EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PoseR: a deep learning toolbox for classifying animal behaviour

Pierce N Mullen, Beatrice Bowlby, Holly C Armstrong, Angus Gray, Maarten F Zwart iD

Open Biology · 21.01.2026 · 16 (1)

DOI: 10.1098/rsob.250322 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Biology, online erschienen am 21.01.2026. Verfasst von Pierce N Mullen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Psychology and Neuroscience, Centre of Biophotonics, University of St Andrews, St Andrews, UK. Hauptthemen laut MEDLINE: Deep Learning, Behavior, Animal. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RS Macdonald Charitable Trust, Biotechnology and Biological Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The actions of animals provide a window into how their minds work. Recent advances in deep learning are providing powerful approaches to recognize patterns of animal movement from video recordings using markerless pose estimation models. Current methods for classifying animal behaviour using the outputs of these models often rely on species and task-specific feature engineering of trajectories, kinematics and task programming. Generalized solutions that use only pose estimations and the inherent structure of animals and their environment provide an opportunity to develop foundational, contextual and, importantly, standardized animal behaviour models for efficient and reproducible behavioural analysis. Here, we present PoseRecognition (PoseR), a behavioural classifier using spatio-temporal graph convolutional networks. We show that it can be used to classify animal behaviour quickly and accurately from pose estimations, using zebrafish larvae, Drosophila melanogaster, mice and rats as model organisms. Our easily accessible tool simplifies the behavioural analysis workflow by transforming coordinates of animal position and pose into semantic labels with speed and precision. The design of our tool ensures scalability and versatility for use across multiple species and contexts, improving the efficiency of behavioural analysis across fields.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBehavior, AnimalAnimalsDrosophila melanogasterZebrafishMiceVideo RecordingRatsClassification AlgorithmsGraph Neural Networks

Stichwörter der Autor:innen

behaviour classificationcomputer visiondeep learning

Autor:innen und Institutionen

  • School of Psychology and Neuroscience, Centre of Biophotonics, University of St Andrews, St Andrews, UK.

ORCID-Profile: Maarten F Zwart

Förderung

  • RS Macdonald Charitable Trust
  • Biotechnology and Biological Sciences Research Council

Zitieren

APA

Mullen, P. N., Bowlby, B., Armstrong, H. C., Gray, A., & Zwart, M. F. (2026). PoseR: a deep learning toolbox for classifying animal behaviour. Open Biology, 16(1). https://doi.org/10.1098/rsob.250322

Vancouver

Mullen PN, Bowlby B, Armstrong HC, Gray A, Zwart MF. PoseR: a deep learning toolbox for classifying animal behaviour. Open Biology. 2026;16(1). doi:10.1098/rsob.250322

BibTeX
@article{Mullen2026,
  author = {Mullen, Pierce N and Bowlby, Beatrice and Armstrong, Holly C and Gray, Angus and Zwart, Maarten F},
  title = {PoseR: a deep learning toolbox for classifying animal behaviour},
  journal = {Open Biology},
  year = {2026},
  volume = {16},
  number = {1},
  doi = {10.1098/rsob.250322}
}
Kostenlos starten →