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

StacMR: Scene-Text Aware Cross-Modal Retrieval


Dec 08, 2020
Andrés Mafla, Rafael Sampaio de Rezende, Lluís Gómez, Diane Larlus, Dimosthenis Karatzas

Figure 1 for StacMR: Scene-Text Aware Cross-Modal Retrieval
Figure 2 for StacMR: Scene-Text Aware Cross-Modal Retrieval
Figure 3 for StacMR: Scene-Text Aware Cross-Modal Retrieval
Figure 4 for StacMR: Scene-Text Aware Cross-Modal Retrieval

  Access Paper or Ask Questions

Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval


Sep 21, 2020
Andres Mafla, Sounak Dey, Ali Furkan Biten, Lluis Gomez, Dimosthenis Karatzas

Figure 1 for Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
Figure 2 for Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
Figure 3 for Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
Figure 4 for Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

  Access Paper or Ask Questions

Document Visual Question Answering Challenge 2020


Aug 20, 2020
Minesh Mathew, Ruben Tito, Dimosthenis Karatzas, R. Manmatha, C. V. Jawahar

Figure 1 for Document Visual Question Answering Challenge 2020
Figure 2 for Document Visual Question Answering Challenge 2020
Figure 3 for Document Visual Question Answering Challenge 2020
* to be published as a short paper in DAS 2020 
  Access Paper or Ask Questions

Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation


Aug 11, 2020
Raul Gomez, Yahui Liu, Marco De Nadai, Dimosthenis Karatzas, Bruno Lepri, Nicu Sebe

Figure 1 for Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
Figure 2 for Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
Figure 3 for Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
Figure 4 for Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
* Submitted to ACM MM '20, October 12-16, 2020, Seattle, WA, USA 
  Access Paper or Ask Questions

Text Recognition -- Real World Data and Where to Find Them


Jul 17, 2020
Klára Janoušková, Jiri Matas, Lluis Gomez, Dimosthenis Karatzas

Figure 1 for Text Recognition -- Real World Data and Where to Find Them
Figure 2 for Text Recognition -- Real World Data and Where to Find Them
Figure 3 for Text Recognition -- Real World Data and Where to Find Them
Figure 4 for Text Recognition -- Real World Data and Where to Find Them
* 10 pages 
  Access Paper or Ask Questions

Location Sensitive Image Retrieval and Tagging


Jul 07, 2020
Raul Gomez, Jaume Gibert, Lluis Gomez, Dimosthenis Karatzas

Figure 1 for Location Sensitive Image Retrieval and Tagging
Figure 2 for Location Sensitive Image Retrieval and Tagging
Figure 3 for Location Sensitive Image Retrieval and Tagging
Figure 4 for Location Sensitive Image Retrieval and Tagging
* ECCV 2020 
  Access Paper or Ask Questions

DocVQA: A Dataset for VQA on Document Images


Jul 01, 2020
Minesh Mathew, Dimosthenis Karatzas, R. Manmatha, C. V. Jawahar

Figure 1 for DocVQA: A Dataset for VQA on Document Images
Figure 2 for DocVQA: A Dataset for VQA on Document Images
Figure 3 for DocVQA: A Dataset for VQA on Document Images
Figure 4 for DocVQA: A Dataset for VQA on Document Images

  Access Paper or Ask Questions

Multimodal grid features and cell pointers for Scene Text Visual Question Answering


Jun 25, 2020
Lluís Gómez, Ali Furkan Biten, Rubèn Tito, Andrés Mafla, Marçal Rusiñol, Ernest Valveny, Dimosthenis Karatzas

Figure 1 for Multimodal grid features and cell pointers for Scene Text Visual Question Answering
Figure 2 for Multimodal grid features and cell pointers for Scene Text Visual Question Answering
Figure 3 for Multimodal grid features and cell pointers for Scene Text Visual Question Answering
Figure 4 for Multimodal grid features and cell pointers for Scene Text Visual Question Answering
* This paper is under consideration at Pattern Recognition Letters 
  Access Paper or Ask Questions

Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features


Jan 14, 2020
Andres Mafla, Sounak Dey, Ali Furkan Biten, Lluis Gomez, Dimosthenis Karatzas

Figure 1 for Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features
Figure 2 for Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features
Figure 3 for Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features
Figure 4 for Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features
* Winter Conference on Applications of Computer Vision (WACV 2020) Accepted paper 
  Access Paper or Ask Questions

ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard


Dec 20, 2019
Xi Liu, Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, Mingkun Yang, Xiang Bai, Baoguang Shi, Dimosthenis Karatzas, Shijian Lu, C. V. Jawahar

Figure 1 for ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
Figure 2 for ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
Figure 3 for ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
Figure 4 for ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
* International Conference on Document Analysis and Recognition, 2019 
  Access Paper or Ask Questions

Exploring Hate Speech Detection in Multimodal Publications


Oct 09, 2019
Raul Gomez, Jaume Gibert, Lluis Gomez, Dimosthenis Karatzas

Figure 1 for Exploring Hate Speech Detection in Multimodal Publications
Figure 2 for Exploring Hate Speech Detection in Multimodal Publications
Figure 3 for Exploring Hate Speech Detection in Multimodal Publications
Figure 4 for Exploring Hate Speech Detection in Multimodal Publications

  Access Paper or Ask Questions

ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT


Sep 17, 2019
Yipeng Sun, Zihan Ni, Chee-Kheng Chng, Yuliang Liu, Canjie Luo, Chun Chet Ng, Junyu Han, Errui Ding, Jingtuo Liu, Dimosthenis Karatzas, Chee Seng Chan, Lianwen Jin

Figure 1 for ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
Figure 2 for ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
Figure 3 for ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
Figure 4 for ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
* ICDAR 2019 Robust Reading Challenge in IAPR International Conference on Document Analysis and Recognition (ICDAR) 
  Access Paper or Ask Questions

ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)


Sep 16, 2019
Chee-Kheng Chng, Yuliang Liu, Yipeng Sun, Chun Chet Ng, Canjie Luo, Zihan Ni, ChuanMing Fang, Shuaitao Zhang, Junyu Han, Errui Ding, Jingtuo Liu, Dimosthenis Karatzas, Chee Seng Chan, Lianwen Jin

Figure 1 for ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
Figure 2 for ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
Figure 3 for ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
Figure 4 for ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
* Technical report of ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT) Competition 
  Access Paper or Ask Questions

ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019


Jul 01, 2019
Nibal Nayef, Yash Patel, Michal Busta, Pinaki Nath Chowdhury, Dimosthenis Karatzas, Wafa Khlif, Jiri Matas, Umapada Pal, Jean-Christophe Burie, Cheng-lin Liu, Jean-Marc Ogier

Figure 1 for ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
Figure 2 for ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
Figure 3 for ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
Figure 4 for ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
* ICDAR'19 camera-ready version. Competition available at https://rrc.cvc.uab.es/?ch=15. The first two authors contributed equally 
  Access Paper or Ask Questions

ICDAR 2019 Competition on Scene Text Visual Question Answering


Jun 30, 2019
Ali Furkan Biten, Rubèn Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, Minesh Mathew, C. V. Jawahar, Ernest Valveny, Dimosthenis Karatzas

Figure 1 for ICDAR 2019 Competition on Scene Text Visual Question Answering
Figure 2 for ICDAR 2019 Competition on Scene Text Visual Question Answering
Figure 3 for ICDAR 2019 Competition on Scene Text Visual Question Answering
Figure 4 for ICDAR 2019 Competition on Scene Text Visual Question Answering
* 15th International Conference on Document Analysis and Recognition (ICDAR 2019) 
  Access Paper or Ask Questions

Selective Style Transfer for Text


Jun 04, 2019
Raul Gomez, Ali Furkan Biten, Lluis Gomez, Jaume Gibert, Marçal Rusiñol, Dimosthenis Karatzas

Figure 1 for Selective Style Transfer for Text
Figure 2 for Selective Style Transfer for Text
Figure 3 for Selective Style Transfer for Text
Figure 4 for Selective Style Transfer for Text
* Accepted in ICDAR 2019 
  Access Paper or Ask Questions

Scene Text Visual Question Answering


May 31, 2019
Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, Ernest Valveny, C. V. Jawahar, Dimosthenis Karatzas

Figure 1 for Scene Text Visual Question Answering
Figure 2 for Scene Text Visual Question Answering
Figure 3 for Scene Text Visual Question Answering
Figure 4 for Scene Text Visual Question Answering

  Access Paper or Ask Questions

Good News, Everyone! Context driven entity-aware captioning for news images


Apr 02, 2019
Ali Furkan Biten, Lluis Gomez, Marçal Rusiñol, Dimosthenis Karatzas

Figure 1 for Good News, Everyone! Context driven entity-aware captioning for news images
Figure 2 for Good News, Everyone! Context driven entity-aware captioning for news images
Figure 3 for Good News, Everyone! Context driven entity-aware captioning for news images
Figure 4 for Good News, Everyone! Context driven entity-aware captioning for news images
* IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019) 
  Access Paper or Ask Questions

Self-Supervised Visual Representations for Cross-Modal Retrieval


Jan 31, 2019
Yash Patel, Lluis Gomez, Marçal Rusiñol, Dimosthenis Karatzas, C. V. Jawahar

Figure 1 for Self-Supervised Visual Representations for Cross-Modal Retrieval
Figure 2 for Self-Supervised Visual Representations for Cross-Modal Retrieval
Figure 3 for Self-Supervised Visual Representations for Cross-Modal Retrieval
Figure 4 for Self-Supervised Visual Representations for Cross-Modal Retrieval
* arXiv admin note: text overlap with arXiv:1807.02110 
  Access Paper or Ask Questions

Self-Supervised Learning from Web Data for Multimodal Retrieval


Jan 07, 2019
Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas

Figure 1 for Self-Supervised Learning from Web Data for Multimodal Retrieval
Figure 2 for Self-Supervised Learning from Web Data for Multimodal Retrieval
Figure 3 for Self-Supervised Learning from Web Data for Multimodal Retrieval
Figure 4 for Self-Supervised Learning from Web Data for Multimodal Retrieval
* Submitted to Multi-Modal Scene Understanding. arXiv admin note: substantial text overlap with arXiv:1808.06368 
  Access Paper or Ask Questions

Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images


Sep 04, 2018
Dena Bazazian, Dimosthenis Karatzas, Andrew D. Bagdanov

Figure 1 for Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images
Figure 2 for Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images
Figure 3 for Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images
* 4 pages, 3 figures, The Third International Workshop on Egocentric Perception, Interaction and Computing (EPIC) at ECCV2018 
  Access Paper or Ask Questions

Single Shot Scene Text Retrieval


Aug 27, 2018
Lluís Gómez, Andrés Mafla, Marçal Rusiñol, Dimosthenis Karatzas

Figure 1 for Single Shot Scene Text Retrieval
Figure 2 for Single Shot Scene Text Retrieval
Figure 3 for Single Shot Scene Text Retrieval
Figure 4 for Single Shot Scene Text Retrieval
* ECCV 2018 
  Access Paper or Ask Questions

Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods


Aug 20, 2018
Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas

Figure 1 for Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods
Figure 2 for Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods
Figure 3 for Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods
Figure 4 for Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods
* ECCV MULA Workshop 2018 
  Access Paper or Ask Questions

Learning to Learn from Web Data through Deep Semantic Embeddings


Aug 20, 2018
Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas

Figure 1 for Learning to Learn from Web Data through Deep Semantic Embeddings
Figure 2 for Learning to Learn from Web Data through Deep Semantic Embeddings
Figure 3 for Learning to Learn from Web Data through Deep Semantic Embeddings
Figure 4 for Learning to Learn from Web Data through Deep Semantic Embeddings
* ECCV MULA Workshop 2018 
  Access Paper or Ask Questions

TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces


Jul 04, 2018
Yash Patel, Lluis Gomez, Raul Gomez, Marçal Rusiñol, Dimosthenis Karatzas, C. V. Jawahar

Figure 1 for TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
Figure 2 for TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
Figure 3 for TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
Figure 4 for TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
* arXiv admin note: text overlap with arXiv:1705.08631 
  Access Paper or Ask Questions

Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings


Jun 19, 2018
Anguelos Nicolaou, Sounak Dey, Vincent Christlein, Andreas Maier, Dimosthenis Karatzas

Figure 1 for Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
Figure 2 for Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
Figure 3 for Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings
Figure 4 for Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings

  Access Paper or Ask Questions

The Robust Reading Competition Annotation and Evaluation Platform


May 21, 2018
Dimosthenis Karatzas, Lluis Gómez, Anguelos Nicolaou, Marçal Rusiñol

Figure 1 for The Robust Reading Competition Annotation and Evaluation Platform
Figure 2 for The Robust Reading Competition Annotation and Evaluation Platform
Figure 3 for The Robust Reading Competition Annotation and Evaluation Platform
Figure 4 for The Robust Reading Competition Annotation and Evaluation Platform
* Proc. of the 13th IAPR Int. W. on Document Analysis Systems (DAS 2018), IEEE CPS, pp. 61-66, 2018 
 * 6 pages, accepted to DAS 2018 
  Access Paper or Ask Questions

Self-supervised learning of visual features through embedding images into text topic spaces


May 24, 2017
Lluis Gomez, Yash Patel, Marçal Rusiñol, Dimosthenis Karatzas, C. V. Jawahar

Figure 1 for Self-supervised learning of visual features through embedding images into text topic spaces
Figure 2 for Self-supervised learning of visual features through embedding images into text topic spaces
Figure 3 for Self-supervised learning of visual features through embedding images into text topic spaces
Figure 4 for Self-supervised learning of visual features through embedding images into text topic spaces
* Accepted CVPR 2017 paper 
  Access Paper or Ask Questions