Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Dimosthenis Karatzas

Dimosthenis Karatzas

Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement



Mohamed Ali Souibgui , Sanket Biswas , Andres Mafla , Ali Furkan Biten , Alicia Fornés , Yousri Kessentini , Josep Lladós , Lluis Gomez , Dimosthenis Karatzas

Figure 1 for Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Figure 2 for Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Figure 3 for Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Figure 4 for Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
* Preprint 
   Access Paper or Ask Questions

OCR-IDL: OCR Annotations for Industry Document Library Dataset



Ali Furkan Biten , Rubèn Tito , Lluis Gomez , Ernest Valveny , Dimosthenis Karatzas

Figure 1 for OCR-IDL: OCR Annotations for Industry Document Library Dataset
Figure 2 for OCR-IDL: OCR Annotations for Industry Document Library Dataset
Figure 3 for OCR-IDL: OCR Annotations for Industry Document Library Dataset
Figure 4 for OCR-IDL: OCR Annotations for Industry Document Library Dataset

   Access Paper or Ask Questions

ICDAR 2021 Competition on Document VisualQuestion Answering



Rubèn Tito , Minesh Mathew , C. V. Jawahar , Ernest Valveny , Dimosthenis Karatzas

Figure 1 for ICDAR 2021 Competition on Document VisualQuestion Answering
Figure 2 for ICDAR 2021 Competition on Document VisualQuestion Answering
Figure 3 for ICDAR 2021 Competition on Document VisualQuestion Answering
Figure 4 for ICDAR 2021 Competition on Document VisualQuestion Answering

   Access Paper or Ask Questions

Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching



Ali Furkan Biten , Andres Mafla , Lluis Gomez , Dimosthenis Karatzas

Figure 1 for Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
Figure 2 for Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
Figure 3 for Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
Figure 4 for Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching
* Accepted WACV 2022 
   Access Paper or Ask Questions

Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning



Ali Furkan Biten , Lluis Gomez , Dimosthenis Karatzas

Figure 1 for Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
Figure 2 for Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
Figure 3 for Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
Figure 4 for Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
* Accepted to WACV 2022 
   Access Paper or Ask Questions

Asking questions on handwritten document collections



Minesh Mathew , Lluis Gomez , Dimosthenis Karatzas , CV Jawahar

Figure 1 for Asking questions on handwritten document collections
Figure 2 for Asking questions on handwritten document collections
Figure 3 for Asking questions on handwritten document collections
Figure 4 for Asking questions on handwritten document collections
* journal = {Int. J. Document Anal. Recognit.}, volume = {24}, number = {3}, pages = {235--249}, year = {2021} 
 * pre-print version 
   Access Paper or Ask Questions

One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition



Mohamed Ali Souibgui , Ali Furkan Biten , Sounak Dey , Alicia Fornés , Yousri Kessentini , Lluis Gomez , Dimosthenis Karatzas , Josep Lladós

Figure 1 for One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
Figure 2 for One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
Figure 3 for One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
Figure 4 for One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition

   Access Paper or Ask Questions

Document Collection Visual Question Answering



Rubèn Tito , Dimosthenis Karatzas , Ernest Valveny

Figure 1 for Document Collection Visual Question Answering
Figure 2 for Document Collection Visual Question Answering
Figure 3 for Document Collection Visual Question Answering
Figure 4 for Document Collection Visual Question Answering

   Access Paper or Ask Questions

InfographicVQA



Minesh Mathew , Viraj Bagal , Rubèn Pérez Tito , Dimosthenis Karatzas , Ernest Valveny , C. V Jawahar

Figure 1 for InfographicVQA
Figure 2 for InfographicVQA
Figure 3 for InfographicVQA
Figure 4 for InfographicVQA

   Access Paper or Ask Questions
1
2
3
4
5
>>