Home

Person

Mathieu Salzmann

About
Privacy
Disclaimer

Graph Chatbot

Related publications (159)

Page 3 of 8

Learning Monocular 3D Human Pose Estimation from Multi-view Images

Pascal Fua, Mathieu Salzmann, Frédéric Meyer, Helge Jochen Rhodin, Isinsu Katircioglu, Victor Constantin

Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Ma ...

IEEE2018

A Stochastic Conditioning Scheme for Diverse Human Motion Prediction

Mathieu Salzmann

Human motion prediction, the task of predicting future 3D human poses given a sequence of observed ones, has been mostly treated as a deterministic problem. However, human motion is a stochastic process: Given an observed sequence of poses, multiple future ...

IEEE2020

Robust Differentiable SVD

Pascal Fua, Mathieu Salzmann, Wei Wang, Yinlin Hu, Zheng Dang

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether using the SVD to compute them analytically or using the Power Iteration (PI) ...

2021

Shape Reconstruction by Learning Differentiable Surface Representations

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík, Erhan Gündogdu

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations. Unfortunately, they offer no control over the deformations of the su ...

IEEE2020

Structured Prediction of 3D Human Pose with Deep Neural Networks

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Bugra Tekin, Isinsu Katircioglu

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a ...

2016

Contrastive Class-aware Adaptation for Domain Generalization

Mathieu Salzmann

Domain generalization (DG) tackles the problem of learning a model that generalizes to data drawn from a target domain that was unseen during training. A major trend in this area consists of learning a domain-invariant representation by minimizing the disc ...

IEEE2022

Residual Parameter Transfer for Deep Domain Adaptation

Pascal Fua, Mathieu Salzmann, Artem Rozantsev

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning feature representation ...

2018

Contextually Plausible and Diverse 3D Human Motion Prediction

Mathieu Salzmann

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational Autoencoder (CVAE). How ...

IEEE2021

Statistically-Motivated Second-order Pooling

Mathieu Salzmann, Kaicheng Yu

Second-order pooling, a.k.a. bilinear pooling, has proven effective for deep learning based visual recognition. However, the resulting second-order networks yield a final representation that is orders of magnitude larger than that of standard, first-order ...

2018

History Repeats Itself: Human Motion Prediction Via Motion Attention

Mathieu Salzmann

Human motion prediction aims to forecast future human poses given a past motion. Whether based on recurrent or feed-forward neural networks, existing methods fail to model the observation that human motion tends to repeat itself, even for complex sports ac ...

Springer Nature2020

Segmentation of Developing Human Embryo in Time-lapse Microscopy

Mathieu Salzmann

Being able to efficiently segment a developing embryo from background clutter constitutes an important step in automated monitoring of human embryonic cells. State-of-the-art automatic segmentation methods remain ill-suited to handle the complex behavior a ...

IEEE2016

Geometry-Aware Deep Recurrent Neural Networks for Hyperspectral Image Classification

Mathieu Salzmann, Wei Wang

Variants of deep networks have been widely used for hyperspectral image (HSI)-classification tasks. Among them, in recent years, recurrent neural networks (RNNs) have attracted considerable attention in the remote sensing community. However, complex geomet ...

2021

Fast Adversarial Training With Adaptive Step Size

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

Ieee-Inst Electrical Electronics Engineers Inc2023

A method for asteroid detection using convolutional neural networks on VST images

Jean-Paul Richard Kneib, Mathieu Salzmann, Frédéric Dux, Stephan Hellmich, Elisabeth Andréa Cécile Rachith

Context. The study of asteroids, particularly near-Earth asteroids, is key to gaining insights into our Solar System and can help prevent dangerous collisions. Beyond finding new objects, additional observations of known asteroids will improve our knowledg ...

2025

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields

Mathieu Salzmann

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns bec ...

Association for Computing Machinery, Inc2024

A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila

Deep networks such as the U-Net are outstanding at segmenting biomedical images when enough training data is available, but only then. Here we introduce a Domain Adaptation approach that relies on two coupled U-Nets that either regularize or share correspo ...

IEEE2018

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Mathieu Salzmann

Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts. How ...

IEEE2021

Robust Binary Models by Pruning Randomly-initialized Networks

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

2022

A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation

Pascal Fua, Mathieu Salzmann, Pablo Marquez Neila, Róger Bermúdez Chacón

2018

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

Pascal Fua, Mathieu Salzmann, Helge Jochen Rhodin, Sena Kiciroglu

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yie ...

IEEE2020