Towards Representation Learning for Phenotyping Beyond Animal Pose Estimation
Abstract
Understanding and quantifying behavior is crucial for phenotyping in biological and medical research. While pose estimation methods like DeepLabCut (DLC) provide structured representations of animal movement, they struggle with occlusions and rapid motion. In this study, we integrate TAPIR with DLC to enhance robust pose tracking, improving continuity and reducing missing key points. Furthermore, we apply CEBRA to refined pose sequences to learn behavioral representations, facilitating computational phenotyping. Experimental results show that our method significantly improves tracking performance, providing a foundation for structured and interpretable representation learning of biological dynamics.
Cite
Text
Kubo et al. "Towards Representation Learning for Phenotyping Beyond Animal Pose Estimation." ICLR 2025 Workshops: LMRL, 2025.Markdown
[Kubo et al. "Towards Representation Learning for Phenotyping Beyond Animal Pose Estimation." ICLR 2025 Workshops: LMRL, 2025.](https://mlanthology.org/iclrw/2025/kubo2025iclrw-representation/)BibTeX
@inproceedings{kubo2025iclrw-representation,
title = {{Towards Representation Learning for Phenotyping Beyond Animal Pose Estimation}},
author = {Kubo, Takatomi and Nakajima, Nina and Miyai, Nanako and Osaki, Midori and Higashitsutsumi, Suzuka},
booktitle = {ICLR 2025 Workshops: LMRL},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/kubo2025iclrw-representation/}
}