Search Results for author: João Paulo Costeira

Found 6 papers, 2 papers with code

Rotation Averaging: A Primal-Dual Method and Closed-Forms in Cycle Graphs

no code implementations29 May 2024 Gabriel Moreira, Manuel Marques, João Paulo Costeira

A cornerstone of geometric reconstruction, rotation averaging seeks the set of absolute rotations that optimally explains a set of measured relative orientations between them.

Simultaneous Localization and Mapping

Learning Visual-Semantic Subspace Representations for Propositional Reasoning

no code implementations25 May 2024 Gabriel Moreira, Alexander Hauptmann, Manuel Marques, João Paulo Costeira

Learning representations that capture rich semantic relationships and accommodate propositional calculus poses a significant challenge.

2D Image head pose estimation via latent space regression under occlusion settings

1 code implementation10 Nov 2023 José Celestino, Manuel Marques, Jacinto C. Nascimento, João Paulo Costeira

Head orientation is a challenging Computer Vision problem that has been extensively researched having a wide variety of applications.

Head Pose Estimation regression

Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin

no code implementations18 Sep 2023 Gabriel Moreira, Manuel Marques, João Paulo Costeira, Alexander Hauptmann

Recent research in representation learning has shown that hierarchical data lends itself to low-dimensional and highly informative representations in hyperbolic space.

Few-Shot Learning Representation Learning

Rotation Averaging in a Split Second: A Primal-Dual Method and a Closed-Form for Cycle Graphs

1 code implementation ICCV 2021 Gabriel Moreira, Manuel Marques, João Paulo Costeira

A cornerstone of geometric reconstruction, rotation averaging seeks the set of absolute rotations that optimally explains a set of measured relative orientations between them.

LocDyn: Robust Distributed Localization for Mobile Underwater Networks

no code implementations27 Jan 2017 Cláudia Soares, João Gomes, Beatriz Ferreira, João Paulo Costeira

LocDyn is robust: it rejects outlier noise, while the comparing methods succumb in terms of positioning error.

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