Biology subjects

Kimock, C.

Publications and source records attributed to Kimock, C..

2 recordsLinked to original sources

bioRxiv2025

PrimateFace: A Machine Learning Resource for Automated Face Analysis in Human and Non-human Primates

Machine learning has revolutionized human face analysis, but equivalent tools for non-human primates remain limited and species-specific, hindering progress in neuroscience, anthropology, and conservation. Here, we present PrimateFace, a comprehensive, cross-species platform for primate facial analysis comprising a systematically curated dataset of 260,000+ images spanning over 60 genera, including a genus-balanced subset of 60,000 images, annotated with bounding boxes and facial landmark configurations. Face detection and facial landmark estimation models trained on PrimateFace achieve high cross-species performance, from tarsiers to gorillas, achieving performance comparable to baseline models trained exclusively on human data (0.34 vs. 0.39 mAP for face detection; 0.061 vs. 0.053 normalized landmark error), demonstrating the generalization benefits of cross-species training. PrimateFace enables diverse downstream applications including individual recognition, gaze analysis, and automated extraction of stereotyped (e.g., lip-smacking) and subtle (e.g., soft left turn) facial movements. PrimateFace provides a standardized platform for facial phenotyping across the primate order, empowering data-driven studies that advance the health and well-being of human and non-human primates. All models, notebooks, and data can be found at github.com/KordingLab/PrimateFace.

animal behavior and cognition↗

bioRxiv2023

Socioecological drivers of injuries in female and male rhesus macaques (Macaca mulatta)

Competition over access to resources, such as food and mates, is believed to be one of the major costs associated with group living. Two socioecological factors suggested to predict the intensity of competition are group size and the relative abundance of sexually active individuals. However, empirical evidence linking these factors to injuries and survival costs is scarce. Here, we leveraged 10 years of data from free-ranging rhesus macaques where injuries inflicted by conspecifics are associated with a high mortality risk. We tested if group size and adult sex ratio predicted the occurrence of injuries and used data on physical aggression to contextualise these results. We found that males were less likely to be injured when living in larger groups, potentially due to advantages in intergroup encounters. Females, instead, had higher injury risk when living in larger groups but this was not explained by within-group aggression among females. Further, male-biased sex ratios predicted a weak increase in injury risk in females and were positively related to male-female aggression, indicating that male coercion during mating competition may be a cause of injuries in females. Overall, our results provide insights into sex differences in the fitness-related costs of competition and empirical evidence for long-standing predictions on the evolution of group living.

evolutionary biology↗