Dimosthenis Karatzas

About Dimosthenis Karatzas

Dimosthenis Karatzas, With an exceptional h-index of 39 and a recent h-index of 30 (since 2020), a distinguished researcher at Universidad Autónoma de Barcelona, specializes in the field of computer vision, document image analysis, vision and language, human document interaction, reading systems.

His recent articles reflect a diverse array of research interests and contributions to the field:

Retrieval Augmented Verification: Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts

STEP-Towards Structured Scene-Text Spotting

Machine Unlearning for Document Classification

Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism

Privacy-Aware Document Visual Question Answering

Hierarchical multimodal transformers for Multipage DocVQA

Overview of DocILE 2023: Document Information Localization and Extraction

ICDAR 2023 Competition on Video Text Reading for Dense and Small Text

Dimosthenis Karatzas Information

University

Position

Computer Vision Center

Citations(all)

8672

Citations(since 2020)

6146

Cited By

4496

hIndex(all)

39

hIndex(since 2020)

30

i10Index(all)

101

i10Index(since 2020)

73

Email

University Profile Page

Google Scholar

Dimosthenis Karatzas Skills & Research Interests

computer vision

document image analysis

vision and language

human document interaction

reading systems

Top articles of Dimosthenis Karatzas

Retrieval Augmented Verification: Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts

arXiv preprint arXiv:2404.10702

2024/4/16

Ernest Valveny
Ernest Valveny

H-Index: 19

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

STEP-Towards Structured Scene-Text Spotting

2024

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Machine Unlearning for Document Classification

arXiv preprint arXiv:2404.19031

2024/4/29

Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism

arXiv preprint arXiv:2404.19024

2024/4/29

Lei Kang
Lei Kang

H-Index: 9

Ernest Valveny
Ernest Valveny

H-Index: 19

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Privacy-Aware Document Visual Question Answering

arXiv preprint arXiv:2312.10108

2023/12/15

Hierarchical multimodal transformers for Multipage DocVQA

Pattern Recognition

2023/12/1

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Ernest Valveny
Ernest Valveny

H-Index: 19

Overview of DocILE 2023: Document Information Localization and Extraction

2023/9/11

Milan Šulc
Milan Šulc

H-Index: 8

Yash Patel
Yash Patel

H-Index: 7

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

ICDAR 2023 Competition on Video Text Reading for Dense and Small Text

2023/8/19

ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition

2023/8/19

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Reading Between the Lanes: Text VideoQA on the Road

2023/8/19

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning

2023/8/19

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

ICDAR 2023 Competition on Reading the Seal Title

2023/8/19

Docile benchmark for document information localization and extraction

2023/8/19

Milan Šulc
Milan Šulc

H-Index: 8

Yash Patel
Yash Patel

H-Index: 7

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Text-diae: A self-supervised degradation invariant autoencoder for text recognition and document enhancement

proceedings of the AAAI conference on artificial intelligence

2023/6/26

Show, interpret and tell: entity-aware contextualised image captioning in wikipedia

Proceedings of the AAAI Conference on Artificial Intelligence

2023/6/26

Icdar 2023 video text reading competition for dense and small text

arXiv preprint arXiv:2304.04376

2023/4/10

Understanding Video Scenes through Text: Insights from Text-based Video Question Answering

2023

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Extended Overview of DocILE 2023: Document Information Localization and Extraction

2023

Milan Šulc
Milan Šulc

H-Index: 8

Yash Patel
Yash Patel

H-Index: 7

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

Watching the news: Towards videoqa models that can read

2023

Dimosthenis Karatzas
Dimosthenis Karatzas

H-Index: 24

See List of Professors in Dimosthenis Karatzas University(Universidad Autónoma de Barcelona)

Co-Authors

academic-engine