Search Results for author: Alexander Mathis

Found 19 papers, 15 papers with code

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

1 code implementation26 Feb 2024 Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis

These representations are typically explicit, such as 3D point clouds or meshes, and thus provide information in the direct surroundings of the intermediate hand pose estimate.

 Ranked #1 on hand-object pose on HO-3D (using extra training data)

hand-object pose Object +1

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

1 code implementation9 Oct 2023 Stéphane d'Ascoli, Sören Becker, Alexander Mathis, Philippe Schwaller, Niki Kilbertus

We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory.

regression Symbolic Regression

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

1 code implementation NeurIPS 2023 Shaokai Ye, Jessy Lauer, Mu Zhou, Alexander Mathis, Mackenzie W. Mathis

To overcome the context window limitation, we implement a novel dual-memory mechanism to allow communication between short-term and long-term memory using symbols as context pointers for retrieval and saving.


Latent Exploration for Reinforcement Learning

1 code implementation NeurIPS 2023 Alberto Silvio Chiappa, Alessandro Marin Vargas, Ann Zixiang Huang, Alexander Mathis

In the PyBullet locomotion tasks, Lattice-SAC achieves state of the art results, and reaches 18% higher reward than unstructured exploration in the Humanoid environment.


DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body

1 code implementation28 Sep 2022 Alberto Silvio Chiappa, Alessandro Marin Vargas, Alexander Mathis

Learning to locomote when the length and the thickness of different body parts vary is challenging, as the control policy is required to adapt to the morphology to successfully balance and advance the agent.

Continuous Control Inductive Bias

AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild

1 code implementation24 Mar 2021 Daniel Joska, Liam Clark, Naoya Muramatsu, Ricardo Jericevich, Fred Nicolls, Alexander Mathis, Mackenzie W. Mathis, Amir Patel

Animals are capable of extreme agility, yet understanding their complex dynamics, which have ecological, biomechanical and evolutionary implications, remains challenging.

3D Pose Estimation Animal Pose Estimation +1

Measuring and modeling the motor system with machine learning

no code implementations22 Mar 2021 Sébastien B. Hausmann, Alessandro Marin Vargas, Alexander Mathis, Mackenzie W. Mathis

The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data.

BIG-bench Machine Learning Dimensionality Reduction +2

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

2 code implementations22 Mar 2021 Lucas Stoffl, Maxime Vidal, Alexander Mathis

Inspired by recent work on end-to-end trainable object detection with transformers, we use a transformer encoder-decoder architecture together with a bipartite matching scheme to directly regress the pose of all individuals in a given image.

Decoder Keypoint Detection +2

A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives

1 code implementation1 Sep 2020 Alexander Mathis, Steffen Schneider, Jessy Lauer, Mackenzie W. Mathis

Extracting behavioral measurements non-invasively from video is stymied by the fact that it is a hard computational problem.

Deep learning tools for the measurement of animal behavior in neuroscience

6 code implementations30 Sep 2019 Mackenzie W. Mathis, Alexander Mathis

Recent advances in computer vision have made accurate, fast and robust measurement of animal behavior a reality.

Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.