Dìmosthenis Karatzas

Universitat Autònoma de Barcelona — Spain

Computer Science · Physical Sciences

33h-index7.4kcitations257works0.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Handwritten Text Recognition Techniques(112), Advanced Image and Video Retrieval Techniques(84), Image Retrieval and Classification Techniques(67), Multimodal Machine Learning Applications(66), Video Analysis and Summarization(38)

Publications257 total

AVIR: Adaptive Visual In-Document Retrieval for Efficient Multi-Page Document Question Answering
2025Open Access
Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
arXiv (Cornell University)·2025Open Access
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
2025
Position-Aware Stamp-Like Adversarial Attack for Document Classification
Lecture notes in computer science·2025
LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis
Lecture notes in computer science·2025
ICDAR 2025 Handwritten Notes Understanding Challenge
Lecture notes in computer science·2025
ComicsPAP: Understanding Comic Strips by Picking the Correct Panel
Lecture notes in computer science·2025
Preserving privacy without compromising accuracy: Machine unlearning for handwritten text recognition
Pattern Recognition·2025· 1 citedOpen Access
A Benchmark for Symbolic Reasoning from Pixel Sequences: Grid-Level Visual Completion and Correction
Mathematics·2025Open Access
Spatially Grounded Explanations in VisionLanguage Models for Document Visual Question Answering
Lecture notes in computer science·2025
Special issue on advanced topics in document analysis (2025 ICDAR-IJDAR journal track)
International Journal on Document Analysis and Recognition (IJDAR)·2025Open Access
Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering
arXiv (Cornell University)·2025Open Access
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
arXiv (Cornell University)·2025Open Access
TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
arXiv (Cornell University)·2025Open Access
LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis
arXiv (Cornell University)·2025Open Access
DocVXQA: Context-Aware Visual Explanations for Document Question Answering
arXiv (Cornell University)·2025Open Access
xLSTM-ECG: Multi-label ECG Classification via Feature Fusion with xLSTM
arXiv (Cornell University)·2025Open Access
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding
arXiv (Cornell University)·2025Open Access
Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition
arXiv (Cornell University)·2025Open Access
ComicsPAP: understanding comic strips by picking the correct panel
arXiv (Cornell University)·2025Open Access
page 1 of 13Next →

Frequent Co-authors

Lluís Gómez(20), Ernest Valveny(11), Marçal Rusiñol(10), C. V. Jawahar(9), Rubèn Tito(7), Andrés Mafla(6), Ali Furkan Biten(6), Minesh Mathew(5), Apostolos Antonacopoulos(5), Andrew D. Bagdanov(4), Josep Lladós(4), Anguelos Nicolaou(3), Jiřı́ Matas(3), Shijian Lu(3), Christophe Rigaud(3), Jean-Christophe Burie(3), Errui Ding(3), Jingtuo Liu(3), Chee Seng Chan(3), Lianwen Jin(3)