Triple-stream Deep Metric Learning of Great Ape Behavioural Actions

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

1 Citation (Scopus)
1 Downloads (Pure)

Abstract

We propose the first metric learning system for the recognition of great ape behavioural actions. Our proposed triple stream embedding architecture works on camera trap videos taken directly in the wild and demonstrates that the utilisation of an explicit DensePose-C chimpanzee body part segmentation stream effectively complements traditional RGB appearance and optical flow streams. We evaluate system variants with different feature fusion techniques and long-tail recognition approaches. Results and ablations show performance improvements of ~12% in top-1 accuracy over previous results achieved on the PanAf-500 dataset containing 180,000 manually annotated frames across nine behavioural actions. Furthermore, we provide a qualitative analysis of our findings and augment the metric learning system with long-tail recognition techniques showing that average per class accuracy -- critical in the domain -- can be improved by ~23% compared to the literature on that dataset. Finally, since our embedding spaces are constructed as metric, we provide first data-driven visualisations of the great ape behavioural action spaces revealing emerging geometry and topology. We hope that the work sparks further interest in this vital application area of computer vision for the benefit of endangered great apes.
Original languageEnglish
Title of host publication Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - VISAPP
EditorsPetia Radeva, Giovanni Maria Farinella, Kadi Bouatouch
PublisherSciTePress
Pages294-302
Number of pages9
Volume5
ISBN (Electronic)9789897586347
DOIs
Publication statusPublished - 21 Feb 2023

Publication series

NameProceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP
PublisherSciTePress
ISSN (Electronic)2184-4321

Fingerprint

Dive into the research topics of 'Triple-stream Deep Metric Learning of Great Ape Behavioural Actions'. Together they form a unique fingerprint.

Cite this