Logo du site
  • English
  • Français
  • Se connecter
Logo du site
  • English
  • Français
  • Se connecter
  1. Accueil
  2. Université de Neuchâtel
  3. Publications
  4. From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave
 
  • Details
Options
Vignette d'image

From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave

Auteur(s)
Fuchs, Michael 
Institut du management de l'information 
Genty, Emilie 
Institut de biologie 
Jean-Marc Odobez
Bangerter, Adrian 
Institut de psychologie du travail et des organisations 
Zuberbühler, Klaus 
Institut de biologie 
Cotofrei, Paul 
Institut du management de l'information 
Date de parution
2025-06-23
In
International Journal of Computer Vision
Revu par les pairs
true
Mots-clés
  • Non-human primates · Great apes · Chimpanzees · Animal behavior recognition · Video foundation models · Skeleton-based action recognition · Pose estimation
  • Non-human primates · ...

Résumé
<jats:title>Abstract</jats:title>
<jats:p>This paper addresses the significant challenge of recognizing behaviors in non-human primates, specifically focusing on chimpanzees. Automated behavior recognition is crucial for both conservation efforts and the advancement of behavioral research. However, it is often hindered by the labor-intensive process of manual video annotation. Despite the availability of large-scale animal behavior datasets, effectively applying machine learning models across varied environmental settings remains a critical challenge due to the variability in data collection contexts and the specificity of annotations. In this paper, we introduce <jats:italic>ChimpBehave</jats:italic>, a novel dataset comprising over 2 h and 20 min of video (approximately 215,000 frames) of zoo-housed chimpanzees, annotated with bounding boxes and fine-grained locomotive behavior labels. Uniquely, <jats:italic>ChimpBehave</jats:italic> aligns its behavior classes with those in PanAf, an existing dataset collected in distinct visual environments, enabling the study of cross-dataset generalization - where models are trained on one dataset and tested on another with differing data distributions. We benchmark <jats:italic>ChimpBehave</jats:italic> using state-of-the-art video-based and skeleton-based action recognition models, establishing performance baselines for both within-dataset and cross-dataset evaluations. Our results highlight the strengths and limitations of different model architectures, providing insights into the application of automated behavior recognition across diverse visual settings. The dataset, models, and code can be accessed at: <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://github.com/MitchFuchs/ChimpBehave" ext-link-type="uri">https://github.com/MitchFuchs/ChimpBehave</jats:ext-link>
</jats:p>
Identifiants
https://libra.unine.ch/handle/123456789/35052
_
https://doi.org/10.1007/s11263-025-02484-6
Type de publication
journal article
Dossier(s) à télécharger
 main article: From Forest to Zoo - Great Ape Behavior Recognition with ChimpBehave.pdf (2.36 MB)
google-scholar
Présentation du portailGuide d'utilisationStratégie Open AccessDirective Open Access La recherche à l'UniNE Open Access ORCIDNouveautés

Service information scientifique & bibliothèques
Rue Emile-Argand 11
2000 Neuchâtel
contact.libra@unine.ch

Propulsé par DSpace, DSpace-CRIS & 4Science | v2022.02.00