Multi-animal pose estimation and tracking with DeepLabCut
J. Lauer, M. Zhou, S. Ye, W. Menegas, T. Nath, M. M. Rahman, V. Di Santo, D. Soberanes, G. Feng, V. N. Murthy, G. Lauder, C. Dulac, M. W. Mathis, A. Mathis
The paper enhances DeepLabCut for multi-animal pose estimation and tracking by adding identity prediction and robust assembly features, validated on four benchmark datasets.
bioRxiv · Apr 30, 2021Animal Behavior & Cognition