
Detecting the Unexpected via Image Resynthesis
Classical semantic segmentation methods, including the recent deep learn...
read it

Estimating People Flows to Better Count them in Crowded Scenes
Stateoftheart methods for counting people in crowded scenes rely on d...
read it

Shape Reconstruction by Learning Differentiable Surface Representations
Generative models that produce point clouds have emerged as a powerful t...
read it

Segmentationdriven 6D Object Pose Estimation
The most recent trend in estimating the 6D pose of rigid objects has bee...
read it

Interpretable BoW Networks for Adversarial Example Detection
The standard approach to providing interpretability to deep convolutiona...
read it

Neural Scene Decomposition for MultiPerson Motion Capture
Learning general image representations has proven key to the success of ...
read it

Using Depth for PixelWise Detection of Adversarial Attacks in Crowd Counting
Stateoftheart methods for counting people in crowded scenes rely on d...
read it

Indirect Local Attacks for Contextaware Semantic Segmentation Networks
Recently, deep networks have achieved impressive semantic segmentation p...
read it

Selfsupervised Training of Proposalbased Segmentation via Background Prediction
While supervised object detection methods achieve impressive accuracy, t...
read it

VIENA2: A Driving Anticipation Dataset
Action anticipation is critical in scenarios where one needs to react be...
read it

Geometryaware Deep Network for SingleImage Novel View Synthesis
This paper tackles the problem of novel view synthesis from a single ima...
read it

Deep Attentional Structured Representation Learning for Visual Recognition
Structured representations, such as Bags of Words, VLAD and Fisher Vecto...
read it

ContextAware Crowd Counting
Stateoftheart methods for counting people in crowded scenes rely on d...
read it

Residual Parameter Transfer for Deep Domain Adaptation
The goal of Deep Domain Adaptation is to make it possible to use Deep Ne...
read it

Learning to Find Good Correspondences
We develop a deep architecture to learn to find good correspondences for...
read it

Compressionaware Training of Deep Networks
In recent years, great progress has been made in a variety of applicatio...
read it

Soft Correspondences in Multimodal Scene Parsing
Exploiting multiple modalities for semantic scene parsing has been shown...
read it

Deep Subspace Clustering Networks
We present a novel deep neural network architecture for unsupervised sub...
read it

Bringing Background into the Foreground: Making All Classes Equal in Weaklysupervised Video Semantic Segmentation
Pixellevel annotations are expensive and timeconsuming to obtain. Henc...
read it

NonLinear Subspace Clustering with Learned LowRank Kernels
In this paper, we present a kernel subspace clustering method that can h...
read it

Imposing Hard Constraints on Deep Networks: Promises and Limitations
Imposing constraints on the output of a Deep Neural Net is one way to im...
read it

Incorporating Network Builtin Priors in Weaklysupervised Semantic Segmentation
Pixellevel annotations are expensive and time consuming to obtain. Henc...
read it

Encouraging LSTMs to Anticipate Actions Very Early
In contrast to the widely studied problem of recognizing an action given...
read it

Secondorder Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have been successfully applied to m...
read it

Boundaryaware Instance Segmentation
We address the problem of instancelevel semantic segmentation, which ai...
read it

Efficient Linear Programming for Dense CRFs
The fully connected conditional random field (CRF) with Gaussian pairwis...
read it

Learning the Number of Neurons in Deep Networks
Nowadays, the number of layers and of neurons in each layer of a deep ne...
read it

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
Most recent approaches to monocular 3D human pose estimation rely on Dee...
read it

Deep Action and ContextAware Sequence Learning for Activity Recognition and Anticipation
Action recognition and anticipation are key to the success of many compu...
read it

Builtin Foreground/Background Prior for WeaklySupervised Semantic Segmentation
Pixellevel annotations are expensive and time consuming to obtain. Henc...
read it

SemanticAware Depth SuperResolution in Outdoor Scenes
While depth sensors are becoming increasingly popular, their spatial res...
read it

Dimensionality Reduction on SPD Manifolds: The Emergence of GeometryAware Methods
Representing images and videos with Symmetric Positive Definite (SPD) ma...
read it

Beyond Sharing Weights for Deep Domain Adaptation
The performance of a classifier trained on data coming from a specific d...
read it

Robust Multibody Feature Tracker: A Segmentationfree Approach
Feature tracking is a fundamental problem in computer vision, with appli...
read it

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data
The Shape Interaction Matrix (SIM) is one of the earliest approaches to ...
read it

Beyond Gauss: ImageSet Matching on the Riemannian Manifold of PDFs
Stateoftheart imageset matching techniques typically implicitly mode...
read it

When VLAD met Hilbert
Vectors of Locally Aggregated Descriptors (VLAD) have emerged as powerfu...
read it

Optimizing Over Radial Kernels on Compact Manifolds
We tackle the problem of optimizing over all possible positive definite ...
read it

A Framework for Shape Analysis via Hilbert Space Embedding
We propose a framework for 2D shape analysis using positive definite ker...
read it

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Symmetric Positive Definite (SPD) matrices have become popular to encode...
read it

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
In this paper, we develop an approach to exploiting kernel methods with ...
read it

Iteratively Reweighted Graph Cut for Multilabel MRFs with Nonconvex Priors
While widely acknowledged as highly effective in computer vision, multi...
read it

Kernel Coding: General Formulation and Special Cases
Representing images by compact codes has proven beneficial for many visu...
read it

Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Modeling videos and imagesets as linear subspaces has proven beneficial...
read it

From Manifold to Manifold: GeometryAware Dimensionality Reduction for SPD Matrices
Representing images and videos with Symmetric Positive Definite (SPD) ma...
read it

Statistically Motivated Second Order Pooling
Secondorder pooling, a.k.a. bilinear pooling, has proven effective for ...
read it

Eigendecompositionfree Training of Deep Networks with Zero Eigenvaluebased Losses
Many classical Computer Vision problems, such as essential matrix comput...
read it

Learning Monocular 3D Human Pose Estimation from Multiview Images
Accurate 3D human pose estimation from single images is possible with so...
read it

Learning ShapefromShading for Deformable Surfaces
Recent years have seen the development of mature solutions for reconstru...
read it

Geometric and Physical Constraints for Head Plane Crowd Density Estimation in Videos
Stateoftheart methods of people counting in crowded scenes rely on de...
read it
Mathieu Salzmann
is this you? claim profile
Scientist and Lecturer at Ecole Polytechnique F´ed´erale de Lausanne