Stefano Soatto

Orcid: 0000-0003-2902-6362

Affiliations:
  • University of California, Los Angeles, USA


According to our database1, Stefano Soatto authored at least 408 papers between 1993 and 2024.

Collaborative distances:

Awards

ACM Fellow

ACM Fellow 2022, "For contributions to the foundations and applications of visual geometry and visual representations learning".

IEEE Fellow

IEEE Fellow 2013, "For contributions to dynamic visual processes".

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Elodi: Ensemble Logit Difference Inhibition for Positive-Congruent Training.
IEEE Trans. Pattern Anal. Mach. Intell., December, 2024

Conjuring Semantic Similarity.
CoRR, 2024

RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions.
CoRR, 2024

NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality.
CoRR, 2024

Compositional Structures in Neural Embedding and Interaction Decompositions.
CoRR, 2024

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory.
CoRR, 2024

Cycles of Thought: Measuring LLM Confidence through Stable Explanations.
CoRR, 2024

Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI.
CoRR, 2024

NeRF-Insert: 3D Local Editing with Multimodal Control Signals.
CoRR, 2024

Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model.
CoRR, 2024

Mixed-Query Transformer: A Unified Image Segmentation Architecture.
CoRR, 2024

WorDepth: Variational Language Prior for Monocular Depth Estimation.
CoRR, 2024

Heat Death of Generative Models in Closed-Loop Learning.
CoRR, 2024

Fast Sparse View Guided NeRF Update for Object Reconfigurations.
CoRR, 2024

A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D.
CoRR, 2024

Sub-token ViT Embedding via Stochastic Resonance Transformers.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Fewer Truncations Improve Language Modeling.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Meaning Representations from Trajectories in Autoregressive Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Tangent Transformers for Composition, Privacy and Removal.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Critical Learning Periods Emerge Even in Deep Linear Networks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation.
Proceedings of the Computer Vision - ECCV 2024, 2024

On the Viability of Monocular Depth Pre-training for Semantic Segmentation.
Proceedings of the Computer Vision - ECCV 2024, 2024

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models.
Proceedings of the Computer Vision - ECCV 2024, 2024

WorDepth: Variational Language Prior for Monocular Depth Estimation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Non-autoregressive Sequence-to-Sequence Vision-Language Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

On the Scalability of Diffusion-based Text-to-Image Generation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

THRONE: An Object-Based Hallucination Benchmark for the Free-Form Generations of Large Vision-Language Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

CPR: Retrieval Augmented Generation for Copyright Protection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Enhancing Vision-Language Pre-Training with Rich Supervisions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Multi-Modal Hallucination Control by Visual Information Grounding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Incorporating physics into data-driven computer vision.
Nat. Mac. Intell., June, 2023

AugUndo: Scaling Up Augmentations for Unsupervised Depth Completion.
CoRR, 2023

Training Data Protection with Compositional Diffusion Models.
CoRR, 2023

Towards Visual Foundational Models of Physical Scenes.
CoRR, 2023

Prompt Algebra for Task Composition.
CoRR, 2023

Taming AI Bots: Controllability of Neural States in Large Language Models.
CoRR, 2023

Musketeer (All for One, and One for All): A Generalist Vision-Language Model with Task Explanation Prompts.
CoRR, 2023

AI Model Disgorgement: Methods and Choices.
CoRR, 2023

Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots.
CoRR, 2023

Quantifying VIO Uncertainty.
CoRR, 2023

Feature Tracks are not Zero-Mean Gaussian.
CoRR, 2023

Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models.
CoRR, 2023

Linear Spaces of Meanings: the Compositional Language of VLMs.
CoRR, 2023

Harnessing Unrecognizable Faces for Improving Face Recognition.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Gacs-Korner Common Information Variational Autoencoder.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Leveraging sparse and shared feature activations for disentangled representation learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Your representations are in the network: composable and parallel adaptation for large scale models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Masked Vision and Language Modeling for Multi-modal Representation Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Tangent Model Composition for Ensembling and Continual Fine-tuning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

SAFE: Machine Unlearning With Shard Graphs.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Train/Test-Time Adaptation with Retrieval.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Depth Estimation from Camera Image and mmWave Radar Point Cloud.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Guided Recommendation for Model Fine-Tuning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Critical Learning Periods for Multisensory Integration in Deep Networks.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

A Meta-Learning Approach to Predicting Performance and Data Requirements.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Graph Spectral Embedding using the Geodesic Betweenness Centrality.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
Stochastic batch size for adaptive regularization in deep network optimization.
Pattern Recognit., 2022

Integral Continual Learning Along the Tangent Vector Field of Tasks.
CoRR, 2022

Stain-invariant self supervised learning for histopathology image analysis.
CoRR, 2022

On Binding Objects to Symbols: Learning Physical Concepts to Understand Real from Fake.
CoRR, 2022

Towards Ground Truth for Single Image Deraining.
CoRR, 2022

Graph Spectral Embedding using the Geodesic Betweeness Centrality.
CoRR, 2022

Towards Differential Relational Privacy and its use in Question Answering.
CoRR, 2022

Does Monocular Depth Estimation Provide Better Pre-training than Classification for Semantic Segmentation?
CoRR, 2022

Stacked Residuals of Dynamic Layers for Time Series Anomaly Detection.
CoRR, 2022

Contrastive Neighborhood Alignment.
CoRR, 2022

On Leave-One-Out Conditional Mutual Information For Generalization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Semi-supervised Vision Transformers at Scale.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

DIVA: Dataset Derivative of a Learning Task.
Proceedings of the Tenth International Conference on Learning Representations, 2022

X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks.
Proceedings of the Computer Vision - ECCV 2022, 2022

Not Just Streaks: Towards Ground Truth for Single Image Deraining.
Proceedings of the Computer Vision - ECCV 2022, 2022

Class-Incremental Learning with Strong Pre-trained Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Omni-DETR: Omni-Supervised Object Detection with Transformers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Task Adaptive Parameter Sharing for Multi-Task Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Mixed Differential Privacy in Computer Vision.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

MeMOT: Multi-Object Tracking with Memory.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Stereoscopic Universal Perturbations across Different Architectures and Datasets.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
An Adaptive Framework for Learning Unsupervised Depth Completion.
IEEE Robotics Autom. Lett., 2021

Learning Topology From Synthetic Data for Unsupervised Depth Completion.
IEEE Robotics Autom. Lett., 2021

SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots.
IEEE Robotics Autom. Lett., 2021

Block-cyclic stochastic coordinate descent for deep neural networks.
Neural Networks, 2021

Redundant Information Neural Estimation.
Entropy, 2021

Representation Consolidation for Training Expert Students.
CoRR, 2021

Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers.
CoRR, 2021

Harnessing Unrecognizable Faces for Face Recognition.
CoRR, 2021

Visual Composite Set Detection Using Part-and-Sum Transformers.
CoRR, 2021

A linearized framework and a new benchmark for model selection for fine-tuning.
CoRR, 2021

Revisiting Contrastive Learning for Few-Shot Classification.
CoRR, 2021

Long Short-Term Transformer for Online Action Detection.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Uniform Sampling over Episode Difficulty.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learned Uncertainty Calibration for Visual Inertial Localization.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

Structured Prediction as Translation between Augmented Natural Languages.
Proceedings of the 9th International Conference on Learning Representations, 2021

Estimating informativeness of samples with Smooth Unique Information.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learning Hierarchical Graph Neural Networks for Image Clustering.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Unsupervised Depth Completion with Calibrated Backprojection Layers.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Positive-Congruent Training: Towards Regression-Free Model Updates.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Mixed-Privacy Forgetting in Deep Networks.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Compatibility-Aware Heterogeneous Visual Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Learning Semantic-Aware Dynamics for Video Prediction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

LQF: Linear Quadratic Fine-Tuning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Small Lesion Segmentation in Brain MRIs with Subpixel Embedding.
Proceedings of the Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 2021

Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates.
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Dynamically Grown Generative Adversarial Networks.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Adaptive Regularization of Some Inverse Problems in Image Analysis.
IEEE Trans. Image Process., 2020

Unsupervised Depth Completion From Visual Inertial Odometry.
IEEE Robotics Autom. Lett., 2020

A Geometric Interpretation of Stochastic Gradient Descent Using Diffusion Metrics.
Entropy, 2020

Spectral Embedding of Graph Networks.
CoRR, 2020

Time-Supervised Primary Object Segmentation.
CoRR, 2020

Continual Universal Object Detection.
CoRR, 2020

Incremental Learning for Metric-Based Meta-Learners.
CoRR, 2020

Predicting Training Time Without Training.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Targeted Adversarial Perturbations for Monocular Depth Prediction.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Rethinking the Hyperparameters for Fine-tuning.
Proceedings of the 8th International Conference on Learning Representations, 2020

Meta-Q-Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

A Baseline for Few-Shot Image Classification.
Proceedings of the 8th International Conference on Learning Representations, 2020

Incremental Few-Shot Meta-learning via Indirect Discriminant Alignment.
Proceedings of the Computer Vision - ECCV 2020, 2020

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations.
Proceedings of the Computer Vision - ECCV 2020, 2020

Disentangled Image Generation for Unsupervised Domain Adaptation.
Proceedings of the Computer Vision - ECCV 2020 Workshops, 2020

Phase Consistent Ecological Domain Adaptation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Learning to Manipulate Individual Objects in an Image.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Towards Backward-Compatible Representation Learning.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

FDA: Fourier Domain Adaptation for Semantic Segmentation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning.
Proceedings of the 4th Conference on Robot Learning, 2020

DeepVoxels++: Enhancing the Fidelity of Novel View Synthesis from 3D Voxel Embeddings.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to Rescue.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020

Zero Shot Learning with the Isoperimetric Loss.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Geo-Supervised Visual Depth Prediction.
IEEE Robotics Autom. Lett., 2019

LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning.
CoRR, 2019

Toward Understanding Catastrophic Forgetting in Continual Learning.
CoRR, 2019

Where is the Information in a Deep Neural Network?
CoRR, 2019

VOICED: Depth Completion from Inertial Odometry and Vision.
CoRR, 2019

The Information Complexity of Learning Tasks, their Structure and their Distance.
CoRR, 2019

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction.
CoRR, 2019

Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss.
Proceedings of the Scale Space and Variational Methods in Computer Vision, 2019

Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Critical Learning Periods in Deep Networks.
Proceedings of the 7th International Conference on Learning Representations, 2019

Input and Weight Space Smoothing for Semi-Supervised Learning.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Unsupervised Domain Adaptation via Regularized Conditional Alignment.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Task2Vec: Task Embedding for Meta-Learning.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Meta-Learning With Differentiable Convex Optimization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

GeoNet: Deep Geodesic Networks for Point Cloud Analysis.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Dense Depth Posterior (DDP) From Single Image and Sparse Range.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Unsupervised Moving Object Detection via Contextual Information Separation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

MARL-PPS: Multi-agent Reinforcement Learning with Periodic Parameter Sharing.
Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019

Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Information Dropout: Learning Optimal Representations Through Noisy Computation.
IEEE Trans. Pattern Anal. Mach. Intell., 2018

Emergence of Invariance and Disentanglement in Deep Representations.
J. Mach. Learn. Res., 2018

The Dynamics of Differential Learning I: Information-Dynamics and Task Reachability.
CoRR, 2018

A Separation Principle for Control in the Age of Deep Learning.
Annu. Rev. Control. Robotics Auton. Syst., 2018

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective.
Proceedings of the 6th International Conference on Learning Representations, 2018

Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks.
Proceedings of the 6th International Conference on Learning Representations, 2018

Conditional Prior Networks for Optical Flow.
Proceedings of the Computer Vision - ECCV 2018, 2018

Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification.
Proceedings of the Computer Vision - ECCV 2018, 2018

Visual-Inertial Object Detection and Mapping.
Proceedings of the Computer Vision - ECCV 2018, 2018

SaaS: Speed as a Supervisor for Semi-supervised Learning.
Proceedings of the Computer Vision - ECCV 2018, 2018

OATM: Occlusion Aware Template Matching by Consensus Set Maximization.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Empirical Study of the Topology and Geometry of Deep Networks.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017
Mathematics of Deep Learning.
CoRR, 2017

DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images.
CoRR, 2017

Critical Learning Periods in Deep Neural Networks.
CoRR, 2017

Analysis of universal adversarial perturbations.
CoRR, 2017

Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors.
CoRR, 2017

Multi-Label Segmentation via Residual-Driven Adaptive Regularization.
CoRR, 2017

Classification regions of deep neural networks.
CoRR, 2017

Deep Relaxation: partial differential equations for optimizing deep neural networks.
CoRR, 2017

Parle: parallelizing stochastic gradient descent.
CoRR, 2017

On the Emergence of Invariance and Disentangling in Deep Representations.
CoRR, 2017

Adaptive Discretizations for Non-smooth Variational Vision.
Proceedings of the Scale Space and Variational Methods in Computer Vision, 2017

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys.
Proceedings of the 5th International Conference on Learning Representations, 2017

S2F: Slow-to-Fast Interpolator Flow.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Visual-Inertial-Semantic Scene Representation for 3D Object Detection.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Zero Shot Learning via Multi-scale Manifold Regularization.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Partial differential equations for training deep neural networks.
Proceedings of the 51st Asilomar Conference on Signals, Systems, and Computers, 2017

2016
Robust Surface Reconstruction.
SIAM J. Imaging Sci., 2016

Detecting Occlusions as an Inverse Problem.
J. Math. Imaging Vis., 2016

Visual-Inertial Scene Representations.
CoRR, 2016

Modeling Visual Representations: Defining Properties and Deep Approximations
Proceedings of the 4th International Conference on Learning Representations, 2016

A Theory of Local Matching: SIFT and Beyond.
CoRR, 2016

Information Dropout: learning optimal representations through noise.
CoRR, 2016

A mid-level representation of visual structures for video compression.
Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision, 2016

Observability, Identifiability and Sensitivity of Vision-Aided Inertial Navigation.
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

Intent-aware long-term prediction of pedestrian motion.
Proceedings of the 2016 IEEE International Conference on Robotics and Automation, 2016

ShapeFit and ShapeKick for Robust, Scalable Structure from Motion.
Proceedings of the Computer Vision - ECCV 2016, 2016

A Simple Hierarchical Pooling Data Structure for Loop Closure.
Proceedings of the Computer Vision - ECCV 2016, 2016

An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015
Adaptive Regularization With the Structure Tensor.
IEEE Trans. Image Process., 2015

Shape Matching Using Multiscale Integral Invariants.
IEEE Trans. Pattern Anal. Mach. Intell., 2015

Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Visual Scene Representations: Sufficiency, Minimality, Invariance and Deep Approximations.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Boosting Convolutional Features for Robust Object Proposals.
CoRR, 2015

How Well Can a CNN Marginalize Simple Nuisances It is Designed for?
CoRR, 2015

Trivializing The Energy Landscape Of Deep Networks.
CoRR, 2015

Robust Poisson Surface Reconstruction.
Proceedings of the Scale Space and Variational Methods in Computer Vision, 2015

Robust inference for visual-inertial sensor fusion.
Proceedings of the IEEE International Conference on Robotics and Automation, 2015

A Power-Performance Approach to Comparing Sensor Families, with application to comparing neuromorphic to traditional vision sensors.
Proceedings of the IEEE International Conference on Robotics and Automation, 2015

Self-Occlusions and Disocclusions in Causal Video Object Segmentation.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Exploiting Temporal Redundancy of Visual Structures for Video Compression.
Proceedings of the 2015 Data Compression Conference, 2015

Perspective distortion modeling, learning and compensation.
Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015

Causal video object segmentation from persistence of occlusions.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Efficient minimal-surface regularization of perspective depth maps in variational stereo.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Texture representations for image and video synthesis.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Domain-size pooling in local descriptors: DSP-SIFT.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Multi-view feature engineering and learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
Visual Correspondence, the Lambert-Ambient Shape Space and the Systematic Design of Feature Descriptors.
Proceedings of the Registration and Recognition in Images and Videos, 2014

Information-Seeking Control Under Visibility-Based Uncertainty.
J. Math. Imaging Vis., 2014

A Linear Systems Approach to Imaging Through Turbulence.
J. Math. Imaging Vis., 2014

Volumetric reconstruction applied to perceptual studies of size and weight.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Asymmetric Sparse Kernel Approximations for Large-Scale Visual Search.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Second-Order Shape Optimization for Geometric Inverse Problems in Vision.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects.
Proceedings of the 2nd International Conference on 3D Vision, 2014

2013
Actionable Information in Vision.
Proceedings of the Machine Learning for Computer Vision, 2013

Observability, Identifiability, Sensitivity and Model Reduction For Vision-Assisted Inertial Navigation.
CoRR, 2013

On the Design and Analysis of Multiple View Descriptors.
CoRR, 2013

Control recognition bounds for visual learning and exploration.
Proceedings of the 2013 Information Theory and Applications Workshop, 2013

Semantic Video Segmentation from Occlusion Relations within a Convex Optimization Framework.
Proceedings of the Energy Minimization Methods in Computer Vision and Pattern Recognition, 2013

Texture Compression.
Proceedings of the 2013 Data Compression Conference, 2013

Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

CLAM: Coupled Localization and Mapping with Efficient Outlier Handling.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video.
IEEE Trans. Pattern Anal. Mach. Intell., 2012

Sparse Occlusion Detection with Optical Flow.
Int. J. Comput. Vis., 2012

Fast planar object detection and tracking via edgel templates.
Proceedings of the IEEE Workshop on Applications of Computer Vision, 2012

Controlled Recognition Bounds for Visual Learning and Exploration.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Information Forests.
Proceedings of the 2012 Information Theory and Applications Workshop, 2012

Video upscaling via spatio-temporal self-similarity.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

Visual-inertial ego-motion estimation for humanoid platforms.
Proceedings of the 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012), Osaka, Japan, November 29, 2012

SuperFloxels: A Mid-level Representation for Video Sequences.
Proceedings of the Computer Vision - ECCV 2012. Workshops and Demonstrations, 2012

Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection.
Proceedings of the Computer Vision - ECCV 2012, 2012

Scene-Aware Video Modeling and Compression.
Proceedings of the 2012 Data Compression Conference, Snowbird, UT, USA, April 10-12, 2012, 2012

Discovering discriminative action parts from mid-level video representations.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

Actionable saliency detection: Independent motion detection without independent motion estimation.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

Information gathering control via exploratory path planning.
Proceedings of the 46th Annual Conference on Information Sciences and Systems, 2012

2011
A New Geometric Metric in the Space of Curves, and Applications to Tracking Deforming Objects by Prediction and Filtering.
SIAM J. Imaging Sci., 2011

Direct Sparse Deblurring.
J. Math. Imaging Vis., 2011

Video-based descriptors for object recognition.
Image Vis. Comput., 2011

Visual-inertial navigation, mapping and localization: A scalable real-time causal approach.
Int. J. Robotics Res., 2011

Steps Towards a Theory of Visual Information: Active Perception, Signal-to-Symbol Conversion and the Interplay Between Sensing and Control.
CoRR, 2011

Biopsy needle detection in transrectal ultrasound.
Comput. Medical Imaging Graph., 2011

Entropy-Scale Profiles for Texture Segmentation.
Proceedings of the Scale Space and Variational Methods in Computer Vision, 2011

Multiple Instance Filtering.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Edgel templates for fast planar object detection and pose estimation.
Proceedings of the 10th IEEE International Symposium on Mixed and Augmented Reality, 2011

Multimodal Registration via Spatial-Context Mutual Information.
Proceedings of the Information Processing in Medical Imaging, 2011

Detachable Object Detection with Efficient Model Selection.
Proceedings of the Energy Minimazation Methods in Computer Vision and Pattern Recognition, 2011

Controlled Recognition Bounds for Scaling and Occlusion Channels.
Proceedings of the 2011 Data Compression Conference (DCC 2011), 2011

Learning and matching multiscale template descriptors for real-time detection, localization and tracking.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

2010
Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition.
Proceedings of the Computer Vision: Detection, Recognition and Reconstruction, 2010

Heartbeat of a nest: Using imagers as biological sensors.
ACM Trans. Sens. Networks, 2010

Face verification across age progression using discriminative methods.
IEEE Trans. Inf. Forensics Secur., 2010

Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats.
Proc. IEEE, 2010

Editorial for the Special Issue on Photometric Analysis for Computer Vision.
Int. J. Comput. Vis., 2010

Occlusion Detection and Motion Estimation with Convex Optimization.
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

Feature tracking and object recognition on a hand-held.
Proceedings of the 9th IEEE International Symposium on Mixed and Augmented Reality, 2010

Earth Mover Distance on superpixels.
Proceedings of the International Conference on Image Processing, 2010

Tracklet Descriptors for Action Modeling and Video Analysis.
Proceedings of the Computer Vision, 2010

Really Quick Shift: Image Segmentation on a GPU.
Proceedings of the Trends and Topics in Computer Vision, 2010

Texture Regimes for Entropy-Based Multiscale Image Analysis.
Proceedings of the Computer Vision, 2010

Curious snakes: A minimum latency solution to the cluttered background problem in active contours.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Spike train driven dynamical models for human actions.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Warping background subtraction.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Analyzing Diving: A Dataset for Judging Action Quality.
Proceedings of the Computer Vision - ACCV 2010 Workshops, 2010

2009
Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits.
Int. J. Comput. Vis., 2009

Unsupervised multiphase segmentation: A recursive approach.
Comput. Vis. Image Underst., 2009

Enforcing local context into shape statistics.
Adv. Comput. Math., 2009

A Non-local Approach to Shape from Ambient Shading.
Proceedings of the Scale Space and Variational Methods in Computer Vision, 2009

SmartLDWS: A robust and scalable lane departure warning system for the smartphones.
Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems, 2009

Nonlocal Similarity Image Filtering.
Proceedings of the Image Analysis and Processing, 2009

Motion segmentation with occlusions on the superpixel graph.
Proceedings of the 12th IEEE International Conference on Computer Vision Workshops, 2009

Actionable information in vision.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

Class segmentation and object localization with superpixel neighborhoods.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009

Nonrigid registration combining global and local statistics.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

On the set of images modulo viewpoint and contrast changes.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

Categorization in natural time-varying image sequences.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009

Tracking deforming objects by filtering and prediction in the space of curves.
Proceedings of the 48th IEEE Conference on Decision and Control, 2009

2008
Shape from Defocus via Diffusion.
IEEE Trans. Pattern Anal. Mach. Intell., 2008

Editorial.
Int. J. Comput. Vis., 2008

3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination.
Int. J. Comput. Vis., 2008

Dynamic Shape and Appearance Modeling via Moving and Deforming Layers.
Int. J. Comput. Vis., 2008

Wide-Sense Estimation on the Special Orthogonal Group.
Commun. Inf. Syst., 2008

Quick Shift and Kernel Methods for Mode Seeking.
Proceedings of the Computer Vision, 2008

Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images.
Proceedings of the Computer Vision, 2008

Background Subtraction on Distributions.
Proceedings of the Computer Vision, 2008

Localizing Objects with Smart Dictionaries.
Proceedings of the Computer Vision, 2008

Filtering Internet image search results towards keyword based category recognition.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

Relaxed matching kernels for robust image comparison.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

Joint data alignment up to (lossy) transformations.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

Edge descriptors for robust wide-baseline correspondence.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

The scale of a texture and its application to segmentation.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

2007
A Variational Approach to Problems in Calibration of Multiple Cameras.
IEEE Trans. Pattern Anal. Mach. Intell., 2007

Classification and Recognition of Dynamical Models: The Role of Phase, Independent Components, Kernels and Optimal Transport.
IEEE Trans. Pattern Anal. Mach. Intell., 2007

Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images.
J. Math. Imaging Vis., 2007

Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks.
Proceedings of the 2007 First ACM/IEEE International Conference on Distributed Smart Cameras, 2007

Correspondence Transfer for the Registration of Multimodal Images.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

A Study of Face Recognition as People Age.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

Proximity Distribution Kernels for Geometric Context in Category Recognition.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

Moving Forward in Structure From Motion.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

Autocalibration and Uncalibrated Reconstruction of Shape from Defocus.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

Joint Priors for Variational Shape and Appearance Modeling.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

On the Blind Classification of Time Series.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007

A Fast RANSAC-Based Registration Algorithm for Accurate Localization in Unknown Environments using LIDAR Measurements.
Proceedings of the IEEE Conference on Automation Science and Engineering, 2007

3-D Shape Estimation and Image Restoration - Exploiting Defocus and Motion Blur.
Springer, ISBN: 978-1-84628-176-1, 2007

2006
Integral Invariants for Shape Matching.
IEEE Trans. Pattern Anal. Mach. Intell., 2006

Dynamic Shape and Appearance Models.
IEEE Trans. Pattern Anal. Mach. Intell., 2006

Harmonic Embeddings for Linear Shape Analysis.
J. Math. Imaging Vis., 2006

The Golem Group/University of California at Los Angeles autonomous ground vehicle in the DARPA grand challenge.
J. Field Robotics, 2006

Region matching with missing parts.
Image Vis. Comput., 2006

Two-View Multibody Structure from Motion.
Int. J. Comput. Vis., 2006

Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation.
Int. J. Comput. Vis., 2006

A Complexity-Distortion Approach to Joint Pattern Alignment.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Detecting Humans via Their Pose.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006

High Performance Feature Detection on a Reconfigurable Co-Processor.
Proceedings of the 14th IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM 2006), 2006

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions.
Proceedings of the Computer Vision, 2006

Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2006

Local Features, All Grown Up.
Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

Control Theory and Fast Marching Techniques for Brain Connectivity Mapping.
Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation.
Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

Classifying Human Dynamics Without Contact Forces.
Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

Integral Invariants and Shape Matching.
Proceedings of the Statistics and Analysis of Shapes, 2006

Modeling Dynamic Scenes: An Overview of Dynamic Textures.
Proceedings of the Handbook of Mathematical Models in Computer Vision, 2006

2005
A Geometric Approach to Shape from Defocus.
IEEE Trans. Pattern Anal. Mach. Intell., 2005

Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance.
Int. J. Comput. Vis., 2005

Fast Marching Method for Generic Shape from Shading.
Proceedings of the Variational, 2005

Features for Recognition: Viewpoint Invariance for Non-Planar Scenes.
Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV 2005), 2005

KALMANSAC: Robust Filtering by Consensus.
Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV 2005), 2005

Layered Active Appearance Models.
Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV 2005), 2005

One-Shot Integral Invariant Shape Priors for Variational Segmentation.
Proceedings of the Energy Minimization Methods in Computer Vision and Pattern Recognition, 2005

2004
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation.
Int. J. Comput. Vis., 2004

Multiple-view geometry for image-based modeling.
Proceedings of the International Conference on Computer Graphics and Interactive Techniques, 2004

Simultaneous localization and mapping using multiple view feature descriptors.
Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28, 2004

Modeling and Synthesis of Facial Motion Driven by Speech.
Proceedings of the Computer Vision, 2004

Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis.
Proceedings of the Computer Vision, 2004

Integral Invariant Signatures.
Proceedings of the Computer Vision, 2004

Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance.
Proceedings of the Computer Vision, 2004

Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion.
Proceedings of the Computer Vision, 2004

Spatially Homogeneous Dynamic Textures.
Proceedings of the Computer Vision, 2004

Kernel Density Estimation and Intrinsic Alignment for Knowledge-Driven Segmentation: Teaching Level Sets to Walk.
Proceedings of the Pattern Recognition, 26th DAGM Symposium, August 30, 2004

Shedding Light on Stereoscopic Segmentation.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), with CD-ROM, 27 June, 2004

A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), with CD-ROM, 27 June, 2004

Tracking deformable moving objects under severe occlusions.
Proceedings of the 43rd IEEE Conference on Decision and Control, 2004

2003
A semi-direct approach to structure from motion.
Vis. Comput., 2003

Estimation of 3D Surface Shape and Smooth Radiance from 2D Images: A Level Set Approach.
J. Sci. Comput., 2003

Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images.
Int. J. Comput. Vis., 2003

Stereoscopic Segmentation.
Int. J. Comput. Vis., 2003

Observing Shape from Defocused Images.
Int. J. Comput. Vis., 2003

Dynamic Textures.
Int. J. Comput. Vis., 2003

Tales of Shape and Radiance in Multi-view Stereo.
Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV 2003), 2003

On Exploiting Occlusions in Multiple-view Geometry.
Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV 2003), 2003

Shape Representation via Harmonic Embedding.
Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV 2003), 2003

Dynamic Texture Segmentation.
Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV 2003), 2003

Variational Space-Time Motion Segmentation.
Proceedings of the 9th IEEE International Conference on Computer Vision (ICCV 2003), 2003

Observability of Linear Hybrid Systems.
Proceedings of the Hybrid Systems: Computation and Control, 2003

Structure From Motion for Scenes Without Features.
Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), 2003

Multi-view Stereo Beyond Lambert.
Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), 2003

Seeing Beyond Occlusions (and other marvels of a finite lens aperture).
Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), 2003

3D Shape from Anisotropic Diffusion.
Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), 2003

An algebraic geometric approach to the identification of a class of linear hybrid systems.
Proceedings of the 42nd IEEE Conference on Decision and Control, 2003

2002
Structure from Motion Causally Integrated Over Time.
IEEE Trans. Pattern Anal. Mach. Intell., 2002

Editable dynamic textures.
Proceedings of the 29th International Conference on Computer Graphics and Interactive Techniques, 2002

DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images.
Proceedings of the Computer Vision, 2002

Learning Shape from Defocus.
Proceedings of the Computer Vision, 2002

Observability and identifiability of jump linear systems.
Proceedings of the 41st IEEE Conference on Decision and Control, 2002

A Model (In)Validation Approach to Gait Recognition.
Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission (3DPVT 2002), 2002

Inpainting from Multiple Views.
Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission (3DPVT 2002), 2002

Variational Multiframe Stereo in the Presence of Specular Reflections.
Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission (3DPVT 2002), 2002

2001
Dynamic Textures.
Proceedings of the Eighth International Conference On Computer Vision (ICCV-01), Vancouver, British Columbia, Canada, July 7-14, 2001, 2001

Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination.
Proceedings of the Eighth International Conference On Computer Vision (ICCV-01), Vancouver, British Columbia, Canada, July 7-14, 2001, 2001

Real-time Virtual Object Insertion.
Proceedings of the Eighth International Conference On Computer Vision (ICCV-01), Vancouver, British Columbia, Canada, July 7-14, 2001, 2001

Dynamic Texture Recognition.
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), 2001

Recognition of Human Gaits.
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), 2001

2000
Euclidean Reconstruction and Reprojection Up to Subgroups.
Int. J. Comput. Vis., 2000

Optimal Structure from Motion: Local Ambiguities and Global Estimates.
Int. J. Comput. Vis., 2000

Shape and Radiance Estimation from the Information-Divergence of Blurred Images.
Proceedings of the Computer Vision - ECCV 2000, 6th European Conference on Computer Vision, Dublin, Ireland, June 26, 2000

3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation.
Proceedings of the Computer Vision - ECCV 2000, 6th European Conference on Computer Vision, Dublin, Ireland, June 26, 2000

A Geometric Approach to Blind Deconvolution with Application to Shape from Defocu.
Proceedings of the 2000 Conference on Computer Vision and Pattern Recognition (CVPR 2000), 2000

Stereoscopic Shading: Integrating Mult1Frame Shape Cues in a Variational Framework.
Proceedings of the 2000 Conference on Computer Vision and Pattern Recognition (CVPR 2000), 2000

Real-Time 3-D Motion and Structure of Point-Features: A Front-End for Vision-Based Control and Interaction.
Proceedings of the 2000 Conference on Computer Vision and Pattern Recognition (CVPR 2000), 2000

Monte Carlo filtering on Lie groups.
Proceedings of the 39th IEEE Conference on Decision and Control, 2000

1999
On Observing Shape from Defocused Images.
Proceedings of the 1oth International Conference on Image Analysis and Processing (ICIAP 1999), 1999

1998
Correction to: "Reducing 'Structure From Motion': A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment".
IEEE Trans. Pattern Anal. Mach. Intell., 1998

Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment.
IEEE Trans. Pattern Anal. Mach. Intell., 1998

Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 1: Modeling.
IEEE Trans. Pattern Anal. Mach. Intell., 1998

Optimal Structure from Motion: Local Ambiguities and Global Estimates.
Proceedings of the 1998 Conference on Computer Vision and Pattern Recognition (CVPR '98), 1998

1997
Motion from Fixation.
Real Time Imaging, 1997

3-D Structure from Visual Motion: Modeling, Representation and Observability.
Autom., 1997

A lagrangian formulation of nonholonomic path following.
Proceedings of the confluence of vision and control, 1997

1996
Motion estimation via dynamic vision.
IEEE Trans. Autom. Control., 1996

Reducing "structure from motion".
Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96), 1996

1995
Visual motion estimation from point features: unified view.
Proceedings of the Proceedings 1995 International Conference on Image Processing, 1995

Dynamic Rigid Motion Estimation from Weak Perspective.
Proceedings of the Procedings of the Fifth International Conference on Computer Vision (ICCV 95), 1995

1994
Recursive Estimation of Camera Motion from Uncalibrated Image Sequences.
Proceedings of the Proceedings 1994 International Conference on Image Processing, 1994

Dynamic Visual Motion Estimation from Subspace Constraints.
Proceedings of the Proceedings 1994 International Conference on Image Processing, 1994

Motion Estimation on the Essential Manifold.
Proceedings of the Computer Vision, 1994

1993
Recursive motion and structure estimation with complete error characterization.
Proceedings of the Conference on Computer Vision and Pattern Recognition, 1993


  Loading...