Meet ApplyKite Twin, the application assistant that learns with you

Meet your Twin, it learns with you

Your Twin learns with you

Launch week codes:30% off annual Pro20% off monthly Pro

Ends in00h00m00s

Dimosthenis Karatzas

Profesor Agregado

University of Barcelona

Spain

Research Interests

Explore related searches

Professors in Spain Professors in Computer Vision Computer Vision professors in Spain

About

Dimosthenis Karatzas is an Associate Professor at Universitat Autonoma de Barcelona, Spain. His research focuses on machine learning applications in handwritten text recognition, symbolic reasoning, and multimodal transformers. Recent articles authored by Professor Karatzas include studies on privacy preservation, visual question answering, and scene text retrieval.

Articles (15)

Year:

2027

Year:

2027

Year:

2027

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2025

Year:

2025

Year:

2025

Year:

2023

Year:

2021

Year:

2021

Year:

2021

Collaborators (5)

Lluis Gomez

Universitat Autònoma de Barcelona (UAB)

SPAIN

View details

Marco Bertini

Associate Professor

Università degli Studi di Napoli Federico II

ITALY

View details

Oriol Ramos Terrades

University of Barcelona

SPAIN

View details

Maura Pintor

Assistant Professor

University of Cagliari

ITALY

View details

Niccolo Biondi

Assistant Professor (RTD/A)

University of Florence

ITALY

View details

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Dimosthenis Karatzas

Research Interests

Explore related searches

About

Articles (15)

AdaNav: Query-Adaptive Multi-granularity Navigation for Long Document Understanding

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

Learning Quantifiable Visual Explanations Without Ground-Truth

Preserving privacy without compromising accuracy: Machine unlearning for handwritten text recognition

LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis

ComicsPAP: Understanding Comic Strips by Picking the Correct Panel

Position-Aware Stamp-Like Adversarial Attack for Document Classification

Spatially Grounded Explanations in VisionLanguage Models for Document Visual Question Answering

A Benchmark for Symbolic Reasoning from Pixel Sequences: Grid-Level Visual Completion and Correction

ComiCap: A VLMs Pipeline for Dense Captioning of Comic Panels

AVIR: Adaptive Visual In-Document Retrieval for Efficient Multi-Page Document Question Answering

Hierarchical multimodal transformers for Multipage DocVQA

Multimodal grid features and cell pointers for scene text visual question answering

Asking questions on handwritten document collections

Real-time Lexicon-free Scene Text Retrieval

Collaborators (5)

Lluis Gomez

Marco Bertini

Oriol Ramos Terrades

Maura Pintor

Niccolo Biondi

Make your next move.