Home

Person

Mathieu Salzmann

About
Privacy
Disclaimer

Graph Chatbot

Related publications (169)

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

Pascal Fua, Mathieu Salzmann, Weizhe Liu, Krzysztof Maciej Lis

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image- plane density has no immediate physical meaning because it is subject to perspecti ...

IEEE2019

Segmentation-driven 6D Object Pose Estimation

Pascal Fua, Mathieu Salzmann, Joachim Ludovic Hugonot, Yinlin Hu

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. I ...

IEEE2019

Neural Scene Decomposition for Multi-Person Motion Capture

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

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

IEEE2019

Learning Trajectory Dependencies for Human Motion Prediction

Mathieu Salzmann, Hongwei Li, Wei Mao

Human motion prediction, i.e., forecasting future body poses given observed pose sequence, has typically been tackled with recurrent neural networks (RNNs). However, as evidenced by prior work, the resulted RNN models suffer from prediction errors accumula ...

IEEE2019

VIENA(2): A Driving Anticipation Dataset

Mathieu Salzmann, Fatemehsadat Saleh

Action anticipation is critical in scenarios where one needs to react before the action is finalized. This is, for instance, the case in automated driving, where a car needs to, e.g., avoid hitting pedestrians and respect traffic lights. While solutions ha ...

SPRINGER INTERNATIONAL PUBLISHING AG2019

Backpropagation-Friendly Eigendecomposition

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

Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it with the Power Iteration method, particularly when dealing with large matri ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2019

Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials

Mathieu Salzmann

Dense conditional random fields (CRFs) have become a popular framework for modeling several problems in computer vision such as stereo correspondence and multiclass semantic segmentation. By modeling long-range interactions, dense CRFs provide a labeling t ...

SIAM PUBLICATIONS2019

Overcoming Multi-model Forgetting

Anthony Christopher Davison, Mathieu Salzmann, Yassine Benyahia, Claudiu-Cristian Musat, Kaicheng Yu, Martin Jaggi

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, ...

JMLR2019

Detecting the Unexpected via Image Resynthesis

Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Krishna Kanth Nakka

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes ...

IEEE2019

Context-Aware Crowd Counting

Pascal Fua, Mathieu Salzmann, Weizhe Liu

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to compensate for p ...

IEEE/CVF2019

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Pascal Fua, Mathieu Salzmann, Victor Constantin, Erhan Gündogdu

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking ...

IEEE2019

Memory Efficient Max Flow for Multi-Label Submodular MRFs

Mathieu Salzmann

Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable X-i is represented by l nodes (where l is the number of labels) arranged in a c ...

2019

Beyond Sharing Weights for Deep Domain Adaptation

Pascal Fua, Mathieu Salzmann, Artem Rozantsev

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractic ...

2018

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny, Yuki Ono

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

2018

Learning Latent Representations of 3D Human Pose with Deep Neural Networks

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Bugra Tekin

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

2018

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

Pascal Fua, Mathieu Salzmann, Fei Wang, Kwang Moo Yi, Zheng Dang, Yinlin Hu

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by ﬁnding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear sy ...

2018

Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods

Mathieu Salzmann

2018

Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation

Mathieu Salzmann, Fatemehsadat Saleh

2018

Learning to Find Good Correspondences

Pascal Fua, Mathieu Salzmann, Vincent Lepetit, Kwang Moo Yi, Eduard Trulls Fortuny, Yuki Ono

IEEE2018

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Pascal Fua, Mathieu Salzmann, Jan Bednarík

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, a ...

2018

Page 6 of 9