J
Jacob M. Graving
Researcher at Max Planck Society
Publications - 15
Citations - 632
Jacob M. Graving is an academic researcher from Max Planck Society. The author has contributed to research in topics: Deep learning & Pose. The author has an hindex of 7, co-authored 13 publications receiving 340 citations. Previous affiliations of Jacob M. Graving include University of Konstanz & Bowling Green State University.
Papers
More filters
Journal ArticleDOI
DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
Jacob M. Graving,Daniel Chae,Hemal Naik,Liang Li,Liang Li,Benjamin Koger,Benjamin Koger,Blair R. Costelloe,Blair R. Costelloe,Iain D. Couzin,Iain D. Couzin +10 more
TL;DR: A new easy-to-use software toolkit, DeepPoseKit, is introduced that addresses animal pose estimation problems using an efficient multi-scale deep-learning model, called Stacked DenseNet, and a fast GPU-based peak-detection algorithm for estimating keypoint locations with subpixel precision.
Journal ArticleDOI
Vortex phase matching as a strategy for schooling in robots and in fish.
Liang Li,Máté Nagy,Jacob M. Graving,Jacob M. Graving,Joseph B. Bak-Coleman,Guangming Xie,Iain D. Couzin,Iain D. Couzin +7 more
TL;DR: Bio-mimetic fish-like robots are developed which allow us to measure directly the energy consumption associated with swimming together in pairs and find that followers, in any relative position to a near-neighbour, could obtain hydrodynamic benefits if they exhibit a tailbeat phase difference that varies linearly with front-back distance.
Journal ArticleDOI
An automated barcode tracking system for behavioural studies in birds
Gustavo Alarcón-Nieto,Jacob M. Graving,James A. Klarevas-Irby,Adriana Alexandra Maldonado-Chaparro,Inge Mueller,Damien R. Farine +5 more
TL;DR: The most important desafio importante que la automatización puede superar es the observación of muchos individuos a la vez, lo que permite el seguimiento de todo el grupo o de toda la población.
Posted ContentDOI
VAE-SNE: a deep generative model for simultaneous dimensionality reduction and clustering
TL;DR: It is found that VAE-SNE produces high-quality compressed representations with results that are on par with existing nonlinear dimensionality reduction algorithms, and can be used for unsupervised action recognition to detect and classify repeated motifs of stereotyped behavior in high-dimensional timeseries data.
Journal ArticleDOI
Amblypygids: Model Organisms for the Study of Arthropod Navigation Mechanisms in Complex Environments?
TL;DR: Some recent discoveries related to navigation by amblypygids, nocturnal arachnids that inhabit the tropics and sub-tropics that possess navigational abilities that are reminiscent of true-navigating vertebrates are discussed.