Lightning Pose: improved animal pose estimation via semi-supervised learning, Bayesian ensembling and cloud-native open-source tools

D Biderman, MR Whiteway, C Hurwitz, N Greenspan… - Nature …, 2024 - nature.com
Contemporary pose estimation methods enable precise measurements of behavior via
supervised deep learning with hand-labeled video frames. Although effective in many cases …

replicAnt: a pipeline for generating annotated images of animals in complex environments using Unreal Engine

F Plum, R Bulla, HK Beck, N Imirzian… - Nature …, 2023 - nature.com
Deep learning-based computer vision methods are transforming animal behavioural
research. Transfer learning has enabled work in non-model species, but still requires hand …

Whole-body simulation of realistic fruit fly locomotion with deep reinforcement learning

R Vaxenburg, I Siwanowicz, J Merel, AA Robie… - bioRxiv, 2024 - biorxiv.org
The body of an animal influences how the nervous system produces behavior. Therefore,
detailed modeling of the neural control of sensorimotor behavior requires a detailed model …

Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos

K Sun, D Litvak, Y Zhang, H Li, J Wu, S Wu - European Conference on …, 2024 - Springer
We introduce a new method for learning a generative model of articulated 3D animal
motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion …

Linking cognitive strategy, neural mechanism, and movement statistics in group foraging behaviors

R Urbaniak, M **e, E Mackevicius - Scientific Reports, 2024 - nature.com
Foraging for food is a rich and ubiquitous animal behavior that involves complex cognitive
decisions, and interactions between different individuals and species. There has been …

UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-view and Temporal Cues

V Davoodnia, S Ghorbani, MA Carbonneau… - … on Computer Vision, 2024 - Springer
We introduce UPose3D, a novel approach for multi-view 3D human pose estimation,
addressing challenges in accuracy and scalability. Our method advances existing pose …

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Y Yang, Y Qiao, X Sun - European Conference on Computer Vision, 2024 - Springer
Automatic estimation of 3D human pose from monocular RGB images is a challenging and
unsolved problem in computer vision. In a supervised manner, approaches heavily rely on …

Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

M Azabou, M Mendelson, N Ahad… - Advances in …, 2024 - proceedings.neurips.cc
Unconstrained and natural behavior consists of dynamics that are complex and
unpredictable, especially when trying to predict what will happen multiple steps into the …

Application of a novel deep learning–based 3D videography workflow to bat flight

J Håkansson, BL Quinn, AL Shultz… - Annals of the New …, 2024 - Wiley Online Library
Studying the detailed biomechanics of flying animals requires accurate three‐dimensional
coordinates for key anatomical landmarks. Traditionally, this relies on manually digitizing …

Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos

K Sun, D Litvak, Y Zhang, H Li, J Wu, S Wu - arxiv preprint arxiv …, 2023 - arxiv.org
We introduce Ponymation, a new method for learning a generative model of articulated 3D
animal motions from raw, unlabeled online videos. Unlike existing approaches for motion …