ConstrastivePose: A contrastive learning approach for self-supervised feature engineering for pose estimation and behavorial classification of interacting animals
T. Zhou, C. C. H. Cheah, E. W. M. Chin, J. Chen, H. J. Farm, E. L. K. Goh, K.-H. Chiam
This paper introduces ConstrastivePose, a contrastive learning method for self-supervised feature engineering in pose estimation and behavioral classification of interacting animals, showing improved performance over handcrafted features.
bioRxiv · Nov 9, 2022 · PreprintAnimal Behavior & Cognition