Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision
This addresses the need for automated keypoint annotation in biology to study social interactions, reducing reliance on manual work, though it is incremental as it builds on existing self-supervised keypoint discovery methods.
The paper tackled the problem of analyzing multi-agent behaviors in videos by introducing B-KinD-multi, a self-supervised method that uses pre-trained segmentation models to discover keypoints without manual annotations, resulting in improved keypoint regression and behavioral classification for species like flies, mice, and rats.
The study of social interactions and collective behaviors through multi-agent video analysis is crucial in biology. While self-supervised keypoint discovery has emerged as a promising solution to reduce the need for manual keypoint annotations, existing methods often struggle with videos containing multiple interacting agents, especially those of the same species and color. To address this, we introduce B-KinD-multi, a novel approach that leverages pre-trained video segmentation models to guide keypoint discovery in multi-agent scenarios. This eliminates the need for time-consuming manual annotations on new experimental settings and organisms. Extensive evaluations demonstrate improved keypoint regression and downstream behavioral classification in videos of flies, mice, and rats. Furthermore, our method generalizes well to other species, including ants, bees, and humans, highlighting its potential for broad applications in automated keypoint annotation for multi-agent behavior analysis. Code available under: https://danielpkhalil.github.io/B-KinD-Multi