Mathis Group @ EPFL

[ICCV 2023] "Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity"

amathislab

DLC2Action is an action segmentation package that makes running and tracking of machine learning experiments easy.

amathislab

[CVPR 2024] HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

amathislab

[NeurIPS 2023] Latent Exploration for Reinforcement Learning

amathislab

Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models

amathislab

[NeurIPS 2022] DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body

amathislab

[NeurIPS 2022, Neuron 2024] Winning code for the Baoding ball MyoChallenge at NeurIPS 2022

amathislab