Mathieu Salzmann

Orcid: 0000-0002-8347-8637

According to our database1, Mathieu Salzmann authored at least 264 papers between 2005 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Detecting Road Obstacles by Erasing Them.
IEEE Trans. Pattern Anal. Mach. Intell., April, 2024

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields.
CoRR, 2024

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes.
CoRR, 2024

2023
Training Provably Robust Models by Polyhedral Envelope Regularization.
IEEE Trans. Neural Networks Learn. Syst., June, 2023

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation.
IEEE Trans. Pattern Anal. Mach. Intell., May, 2023

Perspective Aware Road Obstacle Detection.
IEEE Robotics Autom. Lett., April, 2023

Fast Adversarial Training With Adaptive Step Size.
IEEE Trans. Image Process., 2023

DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration.
CoRR, 2023

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence.
CoRR, 2023

TIC-TAC: A Framework To Learn And Evaluate Your Covariance.
CoRR, 2023

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation.
CoRR, 2023

3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation.
CoRR, 2023

Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation.
CoRR, 2023

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields.
CoRR, 2023

De-coupling and De-positioning Dense Self-supervised Learning.
CoRR, 2023

NOPE: Novel Object Pose Estimation from a Single Image.
CoRR, 2023

Module-Wise Network Quantization for 6D Object Pose Estimation.
CoRR, 2023

Center-aware Adversarial Augmentation for Single Domain Generalization.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Towards Stable and Efficient Adversarial Training against l<sub>1</sub> Bounded Adversarial Attacks.
Proceedings of the International Conference on Machine Learning, 2023

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Center-Based Decoupled Point Cloud Registration for 6D Object Pose Estimation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Vision Transformer Adapters for Generalizable Multitask Learning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Learning Transformations to Reduce the Geometric Shift in Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

CLIP the Gap: A Single Domain Generalization Approach for Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

DrapeNet: Garment Generation and Self-Supervised Draping.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Robust Outlier Rejection for 3D Registration with Variational Bayes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Rigidity-Aware Detection for 6D Object Pose Estimation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Dense Multitask Learning to Reconfigure Comics.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Modeling Object Dissimilarity for Deep Saliency Prediction.
Trans. Mach. Learn. Res., 2022

An Analysis of Super-Net Heuristics in Weight-Sharing NAS.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Robust Differentiable SVD.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Counting People by Estimating People Flows.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Self-Supervised Human Detection and Segmentation via Background Inpainting.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Attention-based domain adaptation for single-stage detectors.
Mach. Vis. Appl., 2022

AttEntropy: Segmenting Unknown Objects in Complex Scenes using the Spatial Attention Entropy of Semantic Segmentation Transformers.
CoRR, 2022

DSI2I: Dense Style for Unpaired Image-to-Image Translation.
CoRR, 2022

Finer-Grained Correlations: Location Priors for Unseen Object Pose Estimation.
CoRR, 2022

DrapeNet: Generating Garments and Draping them with Self-Supervision.
CoRR, 2022

Knowledge Distillation for 6D Pose Estimation by Keypoint Distribution Alignment.
CoRR, 2022

MulT: An End-to-End Multitask Learning Transformer.
CoRR, 2022

Robust Binary Models by Pruning Randomly-initialized Networks.
CoRR, 2022

Estimating Image Depth in the Comics Domain.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Robust Binary Models by Pruning Randomly-initialized Networks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Contact-aware Human Motion Forecasting.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Contrastive Class-aware Adaptation for Domain Generalization.
Proceedings of the 26th International Conference on Pattern Recognition, 2022

Fusing Local Similarities for Retrieval-Based 3D Orientation Estimation of Unseen Objects.
Proceedings of the Computer Vision - ECCV 2022, 2022

Universal, Transferable Adversarial Perturbations for Visual Object Trackers.
Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022

Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation.
Proceedings of the Computer Vision - ECCV 2022, 2022

Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World.
Proceedings of the Computer Vision - ECCV 2022, 2022

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Adversarial Parametric Pose Prior.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

MuIT: An End-to-End Multitask Learning Transformer.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

3D Pose Based Feedback for Physical Exercises.
Proceedings of the Computer Vision - ACCV 2022, 2022

Long Term Motion Prediction Using Keyposes.
Proceedings of the International Conference on 3D Vision, 2022

2021
Geometry-Aware Deep Recurrent Neural Networks for Hyperspectral Image Classification.
IEEE Trans. Geosci. Remote. Sens., 2021

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems.
IEEE Trans. Pattern Anal. Mach. Intell., 2021

Multi-level Motion Attention for Human Motion Prediction.
Int. J. Comput. Vis., 2021

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training.
CoRR, 2021

Dyadic Human Motion Prediction.
CoRR, 2021

What Stops Learning-based 3D Registration from Working in the Real World?
CoRR, 2021

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases.
CoRR, 2021

DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows.
CoRR, 2021

Learning Transferable Adversarial Perturbations.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Distilling Image Classifiers in Object Detectors.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Progressive Correspondence Pruning by Consensus Learning.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Generating Smooth Pose Sequences for Diverse Human Motion Prediction.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Human Detection and Segmentation via Multi-view Consensus.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Contextually Plausible and Diverse 3D Human Motion Prediction.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

PCLs: Geometry-Aware Neural Reconstruction of 3D Pose With Perspective Crop Layers.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Wide-Depth-Range 6D Object Pose Estimation in Space.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images.
IEEE Trans. Medical Imaging, 2020

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures.
Medical Image Anal., 2020

Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers.
CoRR, 2020

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction.
CoRR, 2020

Self-supervised Human Detection and Segmentation via Multi-view Consensus.
CoRR, 2020

Unsupervised Learning on Monocular Videos for 3D Human Pose Estimation.
CoRR, 2020

A Closed-Form Solution to Local Non-Rigid Structure-from-Motion.
CoRR, 2020

3D Registration for Self-Occluded Objects in Context.
CoRR, 2020

Self-supervised Segmentation via Background Inpainting.
CoRR, 2020

Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations.
CoRR, 2020

GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss.
CoRR, 2020

Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration.
CoRR, 2020

ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking.
CoRR, 2020

How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS.
CoRR, 2020

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Evaluating The Search Phase of Neural Architecture Search.
Proceedings of the 8th International Conference on Learning Representations, 2020

Domain Adaptive Multibranch Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020

Indirect Local Attacks for Context-Aware Semantic Segmentation Networks.
Proceedings of the Computer Vision - ECCV 2020, 2020

History Repeats Itself: Human Motion Prediction via Motion Attention.
Proceedings of the Computer Vision - ECCV 2020, 2020

Estimating People Flows to Better Count Them in Crowded Scenes.
Proceedings of the Computer Vision - ECCV 2020, 2020

Volumetric Transformer Networks.
Proceedings of the Computer Vision - ECCV 2020, 2020

Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Single-Stage 6D Object Pose Estimation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

DUNIT: Detection-Based Unsupervised Image-to-Image Translation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Shape Reconstruction by Learning Differentiable Surface Representations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

A Stochastic Conditioning Scheme for Diverse Human Motion Prediction.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Towards Robust Fine-Grained Recognition by Maximal Separation of Discriminative Features.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

Motion Prediction Using Temporal Inception Module.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

Better Patch Stitching for Parametric Surface Reconstruction.
Proceedings of the 8th International Conference on 3D Vision, 2020

2019
Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials.
SIAM J. Imaging Sci., 2019

Beyond Sharing Weights for Deep Domain Adaptation.
IEEE Trans. Pattern Anal. Mach. Intell., 2019

Memory Efficient Max Flow for Multi-Label Submodular MRFs.
IEEE Trans. Pattern Anal. Mach. Intell., 2019

ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture.
CoRR, 2019

Sampling Good Latent Variables via CPP-VAEs: VAEs with Condition Posterior as Prior.
CoRR, 2019

On Certifying Robust Models by Polyhedral Envelope.
CoRR, 2019

Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting.
CoRR, 2019

Learning Variations in Human Motion via Mix-and-Match Perturbation.
CoRR, 2019

Self-supervised Training of Proposal-based Segmentation via Background Prediction.
CoRR, 2019

Interpretable BoW Networks for Adversarial Example Detection.
CoRR, 2019

Backpropagation-Friendly Eigendecomposition.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation.
Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

Overcoming Multi-model Forgetting.
Proceedings of the 36th International Conference on Machine Learning, 2019

Learning Factorized Representations for Open-Set Domain Adaptation.
Proceedings of the 7th International Conference on Learning Representations, 2019

Field Typing for Improved Recognition on Heterogeneous Handwritten Forms.
Proceedings of the 2019 International Conference on Document Analysis and Recognition, 2019

Learning Trajectory Dependencies for Human Motion Prediction.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Detecting the Unexpected via Image Resynthesis.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Recurrent U-Net for Resource-Constrained Segmentation.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Neural Scene Decomposition for Multi-Person Motion Capture.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Context-Aware Crowd Counting.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Segmentation-Driven 6D Object Pose Estimation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018
Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation.
IEEE Trans. Pattern Anal. Mach. Intell., 2018

Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods.
IEEE Trans. Pattern Anal. Mach. Intell., 2018

Learning Latent Representations of 3D Human Pose with Deep Neural Networks.
Int. J. Comput. Vis., 2018

Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation.
CoRR, 2018

Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation.
CoRR, 2018

ExpandNets: Exploiting Linear Redundancy to Train Small Networks.
CoRR, 2018

VIENA2: A Driving Anticipation Dataset.
CoRR, 2018

Learning Shape-from-Shading for Deformable Surfaces.
CoRR, 2018

Geometric and Physical Constraints for Head Plane Crowd Density Estimation in Videos.
CoRR, 2018

Learning to Segment 3D Linear Structures Using Only 2D Annotations.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2018, 2018

A domain-adaptive two-stream U-Net for electron microscopy image segmentation.
Proceedings of the 15th IEEE International Symposium on Biomedical Imaging, 2018

Statistically-Motivated Second-Order Pooling.
Proceedings of the Computer Vision - ECCV 2018, 2018

Effective Use of Synthetic Data for Urban Scene Semantic Segmentation.
Proceedings of the Computer Vision - ECCV 2018, 2018

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation.
Proceedings of the Computer Vision - ECCV 2018, 2018

Eigendecomposition-Free Training of Deep Networks with Zero Eigenvalue-Based Losses.
Proceedings of the Computer Vision - ECCV 2018, 2018

Learning to Find Good Correspondences.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Residual Parameter Transfer for Deep Domain Adaptation.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Learning Monocular 3D Human Pose Estimation From Multi-View Images.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Geometry-Aware Deep Network for Single-Image Novel View Synthesis.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Deep Attentional Structured Representation Learning for Visual Recognition.
Proceedings of the British Machine Vision Conference 2018, 2018

VIENA ^2 : A Driving Anticipation Dataset.
Proceedings of the Computer Vision - ACCV 2018, 2018

3D Box Proposals From a Single Monocular Image of an Indoor Scene.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

Learning to Reconstruct Texture-Less Deformable Surfaces from a Single View.
Proceedings of the 2018 International Conference on 3D Vision, 2018

2017
Learning Domain Invariant Embeddings by Matching Distributions.
Proceedings of the Domain Adaptation in Computer Vision Applications., 2017

Soft Correspondences in Multimodal Scene Parsing.
CoRR, 2017

Second-order Convolutional Neural Networks.
CoRR, 2017

Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation.
CoRR, 2017

Imposing Hard Constraints on Deep Networks: Promises and Limitations.
CoRR, 2017

Low-Rank Kernel Subspace Clustering.
CoRR, 2017

Deep Subspace Clustering Networks.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Compression-aware Training of Deep Networks.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Joint Dimensionality Reduction and Metric Learning: A Geometric Take.
Proceedings of the 34th International Conference on Machine Learning, 2017

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Bringing Background into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Encouraging LSTMs to Anticipate Actions Very Early.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Boundary-Aware Instance Segmentation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Efficient Linear Programming for Dense CRFs.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Efficient Model-Free Anthropometry from Depth Data.
Proceedings of the 2017 International Conference on 3D Vision, 2017

2016
Exploiting Large Image Sets for Road Scene Parsing.
IEEE Trans. Intell. Transp. Syst., 2016

Distribution-Matching Embedding for Visual Domain Adaptation.
J. Mach. Learn. Res., 2016

Semantic labeling for prosthetic vision.
Comput. Vis. Image Underst., 2016

Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation.
CoRR, 2016

Semantic-Aware Depth Super-Resolution in Outdoor Scenes.
CoRR, 2016

Shape-aware Instance Segmentation.
CoRR, 2016

Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation.
CoRR, 2016

Efficient transductive semantic segmentation.
Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision, 2016

Learning the Number of Neurons in Deep Networks.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Scalable Unsupervised Domain Adaptation for Electron Microscopy.
Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, 2016

Segmentation of developing human embryo in time-lapse microscopy.
Proceedings of the 13th IEEE International Symposium on Biomedical Imaging, 2016

Template-Free 3D Reconstruction of Poorly-Textured Nonrigid Surfaces.
Proceedings of the Computer Vision - ECCV 2016, 2016

Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation.
Proceedings of the Computer Vision - ECCV 2016, 2016

Building Scene Models by Completing and Hallucinating Depth and Semantics.
Proceedings of the Computer Vision - ECCV 2016, 2016

Deep Convolutional Neural Networks for Human Embryonic Cell Counting.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Robust Multi-Body Feature Tracker: A Segmentation-Free Approach.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Learning to Co-Generate Object Proposals with a Deep Structured Network.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

When VLAD Met Hilbert.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Structured Prediction of 3D Human Pose with Deep Neural Networks.
Proceedings of the British Machine Vision Conference 2016, 2016

2015
Mirror Surface Reconstruction from a Single Image.
IEEE Trans. Pattern Anal. Mach. Intell., 2015

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels.
IEEE Trans. Pattern Anal. Mach. Intell., 2015

Structured Depth Prediction in Challenging Monocular Video Sequences.
CoRR, 2015

A Multi-modal Graphical Model for Scene Analysis.
Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, 2015

A Linear Chain Markov Model for Detection and Localization of Cells in Early Stage Embryo Development.
Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, 2015

Detecting Abnormal Cell Division Patterns in Early Stage Human Embryo Development.
Proceedings of the Machine Learning in Medical Imaging - 6th International Workshop, 2015

Efficient scene parsing by sampling unary potentials in a fully-connected CRF.
Proceedings of the 2015 IEEE Intelligent Vehicles Symposium, 2015

Automated monitoring of human embryonic cells up to the 5-cell stage in time-lapse microscopy images.
Proceedings of the 12th IEEE International Symposium on Biomedical Imaging, 2015

Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Cutting Edge: Soft Correspondences in Multimodal Scene Parsing.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Structural Kernel Learning for Large Scale Multiclass Object Co-detection.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Indoor scene structure analysis for single image depth estimation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Riemannian coding and dictionary learning: Kernels to the rescue.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Iteratively reweighted graph cut for multi-label MRFs with non-convex priors.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
Discriminative Non-Linear Stationary Subspace Analysis for Video Classification.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

Kernel Coding: General Formulation and Special Cases.
CoRR, 2014

Efficient dense subspace clustering.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Data-driven road detection.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Large-scale semantic co-labeling of image sets.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Null space clustering with applications to motion segmentation and face clustering.
Proceedings of the 2014 IEEE International Conference on Image Processing, 2014

Nonrigid Surface Registration and Completion from RGBD Images.
Proceedings of the Computer Vision - ECCV 2014, 2014

Non-associative Higher-Order Markov Networks for Point Cloud Classification.
Proceedings of the Computer Vision - ECCV 2014, 2014

Robust Motion Segmentation with Unknown Correspondences.
Proceedings of the Computer Vision - ECCV 2014, 2014

Object Co-detection via Efficient Inference in a Fully-Connected CRF.
Proceedings of the Computer Vision - ECCV 2014, 2014

Expanding the Family of Grassmannian Kernels: An Embedding Perspective.
Proceedings of the Computer Vision - ECCV 2014, 2014

From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices.
Proceedings of the Computer Vision - ECCV 2014, 2014

Discrete-Continuous Depth Estimation from a Single Image.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Optimizing over Radial Kernels on Compact Manifolds.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Bregman Divergences for Infinite Dimensional Covariance Matrices.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Domain Adaptation on the Statistical Manifold.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

2013
Learning appearance models for road detection.
Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), 2013

Non-Linear Stationary Subspace Analysis with Application to Video Classification.
Proceedings of the 30th International Conference on Machine Learning, 2013

Real-time keystone correction for hand-held projectors with an RGBD camera.
Proceedings of the IEEE International Conference on Image Processing, 2013

A Framework for Shape Analysis via Hilbert Space Embedding.
Proceedings of the IEEE International Conference on Computer Vision, 2013

Unsupervised Domain Adaptation by Domain Invariant Projection.
Proceedings of the IEEE International Conference on Computer Vision, 2013

Combining Multiple Manifold-Valued Descriptors for Improved Object Recognition.
Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications, 2013

Continuous Inference in Graphical Models with Polynomial Energies.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Monocular 3D Reconstruction of Locally Textured Surfaces.
IEEE Trans. Pattern Anal. Mach. Intell., 2012

A Family of MCMC Methods on Implicitly Defined Manifolds.
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3D Reconstruction.
Proceedings of the Computer Vision - ECCV 2012, 2012

A constrained latent variable model.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

2011
Linear Local Models for Monocular Reconstruction of Deformable Surfaces.
IEEE Trans. Pattern Anal. Mach. Intell., 2011

Physically-based motion models for 3D tracking: A convex formulation.
Proceedings of the IEEE International Conference on Computer Vision, 2011

Learning cross-modality similarity for multinomial data.
Proceedings of the IEEE International Conference on Computer Vision, 2011

2010
Deformable Surface 3D Reconstruction from Monocular Images
Synthesis Lectures on Computer Vision, Morgan & Claypool Publishers, ISBN: 978-3-031-01810-7, 2010

Factorized Orthogonal Latent Spaces.
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Factorized Latent Spaces with Structured Sparsity.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Learning to Recognize Objects from Unseen Modalities.
Proceedings of the Computer Vision, 2010

Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

2009
Learning and recovering 3D surface deformations.
PhD thesis, 2009

Template-free monocular reconstruction of deformable surfaces.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

Reconstructing sharply folding surfaces: A convex formulation.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

Capturing 3D stretchable surfaces from single images in closed form.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

Observable subspaces for 3D human motion recovery.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

2008
Closed-Form Solution to Non-rigid 3D Surface Registration.
Proceedings of the Computer Vision, 2008

Local deformation models for monocular 3D shape recovery.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

3D pose refinement from reflections.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

2007
Surface Deformation Models for Nonrigid 3D Shape Recovery.
IEEE Trans. Pattern Anal. Mach. Intell., 2007

Implicit Meshes for Effective Silhouette Handling.
Int. J. Comput. Vis., 2007

Convex Optimization for Deformable Surface 3-D Tracking.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

Deformable Surface Tracking Ambiguities.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

2005
Implicit Surfaces Make for Better Silhouettes.
Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), 2005

Physically Valid Shape Parameterization for Monocular 3-D Deformable Surface Tracking.
Proceedings of the British Machine Vision Conference 2005, Oxford, UK, September 2005, 2005


  Loading...