Publications

Benchmarking large multimodal models for ophthalmic visual question answering with OphthalWeChat

P. Xu; X. Gong; X. Chen; W. Zhang; J. Yang et al. 

Pairwise-Constrained Implicit Functions for 3D Human Heart Modeling

H. Le; J. Xu; N. Talabot; J. Yang; P. Fua 

DiffAtlas: GenAI-Fying Atlas Segmentation via Image-Mask Diffusion

H. Zhang; Y. Liu; J. Yang; W. Guo; X. Wang et al. 

Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation

T. Wang; M. Liu; H. Liu; B. Ren; Y. You et al. 

SimTA++: Simple attention neural network for clinical asynchronous time series

Z. Li; J. Li; K. Kuang; B. Jing; B. Du et al. 

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

A. Fan; C. Dumery; N. Talabot; P. Fua 

Leveraging Gradient Information for Out-of-Domain Performance Estimations

E. Khramtsova; M. Baktashmotlagh; G. Zuccon; X. Wang; M. Salzmann 

PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization

N. Talabot; O. Clerc; A. C. Demirtas; A. Goujon; M. H. Lê et al. 

Counting Stacked Objects

C. Dumery; N. Etté; A. Fan; R. Li; J. Xu et al. 

High Resolution UDF Meshing via Iterative Networks

F. Stella; N. Talabot; H. Le; P. Fua 

Exploring seismic mass-movement data with anomaly detection and dynamic time warping

F. Kamper; F. Walter; P. Paitz; M. Meyer; M. Volpi et al. 

Revisiting Machine Learning Approaches for Short‐ and Longwave Radiation Inference in Weather and Climate Models

G. Bertoli; S. Mohebi; F. Ozdemir; J. Jucker; S. Rüdisühli et al. 

Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates

R. Li; C. Cao; C. Dumery; H. Li; Y. You et al. 

Automated Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Z. Wei; A. Yang; J. Li; M. Bauerheim; R. P. Liem et al. 

Joint Compression of Multi-model Systems for Edge Devices

J. L. Prado Vieira; L. Makarem; M. Salzmann 

Tuning vision foundation models for rectal cancer segmentation from CT scans

H. Zhang; W. Guo; S. Wan; B. Zou; W. Wang et al. 

6Img-to-3D: Few-Image Large-Scale Outdoor Novel View Synthesis

T. Gieruc; M. Kästingschäfers; S. Bernhard; M. Salzmann 

A multimodal visual–language foundation model for computational ophthalmology

D. Shi; W. Zhang; J. Yang; S. Huang; X. Chen et al. 

Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields

C. Dumery; A. Fan; R. Li; N. Talabot; P. Fua 

Few-shot Personalized Scanpath Prediction

R. Xue; J. Xu; S. Mondal; H. Le; G. Zelinsky et al. 

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

G. Sun; R. Dabral; H. Zhu; P. Fua; C. Theobalt et al. 

A novel immersive catheter ablation simulator based on individualized 3D MR patients’ heart models improves ablation performance of future electrophysiologists

N. Bacha; A. Masi; P. Antiochos; C. Teres; M. Le Bloa et al. 

Unlocking Comics: the Ai4va Dataset for Visual Understanding

P. Gronquist; D. Bhattacharjee; B. Aydemir; B. Ozaydin; T. Zhang et al. 

Deep Learning to Improve the Discovery of Near-earth Asteroids in the Zwicky Transient Facility

B. Y. Irureta-Goyena; G. Helou; J-P. Kneib; F. Masci; T. Prince et al. 

Vision-based power line cables and pylons detection for low flying aircraft

J. Gwizdala; D. Oner; S. K. Roy; M. A. Shah; A. Eberhard et al. 

Tiny satellites, big challenges: A feasibility study of machine vision pose estimation for PocketQubes during conjunctions

N. Sajjad; A. Price; M. Mirshams; M. Salzmann 

Shadow Removal Refinement via Material-Consistent Shadow Edges

S. Hu; H. Le; S. Athar; S. Das; D. Samaras 

Learning to Count from Pseudo-Labeled Segmentation

J. Xu; H. Le; D. Samaras 

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT

M. Kozinski; D. Oner; J. Gwizdala; C. Beigelman-Aubry; P. Fua et al. 

Beyond Pixels: Semi-supervised Semantic Segmentation with a Multi-scale Patch-Based Multi-label Classifier

P. Howlader; S. Das; H. Le; D. Samaras 

Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures

S. L. Gu; J. K. Adhinarta; M. Bessmeltsev; J. Yang; Y. J. Zhang et al. 

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

P. Howlader; H. Le; D. Samaras 

A Latent Implicit 3D Shape Model for Multiple Levels of Detail

B. Guillard; M. Habermann; C. Theobalt; P. Fua 

SINDER: Repairing the Singular Defects of DINOv2

H. Wang; T. Zhang; M. Salzmann 

Assessing Sample Quality via the Latent Space of Generative Models

J. Xu; H. Le; D. Samaras 

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

J. Bednarik; N. Aigerman; V. G. Kim; S. Chaudhuri; S. Parashar et al. 

Neural Garment Modeling

Deep Active Latent Surfaces for Medical Geometries

P. M. Jensen; U. Wickramasinghe; A. B. Dahl; P. Fua; V. A. Dahl 

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

G. Sun; R. Dabral; P. Fua; C. Theobalt; M. Habermann 

Uncertainty in Modern Deep Learning

Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields

K. Xie; J. Yang; D. Wei; Z. Weng; P. Fua 

Dataset for “PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization”

N. Talabot; O. Clerc; A. C. Demirtas; A. Goujon; D. Oner et al. 

Exploring Causal Information Bottleneck for Adversarial Defense

J. Yan; H. Hua; W. Huang; X. Fang; W. Ge et al. 

Improving Human Pose & Shape Estimation with Explicit and Implicit Priors

Image-based Pose Estimation for Previously-Unseen Objects

Reconstruction of Manipulated Garment with Guided Deformation Prior

R. Li; C. Dumery; Z. Deng; P. Fua 

No Identity, no problem: Motion through detection for people tracking

M. Engilberge; F. W. Grosche; P. Fua 

Advancing EGFR mutation subtypes prediction in NSCLC by combining 3D pretrained ConvNeXt, radiomics, and clinical features

P. Hao; Y. Yu; C-T. Huang; F. Zhou; Y. Xu et al. 

Two-stage error detection to improve electron microscopy image mosaicking

J. Shi; H. Ge; S. Wang; D. Wei; J. Yang et al. 

Multi-task learning for medical foundation models

J. Yang 

Tuning Vision Foundation Models for Rectal Cancer Segmentation from CT Scans: Development and Validation of U-SAM

S. Wan; h. zhang; W. Guo; B. Zou; W. Wang et al. 

SGDA: Towards 3-D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention

R. Xu; Z. Liu; Y. Luo; H. Hu; L. Shen et al. 

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models

H. Qi; C. Zhao; M. Salzmann; A. Mathis 

CLOAF: CoLlisiOn-Aware Human Flow

A. Davydov; M. Engilberge; M. Salzmann; P. Fua 

Match Normalization: Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Z. Dang; L. Wang; Y. Guo; M. Salzmann 

Enabling Uncertainty Estimation in Iterative Neural Networks

N. Durasov; D. Oner; J. Donier; M. H. Lê; P. Fua 

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

N. Durasov; N. Dorndorf; M. H. Lê 

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Y. Wu; T. Zhang; W. Ke; c. Qiu; S. Süsstrunk et al. 

Multimodal fusion of liquid biopsy and CT enhances differential diagnosis of early-stage lung adenocarcinoma

Y. Zhang; B. Sun; Y. Yu; J. Lu; Y. Lou et al. 

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

A. Davydov; A. Sidnev; A. Sanakoyeu; Y. Chen; M. Salzmann et al. 

Development of End-to-End Artificial Intelligence Models for Surgical Planning in Transforaminal Lumbar Interbody Fusion

A. T. Bui; H. Le; T. T. Hoang; G. M. Trinh; H. C. Shao et al. 

Toward Automatic Typography Analysis: Serif Classification and Font Similarities

S. T. Wasim; R. S. Collaud; L. Défayes; N. Henchoz; M. Salzmann et al. 

DeepMesh: Differentiable Iso-Surface Extraction

B. Guillard; E. Remelli; A. Lukoaianov; P. Yvernay; S. Richter et al. 

DeepGeo: Deep Geometric Mapping for Automated and Effective Parameterization in Aerodynamic Shape Optimization

Z. Wei; A. Yang; J. Li; M. Bauerheim; R. P. Liem et al. 

Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance

W. Zhang; S. Y. Huang; J. Yang; R. Chen; Z. Ge et al. 

Generating Anatomically Accurate Heart Structures via Neural Implicit Fields

J. Yang; E. Sedykh; J. Adhinarta; M. H. Lê; P. Fua 

Dvmnet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

C. Zhao; T. Zhang; Z. Dang; M. Salzmann 

DiffAirfoil: An Efficient Novel Airfoil Sampler Based on Latent Space Diffusion Model for Aerodynamic Shape Optimization

Z. Wei; E. Dufour; C. Pelletier; P. Fua; M. Bauerheim 

Incorporating Projective Geometry into Deep Learning

Garment Recovery with Shape and Deformation Priors

R. Li; C. Dumery; B. Guillard; P. Fua 

MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision

J. Li; Z. Zhou; J. Yang; A. Pepe; C. Gsaxner et al. 

Detecting Road Obstacles by Erasing Them

K. M. Lis; S. Honari; P. Fua; M. Salzmann 

A Closed-Form Pairwise Solution to Local Non-Rigid Structure-from-Motion

S. Parashar; Y. Long; M. Salzmann; P. Fua 

Aggregating Spatial and Photometric Context for Photometric Stereo

RibSeg v2: A Large-Scale Benchmark for Rib Labeling and Anatomical Centerline Extraction

L. Jin; S. Gu; D. Wei; J. K. Adhinarta; K. Kuang et al. 

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

H. Qi; C. Zhao; M. Salzmann; A. Mathis 

Multi-site, Multi-domain Airway Tree Modeling

M. Zhang; Y. Wu; H. Zhang; Y. Qin; H. Zheng et al. 

Deep learning parametric response mapping from inspiratory chest CT scans: a new approach for small airway disease screening

B. Chen; Z. Liu; J. Lu; Z. Li; K. Kuang et al. 

Coarsest-level improvements in multigrid for lattice QCD on large-scale computers

J. Espinoza-Valverde; A. Frommer; G. Ramirez-Hidalgo; M. Rottmann 

One-shot Retinal Artery and Vein Segmentation via Cross-modality Pretraining

D. Shi; S. He; J. Yang; Y. Zheng; M. He 

Deep learning-based solid component measuring enabled interpretable prediction of tumor invasiveness for lung adenocarcinoma

J. Sun; L. Zhang; B. Hu; Z. Du; W. C. Cho et al. 

Learning for Multi-View Tracking

I. Vrkic 

Dense Multitask Learning to Reconfigure Comics

D. Bhattacharjee; S. Süsstrunk; M. Salzmann 

Prognostic impact of deep learning-based quantification in clinical stage 0-I lung adenocarcinoma

Y. Zhu; L-L. Chen; Y-W. Luo; L. Zhang; H-Y. Ma et al. 

Latent Representation of Computational Fluid Dynamics Meshes and Application to Airfoil Aerodynamics

Z. Wei; B. Guillard; P. Fua; V. Chapin; M. Bauerheim 

The Impact of Chatgpt and Llms on Medical Imaging Stakeholders: Perspectives and Use Cases

J. Yang; H. B. Li; D. Wei 

Spatiotemporal Self-supervised Learning for Point Clouds in the Wild

Y. Wu; T. Zhang; W. Ke; S. Süsstrunk; M. Salzmann 

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

E. Tretschk; N. Kairanda; B. R. Mallikarjun; R. Dabral; A. Kortylewski et al. 

RMAML: Riemannian meta-learning with orthogonality constraints

H. Tabealhojeh; P. Adibi; H. Karshenas; S. K. Roy; M. Harandi 

Visual question answering from another perspective: CLEVR mental rotation tests *

C. Beckham; M. Weiss; F. Golemo; S. Honari; D. Nowrouzezahrai et al. 

Unsupervised Electrofacies Clustering Based on Parameterization of Petrophysical Properties: A Dynamic Programming Approach

K. Sinnathamby; C. -Y. Hou; V-M. Gkortsas; L. Venkataramanan; H. B. Datir et al. 

Perspective Aware Road Obstacle Detection

K. Lis; S. Honari; P. Fua; M. Salzmann 

Ascending neurons convey behavioral state to integrative sensory and action selection brain regions

C-L. Chen; F. Aymanns; R. Minegishi; V. D. V. Matsuda; N. Talabot et al. 

Geodesic Convolutional Neural Network Characterization of Macro-Porous Latent Thermal Energy Storage

N. Mallya; P. B. Baqué; P. Yvernay; A. Pozzetti; P. Fua et al. 

Informing Neural Networks with Simplified Physics for Better Flow Prediction

F. Sergeev 

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping

Z. Yang; S. Li; W. Wu; B. Dai 

GECCO: Geometrically-Conditioned Point Diffusion Models

M. J. Tyszkiewicz; P. Fua; E. Trulls 

How to Boost Face Recognition with StyleGAN?

A. Sevastopolsky; Y. Malkov; N. Durasov; L. Verdoliva; M. Niessner 

MULTI-TASK CURRICULUM LEARNING FOR PARTIALLY LABELED DATA

W-D. Jang; S. Lukyanenko; D. Wei; J. Yang; B. Leahy et al. 

TempSAL – Uncovering Temporal Information for Deep Saliency Prediction

B. Aydemir; L. Hoffstetter; T. Zhang; M. Salzmann; S. Susstrunk 

DrapeNet: Garment Generation and Self-Supervised Draping

L. De Luigi; R. Li; B. Guillard; M. Salzmann; P. Fua 

Automated Human Motion Analysis and Synthesis

Multi-Source Fusion for Voxel-Based 7-DoF Grasping Pose Estimation

J. Qiu; F. Wang; Z. Dang 

Topologically Better Delineation of Curvilinear Structures

LightDepth: Single-View Depth Self-Supervision from Illumination Decline

J. Puigvert; V. Batlle; J. Montiel; R. Cantin; P. Fua et al. 

Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation

H. Wang; Z. Li; W. Zhang 

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

R. Li; B. Guillard; P. Fua 

Rigidity-Aware Detection for 6D Object Pose Estimation

Y. Hai; R. Song; J. Li; M. Salzmann; Y. Hu 

Tracking Adaptation to Improve SuperPoint for 3D Reconstruction in Endoscopy

L. Barbed; J. Montiel; P. Fua; A. Murillo 

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

Q. Wu; J. Yang; K. Sun; C. Zhang; Y. Zhang et al. 

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Z. Li; J. Yang; Y. Xu; L. Zhang; W. Dong et al. 

Robust Outlier Rejection for 3D Registration with Variational Bayes

H. Jiang; Z. Dang; Z. Wei; J. Xie; J. Yang et al. 

Geometrically-Conditioned Point Diffusion Models

M. J. Tyszkiewicz; P. Fua; E. Trulls Fortuny 

Vision Transformer Adapters for Generalizable Multitask Learning

D. Bhattacharjee; S. Süsstrunk; M. Salzmann 

Multi-view Tracking Using Weakly Supervised Human Motion Prediction

M. Engilberge; W. Liu; P. Fua 

Latent Representation of CFD Meshes and Application to Airfoil Aerodynamics

Z. Wei; B. Guillard; P. Fua; V. Chapin; M. Bauerheim 

Multi-view Tracking UsingWeakly Supervised Human Motion Prediction

M. Engilberge; W. Liu; P. Fua 

Two-level Data Augmentation for Calibrated Multi-view Detection

M. Engilberge; H. Shi; Z. Wang; P. Fua 

Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

T. Riedlinger; M. Rottmann; M. Schubert; H. Gottschalk 

Training Provably Robust Models by Polyhedral Envelope Regularization

C. Liu; M. Salzmann; S. Susstrunk 

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration

Z. Dang; M. Salzmann 

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Z. Wei; P. Fua; M. Bauerheim 

Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification

M. Rottmann; M. Reese 

Dense Image-based Predictions for Comics Analysis

Efficient Lung Nodule Detection via 3D Deep Learning with Shifted Convolutions

X. Kuang; K. Yuan; B. Du; J. Yang 

Improving Object Detection under Domain Shifts

Deep Learning for 3D Surface Modelling and Reconstruction

LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline

V. Batlle; J. Montiel; P. Fua; J. Tardos 

Fast Adversarial Training With Adaptive Step Size

Z. Huang; Y. Fan; C. Liu; W. Zhang; Y. Zhang et al. 

Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions

S. Guo; Y. Hu; J. M. Alvarez; M. Salzmann 

Learning Transformations To Reduce the Geometric Shift in Object Detection

V. Vidit; M. Engilberge; M. Salzmann 

OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs

H. He; Z. Yang; S. Li; B. Dai; W. Wu 

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

F. Liu; Y. Hu; M. Salzmann 

Detecting Anomalies and Obstacles in Road Scenes

Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset

Z. Weng; J. Yang; D. Liu; W. Cai 

Center-Based Decoupled Point Cloud Registration for 6D Object Pose Estimation

H. Jiang; Z. Dang; S. Gu; J. Xie; M. Salzmann et al. 

Center-aware Adversarial Augmentation for Single Domain Generalization

T. Chen; M. Baktashmotlagh; Z. Wang; M. Salzmann 

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

V. Vidit; M. Engilberge; M. Salzmann 

PlaceNet: A multi-scale semantic-aware model for visual loop closure detection

H. Osman; N. Darwish; A. Bayoumi 

Overcoming the Domain Gap in Neural Action Representations

S. Guenel; F. Aymanns; S. Honari; P. Ramdya; P. Fua 

RayTran: 3D Pose Estimation and Shape Reconstruction of Multiple Objects from Videos with Ray-Traced Transformers

M. J. Tyszkiewicz; K-K. Maninis; S. Popov; V. Ferrari 

Self-supervised Segmentation via Background Inpainting

I. Katircioglu; H. Rhodin; V. Constantin; J. Spörri; M. Salzmann et al. 

Improving the efficiency of identifying malignant pulmonary nodules before surgery via a combination of artificial intelligence CT image recognition and serum autoantibodies

Y. Ding; J. Zhang; W. Zhuang; Z. Gao; K. Kuang et al. 

Modeling Object Dissimilarity for Deep Saliency Prediction

B. Aydemir; D. Bhattacharjee; T. Zhang; S. Kim; M. Salzmann et al. 

3D Pose Based Feedback For Physical Exercises

Z. Zhao; S. Kiciroglu; H. Vinzant; Y. Cheng; I. Katircioglu et al. 

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

H. Yuan; C. Zhao; S. Fan; J. Jiang; J. Yang 

An Analysis of Super-Net Heuristics in Weight-Sharing NAS

K. Yu; R. Ranftl; M. Salzmann 

Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Z. Dang; L. Wang; Y. Guo; M. Salzmann 

Robust Isometric Non-Rigid Structure-From-Motion

S. Parashar; D. Pizarro; A. Bartoli 

Adversarial Parametric Pose Prior

A. Davydov; A. Remizova; V. Constantin; S. Honari; M. Salzmann et al. 

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

P. U. Wickramasinghe; P. M. Jensen; M. A. Shah; J. Yang; P. Fua 

Long Term Motion Prediction Using Keyposes

S. Kiciroglu; W. Wang; M. Salzmann; P. Fua 

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

S. K. Roy; L. Citraro; S. Honari; P. Fua 

Attention-based domain adaptation for single-stage detectors

V. Vidit; M. Salzmann 

TOPO-Loss for continuity-preserving crack detection using deep learning

B. G. Pantoja-Rosero; D. Oner; M. Kozinski; R. Achanta; P. Fua et al. 

Neurite Exchange Imaging ((NEXI): A minimal model of diffusion in gray matter with inter-compartment water exchange

I. O. Jelescu; A. de Skowronski; F. Geffroy; M. Palombo; D. S. Novikov 

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

D. Oner; M. Kozinski; L. Citraro; P. Fua 

ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging

J. Yang; U. Wickramasinghe; B. Ni; P. Fua 

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

T. Zhang; C. Qiu; W. Ke; S. Süsstrunk; M. Salzmann 

Enforcing Connectivity of 3D Linear Structures Using Their 2D Projections

D. Oner; H. Osman; M. Kozinski; P. Fua 

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

B. Guillard; F. Stella; P. Fua 

A Stepwise Domain Adaptive Segmentation Network With Covariate Shift Alleviation for Remote Sensing Imagery

J. Li; S. Zi; R. Song; Y. Li; Y. Hu et al. 

What Makes for Automatic Reconstruction of Pulmonary Segments

K. Kuang; L. Zhang; J. Li; H. Li; J. Chen et al. 

Multi-planar geometry and latent image recovery from a single motion-blurred image

K. Purohit; S. Vasu; M. P. Rao; A. N. Rajagopalan 

LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection

R. Xu; Y. Luo; B. Du; K. Kuang; J. Yang 

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Object Priors for Volumetric Image Segmentation

Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift

M. Baktashmotlagh; T. Chen; M. Salzmann 

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

S. Honari; V. Constantin; H. Rhodin; M. Salzmann; P. Fua 

Understanding Deep Neural Networks using Adversarial Attacks

Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering

Persistent Homology with Improved Locality Information for more Effective Delineation

D. Oner; A. Garin; M. Kozinski; K. Hess Bellwald; P. Fua 

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Van Nguyen Nguyen; Y. Hu; Y. Xiao; M. Salzmann; V. Lepetit 

Counting People by Estimating People Flows

W. Liu; M. Salzmann; P. Fua 

Learning to Represent and Reconstruct 3D Deformable Objects

Improving the Training of Compact Neural Networks for Visual Recognition

HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation

S. Vasu; N. Talabot; A. Lukoianov; P. Baqué; J. Donier et al. 

Learning to Simulate Realistic LiDARs

B. Guillard; S. Vemprala; J. K. Gupta; O. Miksik; V. Vineet et al. 

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

D. Oner; M. Kozinski; L. Citraro; N. C. Dadap; A. G. Konings et al. 

Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction

W. Mao; M. Liu; M. Salzmann 

Using Animal Motion Capture to Learn Neural Representations

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

C. Zhao; Y. Hu; M. Salzmann 

DIG: Draping Implicit Garment over the Human Body

R. Li; B. Guillard; E. Remelli; P. Fua 

Learning to Align Sequential Actions in the Wild

W. Liu; B. Tekin; H. Coskun; V. Vineet; P. Fua 

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

E. Gündogdu; V. Constantin; S. Parashar; A. Seifoddini; M. Dang et al. 

Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis

J. Yang; R. Shi; U. Wickramasinghe; Q. Zhu; B. Ni et al. 

Leveraging Self-Supervision for Cross-Domain Crowd Counting

W. Liu; N. Durasov; P. Fua 

Contrastive Class-aware Adaptation for Domain Generalization

T. Chen; M. Baktashmotlagh; M. Salzmann 

Distilling Image Classifiers in Object Detectors

S. Guo; M. J. Alvarez; M. Salzmann 

Human Detection and Segmentation via Multi-view Consensus

I. Katircioglu; H. Rhodin; J. Spörri; M. Salzmann; P. Fua 

Defect segmentation for multi-illumination quality control systems

D. Honzátko; E. Türetken; S. Arjomand Bigdeli; L. A. Dunbar; P. Fua 

Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks

O. Altingövde; A. Mishchuk; G. Ganeeva; E. Oveisi; C. Hébert et al. 

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Z. Dang; K. M. Yi; Y. Hu; F. Wang; P. Fua et al. 

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

J. Bednarík; V. Kim; S. Chaudhuri; S. Parashar; M. Salzmann et al. 

LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

A. Gosztolai; S. Gunel; V. Lobato-Rios; M. Pietro Abrate; D. Morales et al. 

Wide-Depth-Range 6D Object Pose Estimation in Space

Y. Hu; S. Speierer; W. Jakob; P. Fua; M. Salzmann 

Deep Active Surface Models

P. U. Wickramasinghe; P. Fua; G. Knott 

Masksembles for Uncertainty Estimation

N. Durasov; T. Bagautdinov; P. B. Baqué; P. Fua 

Geometry-Aware Deep Recurrent Neural Networks for Hyperspectral Image Classification

S. Hao; W. Wang; M. Salzmann 

Drainage Canals in Southeast Asian Peatlands Increase Carbon Emissions

N. C. Dadap; A. M. Hoyt; A. R. Cobb; D. Oner; M. Kozinski et al. 

Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

K. Kanth; M. Salzmann 

Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching

J. Qiu; X. Wang; P. Fua; D. Tao 

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Z. Li; Y. Hu; M. Salzmann; X. Ji 

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

F. Saleh; S. Aliakbarian; H. Rezatofighi; M. Salzmann; S. Gould 

Robust Differentiable SVD

W. Wang; Z. Dang; Y. Hu; P. Fua; M. Salzmann 

Human-Centered Scene Understanding via Crowd Counting

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

B. Guillard; E. Remelli; P. Yvernay; P. Fua 

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers

F. Yu; M. Salzmann; P. Fua; H. Rhodin 

Contextually Plausible and Diverse 3D Human Motion Prediction

S. Aliakbarian; F. Saleh; L. Petersson; S. Gould; M. Salzmann 

Image Matching Across Wide Baselines: From Paper to Practice

Y. Jin; D. Mishkin; A. Mishchuk; J. Matas; P. Fua et al. 

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

R. Chan; K. Lis; S. Uhlemeyer; H. Blum; S. Honari et al. 

Progressive Correspondence Pruning by Consensus Learning

C. Zhao; Y. Ge; F. Zhu; R. Zhao; H. Li et al. 

Person Retrieval in Surveillance Videos Via Deep Attribute Mining and Reasoning

Y. Shi; Z. Wei; H. Ling; Z. Wang; J. Shen et al. 

Adaptive and Robust Partition Learning for Person Retrieval With Policy Gradient

Y. Shi; Z. Wei; H. Ling; Z. Wang; P. Zhu et al. 

Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

D. Honzatko; E. Turetken; P. Fua; L. A. Dunbar 

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

K. Yu; R. Ranftl; M. Salzmann 

Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval

M. Qi; J. Qin; Y. Yang; Y. Wang; J. Luo 

From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

W. Mao; M. Liu; M. Salzmann 

DepthInSpace: Exploitation and Fusion of Multiple Video Frames for Structured-Light Depth Estimation

M. M. Johari; C. Carta; F. Fleuret 

Pyramid Architecture Search for Real-Time Image Deblurring

X. Hu; W. Ren; K. Yu; K. Zhang; X. Cao et al. 

Motion Prediction Using Temporal Inception Module

T. Lebailly; S. Kiciroglu; M. Salzmann; P. Fua; W. Wang 

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

S. Guo; M. J. Alvarez; M. Salzmann 

History Repeats Itself: Human Motion Prediction Via Motion Attention

W. Mao; M. Liu; M. Salzmann 

A convolutional neural network segments yeast microscopy images with high accuracy

N. Dietler; M. Minder; V. Gligorovski; A. M. Economou; D. A. H. L. Joly et al. 

Learning How to Smile: Expression Video Generation With Conditional Adversarial Recurrent Nets

W. Wang; X. Alameda-Pineda; D. Xu; E. Ricci; N. Sebe 

Indirect Local Attacks for Context-aware Semantic Segmentation Networks

K. K. Nakka; M. Salzmann 

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

S. Li; S. Günel; M. Ostrek; P. P. Ramdya; P. Fua et al. 

Volumetric Transformer Networks

S. Kim; S. Süsstrunk; M. Salzmann 

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

S. Vasu; M. Kozinski; L. Citraro; P. Fua 

Estimating People Flows to Better Count Them in Crowded Scenes

W. Liu; M. Salzmann; P. Fua 

XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera

D. Mehta; O. Sotnychenko; F. Mueller; W. Xu; M. Elgharib et al. 

Single-Stage 6D Object Pose Estimation

Y. Hu; P. Fua; W. Wang; M. Salzmann 

DUNIT: Detection-based Unsupervised Image-to-Image Translation

D. Bhattacharjee; S. Kim; G. Vizier; M. Salzmann 

Shape Reconstruction by Learning Differentiable Surface Representations

J. Bednarík; S. Parashar; E. Gündogdu; M. Salzmann; P. Fua 

DISK: learning local features with policy gradient

M. J. Tyszkiewicz; P. Fua; E. Trulls 

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

S. Kiciroglu; H. Rhodin; S. N. Sinha; M. Salzmann; P. Fua 

MeshSDF: Differentiable Iso-Surface Extraction

E. Remelli; A. Lukoianov; S. Ritcher; B. Guillard; T. Bagautdinov et al. 

Joint Segmentation and Path Classification of Curvilinear Structures

A. Mosinska; M. Kozinski; P. Fua 

Real-time camera pose estimation for sports fields

L. Citraro; P. Márquez-Neila; S. Savarè; V. Jayaram; C. Dubout et al. 

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

M. Kozinski; A. Mosinska; M. Salzmann; P. Fua 

UCLID-Net: Single View Reconstruction in Object Space

B. Guillard; E. Remelli; P. Fua 

Better Patch Stitching for Parametric Surface Reconstruction

Z. Deng; J. Bednarik; M. Salzmann; P. Fua 

STC-GAN: Spatio-Temporally Coupled Generative Adversarial Networks for Predictive Scene Parsing

M. Qi; Y. Wang; A. Li; J. Luo 

Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images

R. Bermúdez Chacón; O. Altingövde; C. J. Becker; M. Salzmann; P. Fua 

Learning and leveraging shared domain semantics to counteract visual domain shifts

Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data

P. U. Wickramasinghe; E. Remelli; G. Knott; P. Fua 

Domain-Adaptive Multibranch Networks

R. Bermúdez Chacón; M. Salzmann; P. Fua 

A Stochastic Conditioning Scheme for Diverse Human Motion Prediction

S. Aliakbarian; F. S. Saleh; M. Salzmann; L. Petersson; S. Gould 

Evaluating the search phase of neural architecture search

K. Yu; C. Suito; M. Jaggi; C-C. Musat; M. Salzmann 

Local Non-Rigid Structure-from-Motion from Locally Diffeomorphic Mappings

S. Parashar; M. Salzmann; P. Fua 

Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images

L. Citraro; M. Kozinski; P. Fua 

Multi-Modal Recurrent Attention Networks for Facial Expression Recognition

J. Lee; S. Kim; S. Kim; K. Sohn 

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

W. Liu; K. M. Lis; M. Salzmann; P. Fua 

Learning to Find Unpaired Cross-Spectral Correspondences

S. Jeong; S. Kim; K. Park; K. Sohn 

Detecting the Unexpected via Image Resynthesis

K. M. Lis; K. K. Nakka; P. Fua; M. Salzmann 

Recurrent U-Net for Resource-Constrained Segmentation

W. Wang; K. Yu; J. Hugonot; P. Fua; M. Salzmann 

Probabilistic Atlases to Enforce Topological Constraints

P. U. Wickramasinghe; G. Knott; P. Fua 

DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila

S. Günel; H. Rhodin; D. Morales; J. H. Campagnolo; P. Ramdya et al. 

Are Existing Monocular Computer Vision-Based 3D Motion Capture Approaches Ready for Deployment? A Methodological Study on the Example of Alpine Skiing

M. Ostrek; H. Rhodin; P. Fua; E. Mueller; J. Spoerri 

A new method to determine multi-angular reflectance factor from lightweight multispectral cameras with sky sensor in a target-less workflow applicable to UAV

K. Schneider-Zapp; M. Cubero-Castan; D. Shi; C. Strecha 

Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking

A. Maksai; P. Fua 

Aerodynamic shape optimization via surrogate modelling with convolutional neural networks

F. Bardi 

Neural Scene Decomposition for Multi-Person Motion Capture

H. Rhodin; V. Constantin; I. Katircioglu; M. Salzmann; P. Fua 

Context-Aware Crowd Counting

W. Liu; M. Salzmann; P. Fua 

Segmentation-driven 6D Object Pose Estimation

Y. Hu; J. L. Hugonot; P. Fua; M. Salzmann 

Mo(2)Cap(2): Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera

W. Xu; A. Chatterjee; M. Zollhofer; H. Rhodin; P. Fua et al. 

Geometry in active learning for binary and multi-class image segmentation

K. Konyushkova; R. Sznitman; P. Fua 

A Performance Evaluation of Local Features for Image-Based 3D Reconstruction

B. Fan; Q. Kong; X. Wang; Z. Wang; S. Xiang et al. 

Memory Efficient Max Flow for Multi-Label Submodular MRFs

T. Ajanthan; R. Hartley; M. Salzmann 

Learning Approach to Delineation of Curvilinear Structures in 2D and 3D Images

VIENA(2): A Driving Anticipation Dataset

M. S. Aliakbarian; F. S. Saleh; M. Salzmann; B. Fernando; L. Petersson et al. 

Double Refinement Network for Efficient Monocular Depth Estimation

N. Durasov; M. Romanov; V. Bubnova; P. Bogomolov; A. Konushin 

Temporal Spiking Recurrent Neural Network for Action Recognition

W. Wang; S. Hao; Y. Wei; S. Xia; J. Feng et al. 

Learning Trajectory Dependencies for Human Motion Prediction

W. Mao; M. Liu; M. Salzmann; H. Li 

Training Algorithms for Multiple Object Tracking

The Sixth Visual Object Tracking VOT2018 Challenge Results

M. Kristan; A. Leonardis; J. Matas; M. Felsberg; R. Pflugfelder et al. 

Quadruplet Selection Methods For Deep Embedding Learning

K. Karaman; E. Gundogdu; A. Koc; A. A. Alatan 

Full-Gradient Representation for Neural Network Visualization

S. Srinivas; F. Fleuret 

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

E. Gundogdu; V. Constantin; A. Seifoddini; M. Dang; M. Salzmann et al. 

Overcoming Multi-model Forgetting

Y. Benyahia; K. Yu; K. B. Smires; M. Jaggi; A. C. Davison et al. 

Attribute-Guided Sketch Generation

H. Tang; X. Chen; W. Wang; D. Xu; J. J. Corso et al. 

Shape optimisation of technical devices via gradient descent using convolutional neural network proxies

P. B. Baqué; P. Fua; F. Fleuret 

Gravity as a Reference for Estimating a Person’s Height from Video

D. Bieler; S. Gunel; P. Fua; H. Rhodin 

Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials

T. Joy; A. Desmaison; T. Ajanthan; R. Bunel; M. Salzmann et al. 

Dual Generator Generative Adversarial Networks for Multi-domain Image-to-Image Translation

H. Tang; D. Xu; W. Wang; Y. Yan; N. Sebe 

Backpropagation-Friendly Eigendecomposition

W. Wang; Z. Dang; Y. Hu; P. Fua; M. Salzmann 

Joint Learning of Semantic Alignment and Object Landmark Detection

S. Jeon; D. Min; S. Kim; K. Sohn 

LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation

S. Kim; S. Kim; D. Min; K. Sohn 

Context-Aware Emotion Recognition Networks

J. Lee; S. Kim; S. Kim; J. Park; K. Sohn 

Semantic Attribute Matching Networks

S. Kim; D. Min; S. Jeong; S. Kim; S. Jeon et al. 

What Face and Body Shapes Can Tell Us About Height

S. Gunel; H. Rhodin; P. Fua 

Beyond Cartesian Representations for Local Descriptors

P. Ebel; A. Mishchuk; K. M. Yi; P. Fua; E. Trulls 

Deep Micro-Dictionary Learning and Coding Network

H. Tang; H. Wei; W. Xiao; W. Wang; D. Xu et al. 

Learning to Reduce Annotation Load

Real-Time Seamless Single Shot 6D Object Pose Prediction

B. Tekin; S. N. Sinha; P. Fua 

Modeling Facial Geometry using Compositional VAEs

T. Bagautdinov; C. Wu; J. Saragih; Y. Sheikh; P. Fua 

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

J. Bednarík; M. Salzmann; P. Fua 

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

I. Katiricioglu; B. Tekin; M. Salzmann; V. Lepetit; P. Fua 

Mean-Field methods for Structured Deep-Learning in Computer Vision

Every Smile is Unique: Landmark-Guided Diverse Smile Generation

W. Wang; X. Alameda-Pineda; D. Xu; P. Fua; E. Ricci et al. 

MonoPerfCap: Human Performance Capture From Monocular Video

W. Xu; A. Chatterjee; M. Zollhofer; H. Rhodin; D. Mehta et al. 

Residual Parameter Transfer for Deep Domain Adaptation

A. Rozantsev; M. Salzmann; P. Fua 

Robust 3D Object Tracking from Monocular Images Using Stable Parts

A. Crivellaro; M. Rad; Y. Verdie; K. Yi; P. Fua et al. 

Geometry-aware Deep Network for Single-Image Novel View Synthesis

M. Liu; X. He; M. Salzmann 

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

M. Harandi; M. Salzmann; R. Hartley 

Learning Robust Features and Latent Representations for Single View 3D Pose Estimation of Humans and Objects

Learning to Segment 3D Linear Structures Using Only 2D Annotations

M. Kozinski; A. J. Mosinska; M. Salzmann; P. Fua 

Geodesic Convolutional Shape Optimization

P. B. Baqué; E. Remelli; F. Fleuret; P. Fua 

LF-Net: Learning Local Features from Images

Y. Ono; E. Trulls Fortuny; P. Fua; K. M. Yi 

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

Z. Dang; K. M. Yi; Y. Hu; F. Wang; P. Fua et al. 

A versatile calibration procedure for portable coded aperture gamma cameras and RGB-D sensors

V. Paradiso; A. Crivellaro; K. Amgarou; N. de Lanaute; P. Fua et al. 

Learning to Find Good Correspondences

K. M. Yi; E. Trulls; Y. Ono; V. Lepetit; M. Salzmann et al. 

Beyond Sharing Weights for Deep Domain Adaptation

A. Rozantsev; M. Salzmann; P. Fua 

Ocular Structures Segmentation from Multi-sequences MRI Using 3D Unet with Fully Connected CRFs

Huu-Giao Nguyen; A. Pica; P. Maeder; A. Schalenbourg; M. Peroni et al. 

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

R. Bermúdez Chacón; P. Marquez Neila; M. Salzmann; P. Fua 

Method, system, and device for learned invariant feature transform for computer images

P. Fua; V. Lepetit; E. F. Trulls; K. M. Yi 

Statistically-Motivated Second-order Pooling

K. Yu; M. Salzmann 

Learning to Find Good Correspondences

K. M. Yi; E. Trulls Fortuny; Y. Ono; V. Lepetit; M. Salzmann et al. 

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

F. Saleh; M. Aliakbarian; M. Salzmann; L. Petersson; J. Alvarez et al. 

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

R. Bermudez-Chancon; P. Marquez-Neila; M. Salzmann; P. Fua 

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

H. Rhodin; J. Sporri; I. Katircioglu; V. Constantin; F. Meyer et al. 

3D Box Proposals from a Single Monocular Image of an Indoor Scene

W. Zhuo; M. Salzmann; X. He; M. Liu 

The effects of aging on neuropil structure in mouse somatosensory cortex-A 3D electron microscopy analysis of layer 1

C. Cali; M. Wawrzyniak; C. Becker; B. Maco; M. Cantoni et al. 

Learning Intelligent Dialogs for Bounding Box Annotation

K. Konyushkova; J. Uijlings; C. H. Lampert; V. Ferrari 

Scale-Adaptive Superpixels

R. Achanta; P. Marquez Neila; P. Fua; S. Süsstrunk 

Variational Methods for Human Modeling

Unsupervised Geometry-Aware Representation Learning for 3D Human Pose Estimation

H. Rhodin; M. Salzmann; P. Fua 

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

J. Bednarik; P. Fua; M. Salzmann 

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

A. J. Mosinska; P. Marquez Neila; M. Kozinski; P. Fua 

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery

T. Kurmann; P. Marquez Neila; X. Du; P. Fua; D. Stoyanov et al. 

Joint Dimensionality Reduction and Metric Learning: A Geometric Take

M. Harandi; M. Salzmann; R. Hartley 

Learning Active Learning from Data

K. Konyushkova; R. Sznitman; P. Fua 

Stereo-vision three-dimensional reconstruction of curvilinear structures imaged with a TEM

E. Oveisi; A. Letouzey; S. De Zanet; G. Lucas; M. Cantoni et al. 

Imposing Hard Constraints on Deep Networks: Promises and Limitations

P. Marquez Neila; M. Salzmann; P. Fua 

Flight Dynamics-based Recovery of a UAV Trajectory using Ground Cameras

A. Rozantsev; S. Sinha; D. Dey; P. Fua 

Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference

W. Zhuo; M. Salzmann; X. He; M. Liu 

Deep Subspace Clustering Networks

P. Ji; T. Zhang; H. Li; M. Salzmann; I. Reid 

Vision-based detection of aircrafts and UAVs

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

B. Tekin; P. Marquez Neila; M. Salzmann; P. Fua 

Three-dimensional electron imaging and reconstruction of dislocations from a single acquisition

E. Oveisi; A. Letouzey; P. Fua; C. Hébert 

Geometric Graph Matching Using Monte Carlo Tree Search

M. A. Pinheiro; J. Kybic; P. Fua 

Compression-aware Training of Deep Networks

J. Alvarez; M. Salzmann 

Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency

P. Glowacki; M. Pinheiro; A. Mosinska; E. Türetken; D. Lebrecht et al. 

Computer Vision Techniques Applied to the Reconstruction of the 3-D Structure of Dislocations

E. Oveisi; S. De Zanet; P. Fua; C. Hébert 

Computer assisted detection of axonal bouton structural plasticity in in vivo time-lapse images

R. Gala; D. Lebrecht; D. A. Sahlender; A. Jorstad; G. Knott et al. 

Multi-Modal Mean-Fields via Cardinality-Based Clamping

P. Baqué; F. Fleuret; P. Fua 

Efficient Model-free Anthropometry from Depth Data

T. Probst; A. Fossati; M. Salzmann; L. Van Gool 

Active Learning and Proofreading for Delineation of Curvilinear Structures

A. J. Mosinska; J. Tarnawski; P. Fua 

Boundary-aware Instance Segmentation

Z. Hayder; X. He; M. Salzmann 

Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences

E. Türetken; X. Wang; C. J. Becker; C. Haubold; P. Fua 

Learning Lightprobes for Mixed Reality Illumination

D. Mandl; K. M. Yi; P. Mohr; P. Roth; P. Fua et al. 

Method, System and Device for Direct Prediction of 3D Body Poses from Motion Compensated Sequence

P. Fua; V. Lepetit; A. Rozantsev; B. Tekin 

Detecting Flying Objects using a Single Moving Camera

A. Rozantsev; V. Lepetit; P. Fua 

Tilt-less 3-D electron imaging and reconstruction of complex curvilinear structures

E. Oveisi; A. Letouzey; D. Alexander; Q. Jeangros; R. Schäublin et al. 

Encouraging LSTMs to Anticipate Actions Very Early

M. S. Aliakbarian; F. S. Saleh; M. Salzmann; B. Fernando; L. Petersson et al. 

Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation

F. S. Saleh; M. S. Aliakbarian; M. Salzmann; L. Petersson; J. M. Alvarez 

Efficient Linear Programming for Dense CRFs

A. Thalaiyasingam; A. Desmaison; R. Bunel; M. Salzmann; P. H. S. Torr et al. 

Globally Optimal Cell Tracking using Integer Programming

E. Türetken; X. Wang; C. J. Becker; C. Haubold; P. Fua 

Systems and methods for computing and displaying navigation indicators based on historic and real-time vessel data

J. V. Pilet; J. O. M. Östlund 

Structured Prediction of 3D Human Pose with Deep Neural Networks

B. Tekin; I. Katircioglu; M. Salzmann; V. Lepetit; P. Fua 

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

B. Tekin; A. Rozantsev; V. Lepetit; P. Fua 

Analyzing Volleyball Match Data from the 2014 World Championships Using Machine Learning Techniques

J. VanHaaren; H. Ben Shitrit; J. Davis; P. Fua 

Vision-Based Unmanned Aerial Vehicle Detection and Tracking for Sense and Avoid Systems

K. R. Sapkota; S. A. Roelofsen; A. Rozantsev; V. Lepetit; D. Gillet et al. 

LIFT: Learned Invariant Feature Transform

K. M. Yi; E. Trulls Fortuny; V. Lepetit; P. Fua 

Principled Parallel Mean-Field Inference for Discrete Random Fields

P. B. Baqué; T. Bagautdinov; F. Fleuret; P. Fua 

Learning to Co-Generate Object Proposals with a Deep Structured Network

Z. Hayder; X. He; M. Salzmann 

Segmentation of Developing Human Embryo in Time-lapse Microscopy

A. Khan; S. Gould; M. Salzmann 

Automated Reconstruction of Evolving Curvilinear Tree Structures

Simultaneous segmentation and anatomical labeling of the cerebral vasculature

D. Robben; E. Tueretken; S. Sunaert; V. Thijs; G. Wilms et al. 

Robust 3D Object Pose Estimation and Tracking from Monocular Images in Industrial Environments

Learning to Match Aerial Images with Deep Attentive Architectures

H. Altwaijry; E. Trulls; J. Hays; P. Fua; S. Belongie 

Building Scene Models by Completing and Hallucinating Depth and Semantics

M. Liu; X. He; M. Salzmann 

Reconstructing Curvilinear Networks using Path Classifiers and Integer Programming

E. Türetken; F. Benmansour; B. Andres; P. R. Glowacki; H. Pfister et al. 

Scalable Unsupervised Domain Adaptation for Electron Microscopy

R. Bermúdez-Chacón; C. Becker; M. Salzmann; P. Fua 

Distribution-Matching Embedding for Visual Domain Adaptation

M. Baktashmotlagh; M. Harandi; M. Salzmann 

Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering

M. Najafi; S. Taghavi Namin; M. Salzmann; L. Petersson 

Measuring the accuracy of softball impact simulations

L. Smith; D. Nevins; N. T. Dat; P. Fua 

Exploiting Large Image Sets for Road Scene Parsing

J. M. Alvarez; M. Salzmann; N. Barnes 

Efficient Transductive Semantic Segmentation

J. M. Alvarez; M. Salzmann; N. Barnes 

Learning the Number of Neurons in Deep Networks

J. M. Alvarez; M. Salzmann 

Do We Need Binary Features for 3D Reconstruction?

B. Fan; Q. Kong; W. Sui; Z. Wang; X. Wang et al. 

Template-free 3D Reconstruction of Poorly-textured Nonrigid Surfaces

X. Wang; M. Salzmann; F. Wang; J. Zhao 

Memory Efficient Max Flow for Multi-label Submodular MRFs

A. Thalaiyasingam; R. Hartley; M. Salzmann 

Active Learning for Delineation of Curvilinear Structures

A. Mosinska-Domanska; R. Sznitman; P. Glowacki; P. Fua 

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

T. D. Ngo; J. Östlund; P. Fua 

Tracking Interacting Objects Using Intertwined Flows

X. Wang; E. Türetken; F. Fleuret; P. Fua 

Computer vision profiling of neurite outgrowth dynamics reveals spatio-temporal modularity of Rho GTPase signaling

O. Pertz; L. Fusco; R. Lefort; K. C. Smith; F. Benmansour et al. 

Three-dimensional electron imaging of dislocations from a single sample tilt

E. Oveisi; A. Letouzey; P. Fua; C. Hébert 

Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

F. Saleh; M. S. Ali Akbarian; M. Salzmann; L. Petersson; S. Gould et al. 

Robust Multi-body Feature Tracker: A Segmentation-free Approach

P. Ji; H. Li; M. Salzmann; Y. Zhong 

Learning to Assign Orientations to Feature Points

K. M. Yi; Y. Verdie; P. Fua; V. Lepetit