PriMAT: Robust multi-animal tracking of primates in the wild
Richard Vogg, Matthias Nuske, Marissa A Weis, Timo Lüddecke, Elif Karakoç, Zurna Ahmed, Sofia M Pereira, Suchinda Malaivijitnond · 2026
Read PriMAT: Robust multi-animal tracking of primates in the wild by Richard Vogg, Matthias Nuske, Marissa A Weis, Timo Lüddecke, Elif Karakoç, Zurna Ahmed, Sofia M Pereira, Suchinda Malaivijitnond (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0347669.txt.
Description
Richard Vogg and colleagues present PriMAT, software that tracks individual primates in wild video footage, a job deep learning usually does well only in tidy laboratories. Forest light shifts, animals hide behind each other, and backgrounds change constantly. PriMAT learns from simple labelled boxes around animals rather than detailed body points, making training data far quicker to prepare.
With only a few hundred labelled frames, the system tracked Assamese macaques and red-fronted lemurs robustly, and transferred to baboons, chimpanzees, and gorillas. An added identification branch named individual lemurs with eighty-four percent accuracy. Code and models are public, offering field researchers automated behaviour watching.
Catalog record
| CREATOR | Richard Vogg, Matthias Nuske, Marissa A Weis, Timo Lüddecke, Elif Karakoç, Zurna Ahmed, Sofia M Pereira, Suchinda Malaivijitnond |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56003 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |