no code implementations • 22 May 2024 • Yingxue Yu, Vidit Vidit, Andrey Davydov, Martin Engilberge, Pascal Fua
Animal Re-ID is crucial for wildlife conservation, yet it faces unique challenges compared to person Re-ID.
no code implementations • 14 Mar 2024 • Andrey Davydov, Martin Engilberge, Mathieu Salzmann, Pascal Fua
Even the best current algorithms for estimating body 3D shape and pose yield results that include body self-intersections.
1 code implementation • CVPR 2023 • Vidit Vidit, Martin Engilberge, Mathieu Salzmann
Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain.
1 code implementation • CVPR 2023 • Vidit Vidit, Martin Engilberge, Mathieu Salzmann
The performance of modern object detectors drops when the test distribution differs from the training one.
1 code implementation • 19 Oct 2022 • Martin Engilberge, Weizhe Liu, Pascal Fua
Multi-view approaches to people-tracking have the potential to better handle occlusions than single-view ones in crowded scenes.
Ranked #2 on Multi-Object Tracking on Wildtrack
1 code implementation • 19 Oct 2022 • Martin Engilberge, Haixin Shi, Zhiye Wang, Pascal Fua
Data augmentation has proven its usefulness to improve model generalization and performance.
1 code implementation • CVPR 2019 • Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord
Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores.
no code implementations • ICCV 2019 • Romain Cohendet, Claire-Hélène Demarty, Ngoc Q. K. Duong, Martin Engilberge
Humans share a strong tendency to memorize/forget some of the visual information they encounter.
1 code implementation • CVPR 2018 • Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord
Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships.