Animal social behavior is complex. Species from ants to wolves to mice form social groups where they build nests, raise their young, care for their groupmates, and defend their territory. Studying these behaviors teaches us about the brain and the evolution of behavior, but the work has usually required subjective, time-consuming documenting of animals' actions. ML advancements now let us automate this process, supporting large-scale behavioral studies in the wild and in the lab.

But even automated systems suffer from limited training data and poor generalizability. In current methods, an experimenter must hand-label hundreds of new training examples to automate recognition of a new behavior, which makes studying rare behaviors a challenge. And models trained within one research group usually fail when applied to data from other studies, meaning there is no guarantee that two labs are really studying the same behavior.

This competition challenges you to build models to identify over 30 different social and non-social behaviors in pairs and groups of co-housed mice, based on markerless motion capture of their movements in top-down video recordings. The dataset includes over 400 hours of footage from 20+ behavioral recording systems, all carefully labeled frame-by-frame by experts. Your goal is to recognize these behaviors as accurately as a trained human observer while overcoming the inherent variability arising from the use of different data collection equipment and motion capture pipelines.

Your work will help scientists automate behavior analysis and better understand animal social structures. These models may be deployed across numerous labs, in neuroscience, computational biology, ethology, and ecology, to create a foundation for future ML and behavior research.