to generalize to unseen sequences through higher scores for sign and transition identification on the test set, reaching a median value of 71.89% for mF1S and 72.68% for mF1B.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sign LanguageVideo RecordingHumansMachine LearningPeruAlgorithms

Stichwörter der Autor:innen

Peruvian Sign Languagedeep learningdiffusion networktemporal segmentation

Autor:innen und Institutionen

  • Electrical and Electronics Engineering Department, Universidad Católica San Pablo, Arequipa 04001, Peru.
  • Department of Signal Theory and Communications, Universidad Carlos III de Madrid, 28911 Leganes, Spain.
  • Escuela de Ingeniería Informática, Facultad de Ingeniería, Universidad de Valparaíso, Valparaíso 2340000, Chile.
  • MEDING Interdisciplinary Center, Facultad de Ingeniería, Universidad de Valparaíso, Valparaíso 2340000, Chile.
  • ESTIA Institute of Technology, University of Bordeaux, 64210 Bidart, France.
  • Centro de Estudios en Ciencia de Datos e Inteligencia Artificial (ESenCIA), Universidad Internacional de Valencia, 46002 València, Spain.

ORCID-Profile: Summy Farfan, Juan J Choquehuanca-Zevallos, Ana Aguilera, Irvin Dongo, Yudith Cardinale

Förderung

  • PROCIENCIA-CONCYTEC
  • PROCIENCIA
  • ANID, Chile

Zitieren

APA

Farfan, S., Choquehuanca-Zevallos, J. J., Aguilera, A., Dongo, I., & Cardinale, Y. (2025). Temporal Video Segmentation Approach for Peruvian Sign Language. Sensors. https://doi.org/10.3390/s25175217

Vancouver

Farfan S, Choquehuanca-Zevallos JJ, Aguilera A, Dongo I, Cardinale Y. Temporal Video Segmentation Approach for Peruvian Sign Language. Sensors. 2025. doi:10.3390/s25175217

BibTeX
@article{Farfan2025,
  author = {Farfan, Summy and Choquehuanca-Zevallos, Juan J and Aguilera, Ana and Dongo, Irvin and Cardinale, Yudith},
  title = {Temporal Video Segmentation Approach for Peruvian Sign Language},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25175217}
}
Kostenlos starten →