Publications

Follow me on: 

Journals

1. T. Benzenati, A. Kallel,  Y. Kessentini, STF-Trans: A Two-stream SpatioTemporal Fusion Transformer for Very High Resolution Satellites Images, Neurocomputing, vol. 563, January 2024.  [Link]

2. M. Dhiaf, A. Cheikhrouhou, Y. Kessentini, S. Ben Salem, MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognition, Pattern Recognition Letters (PRL), vol. 169, pp. 28-34, May 2023. [Link] [arxiv] 

3. T. Benzenati, Y. Kessentini, A. Kallel, Spectral-Temporal Fusion of Satellite Images Via an End-to-End Two-Stream Attention With an Effective Reconstruction Network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 16, pp. 1308-1320, January 2023. [Link] [PDF]

4. M. A. Souibgui, A. Fornés, Y. Kessentini, B. Megyesi, Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwriting Recognition. Pattern Recognition Letters (PRL), vol. 160, pp. 43-49, August 2022.  [Link] [code] [arxiv] 

5. M. Ghorbel, S. Ammar, Y. Kessentini, M. Jmaiel, Masking for Better Discovery: Weakly Supervised Complementary Body Regions Mining for Person Re-identification, Expert Systems with Applications (ESWA), vol. 197, July 2022. [Link] 

6. S. Khamekhem Jemni, M. A. Souibgui, Y. Kessentini, A. Fornés, Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement, Pattern Recognition journal, vol. 123, March 2022. [Link] [arxiv]

7. M. A. Souibgui, Y. Kessentini, DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 44, no. 3, pp. 1180-1191, March 2022.  [Link] [code] [arxiv] 

8. A. Cheikhrouhou, M. Dhiaf, Y. Kessentini, S. Ben Salem, Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents, Pattern Recognition Letters (PRL), vol. 155, pp. 128-134, March 2022.  [Link] [arxiv]

9. S. Khamekhem Jemni, S. Ammar, Y. Kessentini, Domain and writer adaptation of offline Arabic handwriting recognition using deep neural networks, Neural Computing and Applications (NCAA), vol. 34, pp. 2055–2071 February 2022. [Link] 

10. T. Benzenati, Y. Kessentini, A. Kallel, Pansharpening Approach via Two-stream Detail Injection Based on Relativistic Generative Adversarial Networks, Expert Systems with Applications (ESWA), vol. 188, February 2022. [Link] [PDF]

11. I. Feki, S. Ammar, Y. Kessentini, M. Khan, Federated learning for COVID-19 screening from Chest X-ray images, Applied Soft Computing journal (ASOC), vol. 116, July 2021. [Link]

12. T. Benzenati, A. Kallel, Y. Kessentini, Two stages Pan-sharpening Details Injection Approach based on very Deep Residual Networks, IEEE Transactions on Geoscience and Remote Sensing (TGRS), vol. 59, no. 6, pp. 4984-4992, June 2021. [Link]

13. A. Cheikhrouhou, Y. Kessentini, S. Kanoun, Multi-Task Learning for Simultaneous Script Identification and Keyword Spotting in Document images, Pattern Recognition, vol. 113, pp. 107832, May 2021. [Link]

14. N. Mansouri, S. Ammar, Y. Kessentini, Re-ranking Person Re-identification using Attributes learning, Neural Computing and Applications, vol. 33, pp. 12827–12843, October 2021. [Link] 

15. A. Cheikhrouhou, Y. Kessentini, S. Kanoun, Hybrid HMM/BLSTM system for multi-script keyword spotting in printed and handwritten documents with identification stage, Neural Computing and Applications (NCAA), vol. 32, pp. 9201–9215, July 2020. [Link]

16. T. Benzenati, Y. Kessentini, A. Kallel, H.Hallabia, Generalized Laplacian Pyramid Pan-sharpening Gain Injection Prediction based on CNN, IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 4, pp. 651-655, April 2020. [Link]

17. S. Khamekhem Jemni, Y. Kessentini, S. Kanoun, Improving Recurrent Neural Networks for Offline Arabic Handwriting Recognition by combining different Language Models, International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI). vol. 34, no. 12, 2020. [Link]

18. Y. Kessentini, M. D. Besbes, S. Ammar, A. Chabbouh, A Two-Stage Deep Neural Network for Multi-norm License Plate Detection and Recognition, Expert Systems with Applications, Vol 136, pp 159-170, 2019. [Link]

19. S. Khamekhem Jemni, Y. Kessentini, S. Kanoun, Out of Vocabulary Word Detection and Recovery in Arabic Handwritten Text Recognition, Pattern Recognition, Vol 93, pp. 507-520, 2019. [Link]

20. Y. Kessentini, Sana BenAbderrahim, Chawki Djeddi, Evidential Combination of SVM Classifiers for Writer Recognition, Neurocomputing, Vol 313, pp. 1-13, November 2018.  [Link]

21. Y. Kessentini, T. Burger, T. Paquet. A Demspter-Shafer Theory based combination of Handwriting Recognition Systems with multiple rejection strategies. Pattern Recognition. Vol 48, Issue 2, pp. 534–544, February 2015. [Link]

22. S. Thomas, C. Chatelain, L. Heutte, T. Paquet, and Y. Kessentini, A Deep HMM model for multiple keywords spotting in handwritten documents,  Pattern Analysis and Applications, Vol 18, Issue 4, pp 1003-1015, November 2015. [Link]

23. Y. Kessentini, T. Paquet, A. Benhamadou. Off-Line Handwritten Word Recognition Using Multi-Stream Hidden Markov Models. Pattern recognition Letters (PRL), Vol 30, Issue 1, pp. 60-70, January 2010. [Link]

24. Y. Kessentini, T. Paquet, A. Benhamadou. Reconnaissance de L'écriture Manuscrite Multi-Scripts par des Modèles de Markov Cachés Multi-Flux. Traitement de Signal, vol 26, n° 5, 2009, (selected from CIFED'08). [Link]

International conferences

2024

• Y. Khanfir, M. Dhiaf, A. Cheikhrouhou, E. Ghodhbani, Y. Kessentini, Graph Neural Networks for End-to-End Information Extraction from Handwritten Documents, Winter Conference on Applications of Computer Vision (WACV'2024), pp. 504-512, WAIKOLOA, HAWAII, 2024. [Link] [PDF] [Video]

2023

• I. Feki, S. Ammar, Y. Kessentini, SS-FL: Self-Supervised Federated Learning for COVID-19 Detection from Chest X-ray Images, 15th International Conference on Computational Collective Intelligence (ICCCI'23), Communications in Computer and Information Science, vol 1864, pp 702-714, Budapest, Hungary, 2023. [Link]

• Souibgui, M. A., Biswas, S., Mafla, A., Biten, A. F., Fornés, A., Kessentini, Y., Lladós, J, Gomez, L, & Karatzas, D. Text-DIAE: Degradation Invariant Autoencoders for Text Recognition and Document Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'23), vol 37, N°2, pp 2330-2338, Washington DC, USA, 2023.  [Link][arxiv][code]

2022

• Souibgui, M. A., Biswas, S., Jemni, S. K., Kessentini, Y., Fornés, A., Lladós, J., & Pal, U., DocEnTr: An End-to-End Document Image Enhancement Transformer. In 26th International Conference on Pattern Recognition (ICPR'2022), pp 1699-1705, Montreal, QC, Canada.  [Link][arxiv][Code][DEMO]

• Souibgui M. A., Biten A. F., Dey S., Fornés A., Kessentini Y., Gomez L., Dimosthenis L., Lladós, J, One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition. Winter Conference on Applications of Computer Vision (WACV'2022), pp. 2563-2571, January 2022, Hawaii. [arxiv] [Link]

• I. Feki, S. Ammar, Y. Kessentini, Self-supervised learning for COVID-19 detection from Chest X-ray images, International Conference on Intelligent Systems and Patterns Recognition (ISPR'2022), Communications in Computer and Information Science, vol 1589, pp. 78-89. Springer. Mars 2022. [Link]  

2021

• M. Dhiaf, S. Khamekhem, Y. Kessentini, DocNER: A Deep Learning System for Named Entity Recognition in Handwritten Document Images, 28th International Conference on Neural Information Processing (ICONIP'21), Communications in Computer and Information Science, vol 1517, pp 239-246, Springer, December 2021. Bali, Indonesia.  [Link]

• M. D. Besbes, H. Tabia, Y. Kessentini, B. Benhamed, Progressive Learning with Anchoring Regularization for Vehicle Re-Identification, 28th IEEE International Conference on Image Processing (ICIP'2021), pp. 1154-1158, May 2021. [Link]

2020

•  M. A. Souibgui, A. Fornés, Y. Kessentini, C. Tudor, A Few-shot Learning Approach for Historical Encoded Manuscript Recognition, 25th International Conference on Pattern Recognition (ICPR'2020), pp. 5413-5420, 2020.  ★ Best Student Paper Award ★ [Link][arxiv] 

• M. A. Souibgui, Y. Kessentini,  A. Fornés. A conditional GAN based approach for distorted camera captured documents recovery. Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI'20), Communications in Computer and Information Science, vol 1322, pp 215-228, 2020. [Link]

• T. Benzenati,  Y. Kessentini, A. Kallel. End-to-end Spectral-Temporal Fusion using Convolutional Neural Network, Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI'20), Communications in Computer and Information Science, vol 1322, pp 60-72, 2020. [Link]  ★ Best Student Paper Award ★

• M. Ghorbel, S. Ammar, Y. Kessentini, M. Jmaiel, A. Chaari. Fusing local and global features for person re-identification using multi-stream deep neural networks, Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI), Communications in Computer and Information Science, vol 1322, pp 73-85, 2020. [Link]

• I. Ben Slima, S. Ammar, M. Ghorbel and Y. Kessentini. Possibilistic classifier combination for person re-identification, Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI), Communications in Computer and Information Science, vol 1322, pp 98-111, 2020. [Link] ★ Best Paper Award (2nd place)★

•  M. D. Besbes, Y. Kessentini, H. Tabia, Multi-Stream deep networks for Vehicle Make and Model Recognition, 15-th International Conference on Computer Vision Theory and Applications (VISAPP'20), pp 413-419, Valetta, Malta, 2020. [Link]

2019

• N. Mansouri, S. Ammar, Y. Kessentini, Improving Person Re-identification by Combining Siamese Convolutional Neural Network and Re-ranking Process, 16-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS'19), Taipei, Taiwan, pp 1-8, 2019. [Link]

• A. Mdhaffar, F. Cherif, Y. Kessentini, M. Maalej, J. Ben Thabet, M. Maalej, M. Jmaiel, B. Freisleben, DL4DED: Deep Learning for Depressive Episode Detection on Mobile Devices, 17th International Conference On Smart Living and Public Health (ICOST'19), pp 109-121, 2019. [Link]

• M. Ghorbel, S. Ammar, Y. Kessentini, M. Jmaiel, Improving Person Re-identification by Background Subtraction using Two-stream Convolutional Networks,16th International Conference on Image Analysis and Recognition (ICIAR), pp 345-356, 2019. [Link]

• A. Cheikhrouhou, Y. Kessentini, S. Kanoun, Hybrid HMM/DNN System for Arabic Handwriting Keyword Spotting, 16th International Conference on Image Analysis and Recognition (ICIAR), pp 216-227, 2019. [Link]

• A. Cheikhrouhou, Y. Kessentini, S. Kanoun, HMM based keyword spotting system in printed/handwritten Arabic/Latin documents with identification stage, 16th International Conference on Image Analysis and Recognition (ICIAR), pp 309-320, 2019. [Link]

2018

• S. Khamekhem Jemni, Y. Kessentini, S. Kanoun, Offline Arabic Handwriting Recognition Using BLSTMs Combination. 13th international workshop on document analysis systems (DAS), pp 31-36, Vienna, Austria, 2018. [Link]

2016

• A. Naimi, Y. Kessentini, M. Hammami. Multi-nation and multi-norm License plates detection in real traffic surveillance environment using Deep Learning, International Conference on Neural Information Processing (ICONIP), pp 462-469, Kyoto, Japan, 2016. [Link]

• F. Chabchoub, Y. Kessentini, S. Kanoun, V. Eglin. SmartATID : A mobile captured Arabic Text Images Dataset for multi-purpose recognition tasks, 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 120-125, , Shenzhen, China, 2016. [Link]

• H. Khlif, S. Prum, Y. Kessentini, S. Kanoun, J.M. Ogier. Fusion of explicit segmentation based system and segmentation-free based system for on-line Arabic handwritten word recognition, 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 399-404, Shenzhen, China, 2016. [Link]

• S. Khamekhem Jemni, Y. Kessentini, S. Kanoun. Benchmarking Post-Processing Techniques for Offline Arabic Text Recognition System. 16th International Conference on Hybrid Intelligent Systems (HIS 2016), pp 267-277, vol 552. Springer. [Link]

• A. Cheikhrouhou, Z. Abdelhedi, Y. Kessentini. A HMM-Based Arabic/Latin Handwritten/Printed Identification System. 16th International Conference on Hybrid Intelligent Systems (HIS 2016), pp 298-307, vol 552. Springer. [Link]

2015

• Y. Kessentini, T. Paquet. Keyword spotting in handwritten documents based on a generic text line HMM and a SVM verification, International Conference on Document Analysis and Recognition (ICDAR 2015), pp. 41-45, Nancy, France, Aout, 2015. [Link]

2013

• Y. Kessentini, C. Chatelain, T. Paquet. Word Spotting and Regular Expression Detection in Handwritten Documents, International Conference on Document Analysis and Recognition (ICDAR 2013), pp. 516-520, Washington, USA, Aout, 2013. [Link]

2011

• Y. Kessentini, A. Guermazi, T. Paquet. An Optimized multi-stream decoding algorithm for handwritten word recognition, International Conference on Document Analysis and Recognition (ICDAR 2011), pp 192 - 196, Beijing, China, 2011. [Link]

• T. Burger, Y. Kessentini, T. Paquet. "Dempster-Shafer theory based rejection strategy for handwritten word recognition", International Conference on Document Analysis and Recognition (ICDAR 2011), pp 528 - 532, Beijing, China, September, 2011. [Link]

• Y. Kessentini, T. Burger, T. Paquet. Constructing dynamic frames of discernment in cases of large number of classes, The 11th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU 2011). W. Liu (Ed.), LNAI 6717, pp. 275--286. Springer, Heidelberg, Belfast, Northern Ireland, UK, July 2011. [Link]

• B. Besbes, S. Ammar, Y. Kessentini, A. Rogozan, A. Bensrhair, Evidential combination of SVM road obstacle classifiers in visible and far infrared images, in IEEE Intelligent Vehicles Symposium (IV'11). pp 1074 - 1079, 2011, Baden, Germany. [Link]

2010

• Y. Kessentini, T. Burger, T. Paquet. Evidential combination of multiple HMM classifiers for multi-script handwritting recognition. 13th international conference on Information processing and management of uncertainty (IPMU'10), vol 6178, pp 445-454, 2010. [Link]

• T. Burger, Y. Kessentini, T. Paquet. Dealing with precise and imprecise decisions with a Dempster-Shafer Theory based algorithm in the context of handwriting recognition . 12th International Conference on Frontiers in Handwriting Recognition (ICFHR'10), pp. 369-374, 2010, Kolkata, India.  [Link]

2005-2009

• Y. Kessentini, T. Paquet, A. Benhamadou. A Multi-Lingual Recognition System for Arabic and Latin Handwriting. 10th International Conference on Document Analysis and Recognition, ICDAR'2009, pp. 1196-1200, Barcelone, Espagne 2009. [Link]

• Y. Kessentini, T. Paquet, A. Benhamadou. Multi-Script Handwriting Recognition with N-Streams Low Level Features. International conference on pattern recognition ICPR. pp 1-4, Tampa, Floride 2008. [Link]

• Y. Kessentini, T. Paquet, A. Benhamadou, A Multi-Stream HMM-based Approach for Off-line Multi-Script Handwritten Word Recognition. 11th International Conference on Frontiers in Handwriting Recognition ICFHR 2008, vol 1, pp. 147-152, Montréal, Québec. [PDF] 

• Y. Kessentini, T. Paquet, A. Benhamadou. A Multi-stream Approach to Off-Line Handwritten Word Recognition. 9th International Conference on Document Analysis and Recognition, ICDAR’2007, Curitiba, Brazil, Vol. 1, pp. 317-321, 2007. [Link]

• S. Nicolas, Y. Kessentini, T. Paquet, L. Heutte. Handwritten document segmentation using hidden markov random fields. 8th International Conference on Document Analysis and Recognition ICDAR, Seoul, Korea, IEEE Proceedings, pp. 212-216, 2005. [Link]

Editorials & Book chapters

• Y. Kessentini, H.Laga, H. Tabia, Editorial for topical collections on emerging trends in artificial intelligence and machine learning, Neural Computing and Applications (NCAA), ISSN: 0941-0643 (Print) 1433-3058, August 2022. [Link] [Papers] 

• A.Bennour, Tolga Ensari,  Y. Kessentini, Sean Eom, Intelligent Systems and Pattern Recognition, Communications in Computer and Information Science, Springer Nature, Series ISSN 1865-0929 , 2022, ISBN 978-3-031-08277-1. [Link]  

• A. Cheddad, A.Bennour, Y. Kessentini, special section on topical collection on intelligent systems and pattern recognition, Pattern Recognition Letters (PRL), Volume 156, pp190-19, April 2022. [Link]

• A.Bennour, A. Cheddad, Y. Kessentini, Special Issue on Emerging trends in Artificial Intelligence and Machine Learning, International Journal of Computational Systems Engineering, Volume 6, n°5, pp 211-246, 2022. [Link]

• Djeddi, C., Kessentini, Y., Siddiqi, I., Jmaiel, M., Pattern Recognition and Artificial Intelligence, Communications in Computer and Information Science, Springer Nature, Series Volume 1322, 2021, ISBN 978-3-030-71804-6. [Link]

• Y. Kessentini, T. Paquet, A. Benhamadou. Multi-Stream Markov Models for Arabic Handwriting Recognition. Guide to OCR for Arabic Scripts, Chp. Part II: Recognition, pp. 335-350, Springer, London, UK, June 2012. ISBN 978-1-4471-4071-9. [Link]

French conferences

• M. Ghorbel, S. Ammar, Y. Kessentini, M. Jmaiel, A. Chaari, Système multi-flux pour la ré-identification de personnes : combinaison de caractéristiques globales et locales, Traitement et Analyse de l'Information Méthodes et Applications (TAIMA'2002), Hammamet, 2022. [Link]

• Y. Kessentini, T. Paquet, T. Burger. Comparaison des méthodes probabilistes et évidentielles de fusion de classifieurs pour la reconnaissance de mots manuscrits, Conférence Internationnale Francophone sur l'Ecrit et le Document (CIFED), Sousse, Tunisia, March 2010. [Link]

• Y. Kessentini, T. Paquet, A. Benhamadou. Combinaison d’Information pour la Reconnaissance de l’Ecriture Manuscrite Hors-Ligne. 16e congrès francophone de Reconnaissance des Formes et Intelligence Artificielle RFIA’2008, Amiens, France 2008. 

• Y. Kessentini, T. Paquet, A. Benhamadou. Combinaison de caractéristiques bas niveau à travers des modèles N-flux dans le cadre de la reconnaissance de l’écriture manuscrite multi-scripts. CIFED 2008, pp. 109-114, Rouen, France 2008. 

• Y. Kessentini, T. Paquet, A. Benhamadou. Modèles multi-flux pour la reconnaissance de mots manuscrits. 21e colloque sur le traitement du signal et des images GRETSI, Troyes’2007. 

HDR

Contributions au traitement automatique des images de documents et de scènes à l'ère de l'apprentissage profond. University of Sfax, May 2021  

PHD

Modèles de Markov multi-flux pour la reconnaissance de l’écriture manuscrite multi-scripts. University of Rouen May 2009.