Seminars

A General Framework for Text Line Detection and Recognition

Marrying Multi-view Geometry with Deep Priors for Image-based 3D Reconstruction

Computer Vision Group at the UvA

Vision-Language Contrastive Models: Generalizing Semantic Segmentation and Studying Model Dynamics

Study and modeling of user behavior and attention in immersive environments.

Benchmarking and Optimizing Gradient-Based Adversarial Attacks for ML Security.

“Hey GPT, please diagnose this histology slide”

Multimedia Retrieval Strategies in Videos and the Metaverses Frontier

Two complementary perspectives to continual learning: ask not only what to optimize, but also how

Image quality assessment in practical – exploring IQA in dynamic scenes

The Particle and Astrophysical Science Computing Center on the AI era

Responsible AI

Brain Imaging: Data Analysis and Modeling

Challenges in Educational Technology

Brain Networks and Medical Image Analysis

Computational Models and Machine Learning for Neuroscience

Normalized Moments for Photo-realistic Style Transfer

Calibration in Neural Networks: Understanding, Measuring & Improving it

Quantum Machine Learning

Intelligent Automation for AI-driven Document Understanding

Multimedia content protection: from model-based to data-driven approaches

Interpretable-by-design Prototype-based Deep Learning

Meta-RL for Visual Semantic Navigation

Self-supervised Learning from Images, and Augmentations

Mining large medical radiology image repositories

Improving generalization for classification and retrieval tasks

Deep Learning for Document, Scene and Satellite Images Processing and Recognition

From scans to information: end-to-end information extraction from documents

Calibrated Fine-Grained Recognition and Retrieval

ACM Multimedia, ECCV and ICPR Internal Seminar 

Continual Learning from Pretrained Models

Requisitos necesarios para realizar pruebas con vehículos automatizados en carreteras españolas

CVPR and IVS 2021 Presentations

Towards better cross-modal learning by Probabilistic embedding and AdamP optimizer

Simple Inference and Generation Using Multimodal Information

Towards active sensing: MRI acquisition as case study

Keep on Learning

Crafting and learning for image matching

Machine Learning for Robot Vision

Counting Votes and the Attempt to Replicate Human Interpretation and The Code 8.7 Initiative: Using AI to End Modern Slavery

Comparison and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to human behavior understanding

CVC Seminars: Dr. Daniela Rus

Multisensor multitemporal AI approaches to the detection and analysis of archaeological settlements at a continental scale

Learning to Reconstruct 3D Objects

Mining and Enriching Multilingual Scientific Text Collections: Challenges and Opportunities

Learning spatio-temporal video representations

CVPR2018 Seminar

Multi-level image understanding and beyond

ICLR 2018 presentations

Lifelong learning seminar

Recent Applications of Deep Learning for Retinal Image Analysis

Learning CNN filter resolution using multi-scale structured receptive fields

Deep Multimodal and contextual visual recognition

Historical Map Alignment and Toponym Recognition with Geographic and Style Models

Semantic segmentation of 3D textured meshes for urban scene analysis

3D Mask Face Anti-Spoofing with Remote Photoplethy Smography

The World-as-Support: embodied exploration, understanding and meaning-making of the augmented world

Mapping the World with Street View

Computational mechanisms of rapid visual recognition

Low-Level Vision Color Constancy and Prior Color Naming for Application-independent Automated Linear-Time Detection and Quality Assessment of Superpixels in Multi-Source Color Images

From Medical Image Analysis to Computer-based Personalized Medicine.

Dynamic Probabilistic Models for Person Tracking and Activity Recognition

Semi-Supervised Learning in Large Image Collections

Active Pedestrian Safety 2.0

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation.

Leave-One-Out Kernel Optimization for Shadow Detection

Image guided robotics for cardiac surgery

Looking at / Sensing People

An Active Search Strategy for Efficient Object Class Detection

Assisting the training of deep neural networks with applications to computer vision

Spectral Edge Image Fusion: Theory and Practice

Advances in Statistical Machine Translation in the last 10 years

Deep fishing: Extracting Gradient Features from Deep Nets / LEWIS: Latent embeddings for word images and their semantics

Structural Models for Deformable Shape Recognition

Game Theory as a Tool for Inlier Selection

3D pose and shape from monocular images

Object detection with incomplete supervision

Considering the camera imaging pipeline for color image processing: Color stabilization, blind gamma estimation, and…

Document Image Classification and Retrieval

Applications to Annotation and Retrieval

Making Bertha See

Data-driven detection and self-learning camera

Scene Understanding in Videos: Segmentation, Tracking and Pose Estimation

Characteristics of Characters and Contexts of Texts: Several topics around Scene Texts

A polynomial algorithm for HMM decoding with long-distance dependencies

A polynomial algorithm for HMM decoding with long-distance dependencies

Automation of Flow Cytometric Analysis (Marie Curie Research Action)

Using a deformation field model for localizing faces and facial points under weak supervision

Strong Geometric Context for Image Understanding

Studying Perceptual Tasks in Different Domains using Eye-Movements

Visual Language Processing (VLP) of Ancient Manuscripts: Converting Collections to Windows on the Past

Sequential image analysis for computer-aided wireless endoscopy.

Motion Estimation Revisited: an Estimation-Theoretic Approach

Context, regularized expert stacking, and transductive inference for large-scale action recognition in video

Mass digitisation is here now: What it means for Document Analysis Researchers

Visual Scene Understanding for Autonomous Systems

Some contributions to structural methods for pattern recognition

Prediction of Pedestrians Intentions

Towards a Quadratic Time Approximation of Graph Edit Distance.

Statistical learning & computer vision: affective computing, action modeling and tracking at SEQAM Lab

Video Stabilization for Everyone: From Research to Launch on YouTube

Real-time Visual Map Building

Classifier ensembles: Is there more to be done?

Digital Spaces Living Lab

Ebook readers: challenges and opportunities for Document Analysis research

Search Based Inference and 3D Object Detection

Artificial Neural Networks for Preprocessing and Recognizing Handwritten Text

Approximate search as a source coding problem, with application to large scale image and object recognition

Spatio-chromatic Adaptation via Higher-Order Canonical Correlation Analysis

The contribution of color for edge detection in natural scenes

Kernel signal-to-noise ratio for machine learning

Differential Evolution: Properties and Applications

Ground Truth for Correspondence Problems: What we need to know

Dynamic Shape Instantiation for Intra-operative Navigation

Intelligent Vision Systems: A foray into Computer Vision at the University of Auckland

Computer vision research at the University of Oulu: from LBP to computational photography

Why don’t we hear lightning and see thunder? The sensorimotor approach to phenomenal consciousness

Applied Visual Computing: Case Studies from the University of Bradford

Platforms for Document Image Processing

Lie Groups and Algebras in Computer Vision

Combining Vision, Interaction, and Web Queries: Reasoning about Epistemic Actions and Uncertainty for Autonomous Knowledge Gathering in Robots

Virtual Colonoscopy (Techniques of CT colonography)

Humans like watching humans: recent advances in human-centered video analysis

Image categorization using Fisher kernels of non-iid image models

Disturbing vision

Vision por Computador en la Universidad del Bio-Bio

Understanding the Structure of Cognition across Individuals – Machine Learning in Neuroimaging

Service Robots for Elderly Care

Handwriting Recognition in Historical Documents

Brain-inspired computing for machine vision

Energy Aware Recognition for Man Made Structures and other research projects at the American University of Beirut

Aldebaran Robotics – NAO

Network Analysis using Diffusions, Entropy and Graph Spectra

Introduction to Android Programming and OpenCV for Android

Change Detection in Streaming Multivariate Data Using Likelihood Detectors

Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning

Monocular 3D Pose Estimation

Saliency, visual attention and image quality

Space, Design, and Interactive Vision: Creating a Spatial Operating Environment

Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models

Multi ­scale Stacked Sequential Learning

Learning Components for Human Sensing

LARTREAT EU project: Computer, Experimental and Clinicalmodel of Three-Dimensional Plaque

Affective Image Classification using Features Inspired by Psychology and Art Theory

Layered Surfaces Decomposition Using the Spider Model

In Uncertainty in Artificial Intelligence 2011

4D PET-CT imaging for radiotherapy treatment planning

Document Image processing and Word Spotting

Learning Gaussian Graphical Models With Domain Specific Prior

Multiobjective Fuzzy Clustering

Unsupervised STDP-based learning and computer vision applications

Improving Web Image Search Results Using Query-Relative Classifiers

Actom Sequence Models for Efficient Action Detection

Albatrosses, jackals and gaze shifts

Governance and technology: Imaging law

A multimodal interactive image information retrieval system for smartphones

Colour constancy in natural scenes: a computational look

Illuminant Color Estimation in Support of Vision Applications

Wearable devices for the visually impaired. Lessons learnt from autonomous robotics

Iterative Gaussianization Framework for Image Processing

Recent advances on contact less hand biometrics and off line signature verification

Learning of Data Collections in High-Dimensional Spaces Without Supervision