no code implementations • 4 May 2024 • Joaquim Comas, Adria Ruiz, Federico Sukno
Recent advancements in remote heart rate measurement (rPPG), motivated by data-driven approaches, have significantly improved accuracy.
no code implementations • 11 Mar 2024 • Joaquim Comas, Adria Ruiz, Federico Sukno
The objective of our proposed model is to tailor the CZT to match the characteristics of each specific dataset sensor, facilitating a more optimal and accurate estimation of HR from the rPPG signal without compromising generalization across diverse datasets.
no code implementations • 3 Nov 2023 • Jianxiong Shen, Ruijie Ren, Adria Ruiz, Francesc Moreno-Noguer
To quantify the uncertainty on the learned surface, we model a stochastic radiance field.
no code implementations • 11 Apr 2022 • Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu, Francesc Moreno-Noguer
For this purpose, we build a residual-like permutation-invariant network that successfully refines potentially corrupted initial 3D poses estimated by an off-the-shelf detector.
3D Multi-Person Pose Estimation (absolute) 3D Multi-Person Pose Estimation (root-relative) +1
no code implementations • 21 Mar 2022 • Joaquim Comas, Adria Ruiz, Federico Sukno
We present a lightweight neural model for remote heart rate estimation focused on the efficient spatio-temporal learning of facial photoplethysmography (PPG) based on i) modelling of PPG dynamics by combinations of multiple convolutional derivatives, and ii) increased flexibility of the model to learn possible offsets between the facial video PPG and the ground truth.
1 code implementation • 18 Mar 2022 • Jianxiong Shen, Antonio Agudo, Francesc Moreno-Noguer, Adria Ruiz
For this purpose, our method learns a distribution over all possible radiance fields modelling which is used to quantify the uncertainty associated with the modelled scene.
1 code implementation • 2 Nov 2021 • Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu, Francesc Moreno-Noguer
We address the problem of multi-person 3D body pose and shape estimation from a single image.
no code implementations • 5 Sep 2021 • Jianxiong Shen, Adria Ruiz, Antonio Agudo, Francesc Moreno-Noguer
In this context, we propose Stochastic Neural Radiance Fields (S-NeRF), a generalization of standard NeRF that learns a probability distribution over all the possible radiance fields modeling the scene.
no code implementations • ICCV 2021 • Adria Ruiz, Antonio Agudo, Francesc Moreno
Attribution map visualization has arisen as one of the most effective techniques to understand the underlying inference process of Convolutional Neural Networks.
1 code implementation • 3 Mar 2020 • Adria Ruiz, Jakob Verbeek
We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers.
no code implementations • ICCV 2019 • Adria Ruiz, Jakob Verbeek
Despite the outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited.
no code implementations • 24 Jan 2019 • Adria Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek
Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others.
no code implementations • 1 Mar 2018 • Adria Ruiz, Ognjen Rudovic, Xavier Binefa, Maja Pantic
In this framework, we treat instance-labels as temporally-dependent latent variables in an Undirected Graphical Model.
no code implementations • 6 Sep 2016 • Adria Ruiz, Ognjen Rudovic, Xavier Binefa, Maja Pantic
In this paper, we address the Multi-Instance-Learning (MIL) problem when bag labels are naturally represented as ordinal variables (Multi--Instance--Ordinal Regression).
no code implementations • ICCV 2015 • Adria Ruiz, Joost Van de Weijer, Xavier Binefa
Additionally, we show that SHTL achieves competitive performance compared with state-of-the-art Transductive Learning approaches which face the problem of limited training data by using unlabelled test samples during training.