PhD Defenses

Towards Robustness in Computer-based Image Understanding

Advancing Vision-based End-to-End Autonomous Driving

Towards Source-Free Domain Adaption of Neural Networks in an Open World

Deep Learning Based Data Fusion Approaches for the Assessment of Cognitive States on EEG Signals

Synth-to-real semi-supervised learning for visual tasks

Going beyond Classification Problems for the Continual Learning of Deep Neural Networks

Deep learning based architectures for cross-domain image processing

Document Image Enhancement & Recognition in Low Resource Scenarios: Application to Ciphers and Handwritten Text

Leveraging Scene Text Information for Image Interpretation

A Bitter-Sweet Symphony on Vision and Language: Bias and World Knowledge

Reading Music Systems: From Deep Optical Music Recognition to Contextual Methods

Deep Metric Learning for re-identification, tracking and hierarchical novelty detection

Self-supervised learning for image-to-image translation in the small data regime

Continual learning for hierarchical classification, few-shot recognition, and multi-modal learning

Towards Efficient and Robust Convolutional Neural Networks for Single Image Super-Resolution

Monocular Depth Estimation for Autonomous Driving

Towards Smart Fashion: Visual Recognition of Products and Attributes

Towards Practical Neural Image Compression

Reducing Label Effort with Deep Active Learning

Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation

Training strategies for efficient deep image retrieval

Efficient and Scalable Handwritten Word Spotting on Historical Documents using Bag of Visual Words

Visual Saliency for Object Recognition and Object Recognition for Visual Saliency

Leveraging Synthetic Data to Create Autonomous Driving Perception Systems

Geometric Computer Vision Techniques for Scene Reconstruction

Lifelike Humans: Detailed Reconstruction of Expressive Human Faces

Neural Information Extraction from Semi-structured Documents

Robust Handwritten Text Recognition in Scarce Labeling Scenarios: Disentanglement, Adaptation and Generation

Lifelong Learning of Neural Networks: Detecting Novelty and Adapting to New Domains without Forgetting

Texture analysis for robust reading systems

Mapping between Images and Conceptual Spaces: Sketch-based Image Retrieval

Exploiting the Interplay between Visual and Textual Data for Scene Interpretation

Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images

Transferring and Learning Representations for Image Generation and Translation

Visual recognition in the wild: learning from rankings in small domains and continual learning in new domains

Towards End-to-End Networks for Visual Tracking in RGB and TIR Videos

Analysis of background textures in banknotes and identity documents for counterfeit detection

Semantic Representation: From Color to Deep Embeddings

An Endoscopic Navigation System for Lung Cancer Biopsy

Single Sensor Multi-Spectral Imaging

Understanding Eye Movements: Psychophysics and a Model of Primary Visual Cortex

Information Extraction from Heterogeneous Handwritten Documents

Behavior understanding of vulnerable road users by 2D pose estimation

On Building End-to-End Driving Models Through Imitation Learning

Understanding color vision: from psychophysics to computational modeling

Towards Robust Neural Models for Fine-Grained Image Recognition

Fully Convolutional Networks for Text Understanding in Scene Images

Word Spotting and Recognition in Images from Heterogeneous Sources

Action Recognition in Videos: Data-efficient approaches for supervised learning of human action classification models for video

Color in Visual Recognition: from flat to deep representations and some biological parallelisms

Human Segmentation, Pose Estimation and Applications

Computational Model of Visual Perception: From Colour to Form

Local feature description in cross-spectral imagery

Analysis of Head-Pose Invariant, Natural Light Gaze Estimation Methods

Probabilistic Graphical Models for Document Analysis

Exploiting similarity hierarchies for multi-script scene text understanding.

Multi-modal Pedestrian Detection

Vascular Pattern Characterization in Colonoscopy Images

Anatomic Registration based on Medial Axis Parametrizations

Modeling, estimation and evaluation of intrinsic images considering color information

A Confidence Framework for the Assessment of Optical Flow Performance

A Statistical Framework for Terminating Evolutionary Algorithms at their Steady State

Domain Adaptation of Deformable Part-based Models

Focused Structural Document Image Retrieval in Digital Mailroom Applications

Tracheal Structure Characterization using Geometric and Appearance Models for Efficient Assessment of Stenosis in Videobronchoscopy

Relational Models for Visual Understanding of Graphical Documents. Application to Architectural Drawings.

Contextual Word Spotting in Historical Handwritten Documents

Learning to Represent Handwritten Shapes and Words for Matching and Recognition

A computational model of eye guidance, searching for text in real scene images

Reinforcement Learning of Visual Descriptors for Object Recognition

Inexact Subgraph Matching Applied to Symbol Spotting in Graphical Documents

Optical Flow in Driver Assistance Systems

Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection

Color for Object Detection and Action Recognition

Pedestrian Detection Based on Local Experts

Illumination and Object Reflectance Modeling

Environment-Independent Moving Cast Shadow Suppression in Video Surveillance

Multiclass Learning for Vessel Characterization in Intravascular Ultrasound

Looking at Faces: Detection, Tracking and Pose Estimation

Detection and alignment of vascular structures in Intravascular Ultrasound using Pattern Recognition techniques

Document Image Representation, Classification and Retrieval in Large-Scale Domains

Predicting Saliency and Aesthetics in Images: A Bottom-up Perspective

Polyp Localization and Segmentation in Colonoscopy Images by Means of a Model of Appearance for Polyps

Monocular Depth Cues in Computer Vision Applications

Constancy and inconstancy in categorical colour perception

Multimodal Stereo from Thermal Infrared and Visible Spectrum

Contributions to the Diagnosis of Intestinal Motility by Automatic Image Analysis

Towards Deep Image Understanding: From pixels to semantics

3D Motion Data aided Human Action Recognition and Pose Estimation

Model free approach to human action recognition

Many-to-Many High Order Matching. Applications to Tracking and Object Segmentation

Shape Representation and Registration using Implicit Functi ons

Vector Space Embedding of Graphs via Statistics of Labelling Information

Hierarchical Multiresolution Models for fast Object Detection

Compact, Adaptive and Discriminative Spatial Pyramids for Improved Object and Scene Classification

Coloring bag-of-words based image representations

Approximate Ensemble Methods for Physical Activity Recognition Applications

Probabilistic Alignment of Video Sequences recorded by Moving Cameras

Perceptual Criteria on Image Compression

Colour constancy in natural images through Colour Naming and Sensor Sharpening

Multi-Oriented and Multi-Scaled Text Character Analysis and Recognition in Graphical Documents and Their Applications to Document Image Retrieval

Combining Context and Appearance for Road Detection

Texton Theory Revisited. A computational colour approach

Motion Priors for Efficient Bayesian Tracking in Human Sequence Evaluation

Foreground Object Segmentation and Shadow Detection for Video Sequences in Uncontrolled Environments

Understanding Image Sequences: the Role of Ontologies in Cognitive Vision

A Syntactic Pattern Recognition Approach based on a Distribution Tolerant Adjacency Grammar and a Spatial Indexed Parser. Application to Sketched Document Recognition

A global approach to vision-based pedestrian detection for advanced driver assistance systems

Contributions to the Content-Based Image Retrieval Using Pictorial Queries

Statistical Models of the Architecture and Function of the Left Ventricle

Human Emotion Understanding On Facial Image Sequences

Modeling Human Behavior for Image Sequence Understanding and Generation

Exploring Arterial Dynamics and Structures in IntraVascular UltraSound

Statistical framework and prior information modeling in handwritten word-spoting

Writer Identification by a Combination of Graphical Features in the Framework of Old Handwritten Musical Documents

Geometric and Structural-based Symbol Spotting. Application to Focused Retrieval in Graphic Document Collections

Multitask Learning Techniques for Automatic Face Classification

Probabilistic Darwin Machines: A new approach to develop Evolutionary Object Detection

Analysis and Multi-Modal Fusion of Coronary Images

Coding and Decoding Design of ECOCs for Multi-class Pattern and Object Recognition

Theory and Algorithms on the Median Graph. Application to Graph-based

Missing Data Matrix Factorization Addressing the Structure from Motion Problem

Towards Robust Multiple-Target Tracking in Unconstrained Human-Populated Environments