—————————–<\/p>\n
Keynote speaker : Elisa FROMONT<\/strong><\/h4>\n![\"image](\"https:\/\/project.inria.fr\/sifed2022\/files\/2022\/06\/elisa_fromont-300x200.jpg\")
<\/a><\/p>\nSlides<\/a><\/p>\nTitle<\/em> : Explainable Time Series Classification<\/strong><\/p>\nAbstract<\/em> : I will introduce motivations about explainability in machine learning models and deep learning models as well as state-of-the-art methods. Then, I will present original works, especially on univariate or multivariate time series classification:<\/p>\n\n- Adversarial Regularization for Explainable-by-Design Time Series Classification – ICTAI 2020<\/li>\n
- A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers – IJCAI Workshop on Explainable Artificial Intelligence (XAI), 2020<\/li>\n
- XEM: An Explainable-by-Design Ensemble Method for Multivariate Time Series Classification, DAMI 2022<\/li>\n
- XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification, Mathematics<\/li>\n<\/ul>\n
Bio<\/em> : Elisa is a full professor at Universit\u00e9 de Rennes 1 France, since 2017 and a Junior member of the Institut Universitaire de France (2019-2024). Elisa works at IRISA research institute in the INRIA LACODAM (“Large Scale Collaborative Data Mining”) team. From 2008 until 2017, she was associate professor at Universit\u00e9 Jean Monnet in Saint-Etienne, France. She worked at the Hubert Curien research institute in the Data Intelligence team. Elisa received her Research Habilitation (HDR) in December 2015 from the University of Saint-Etienne. From 2006 until 2008, she was a postdoctoral researcher in the Machine Learning group of the Katholieke Universteit Leuven, Belgium. She received her PhD in December 2005 from Universit\u00e9 de Rennes 1.<\/p>\nResearch domains :<\/em><\/p>\n\n- Explainable AI<\/b> (interpretability of data mining\/machine learning models and explainable decisions)<\/li>\n
- Data mining for time series analysis<\/b> (including fraud and anomaly detection)<\/li>\n<\/ul>\n
—————————–<\/p>\n
Detailed program of sessions<\/h4>\nOral Session 1 (slides<\/a>)<\/h5>\n<td9h10-9h30<\/p>\n
\n\n\nTime<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n8h50-9h10<\/td>\n Handwritting Recognition using Multi-Hypothesis based Semi-Supervised Learning for adaptation to specific documents<\/td>\n Alexandre Chapin, Yann Soullard, Aur\u00e9lie Lema\u00eetre, Bertrand Couasnon (IRISA)<\/td>\n<\/tr>\n \n9h10-9h30<\/td>\n EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification<\/td>\n Souhail Bakkali, Zuheng Ming, Mickael Coustaty, Marcal Rusinol, Oriol Ramos Terrades (L3I)<\/td>\n<\/tr>\n \n9h30-9h50<\/td>\n EXO-POPP : Extraction d\u2019entit\u00e9s nomm\u00e9es dans des actes de mariage manuscrits<\/td>\n Thomas Constum, Pierrick Tranouez, Thierry Paquet (LITIS)<\/td>\n<\/tr>\n \n9h50-10h10<\/td>\n Localisation d\u2019une fraude dans des documents<\/td>\n Aur\u00e9lie Ling, Cuong van Kieu, Camille Kurtz, Nicole Vincent (LIPADE)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nOral Session 2 (slides<\/a>)<\/h5>\n
\n\n\nTime<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n10h30-10h50<\/td>\n D\u00e9tection et association des queues de bulles : cas des multi-bulles<\/td>\n Christophe Rigaud (L3I), Jean-Christophe Burie (L3i), Samuel Petit (Geo Comix)<\/td>\n<\/tr>\n \n10h50-11h10<\/td>\n Open Source Maif pour une IA transparente & Maitris\u00e9e<\/td>\n Laure Bonafous et S\u00e9bastien Bidault (MAIF)<\/td>\n<\/tr>\n \n11h10-11h30<\/td>\n Arkindex pour l’exp\u00e9rimentation en traitement de documents num\u00e9ris\u00e9s<\/td>\n M\u00e9lodie Boillet, Sol\u00e8ne Tarride et Christopher Kermorvant (TEKLIA)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nOral Session 3 (slides<\/a><\/h5>\n
\n\n\nTime<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n3h20-3h40<\/td>\n Toward Deep neural network for pen trajectory reconstruction from kinematic sensors<\/td>\n Imbert Florent, Wassim Swaileh, Yann Soullard, Romain Tavenard, Eric Anquetil (IRISA)<\/td>\n<\/tr>\n \n3h40-4h00<\/td>\n EyCon: Computational Approaches to the Circulation of photographs in late 19th-\/Early 20th-Century periodicals and beyond<\/td>\n Julien Schuh, Marina Giardinetti, Soumik Mallick et Daniel Foliard (LARCA)<\/td>\n<\/tr>\n \n4h00-4h20<\/td>\n Reconnaissance de texte dans les bandes dessin\u00e9es par Smartphone<\/td>\n Cl\u00e9ment Charrier, Fr\u00e9d\u00e9ric Daubignard (Entreprise ALGONA), R\u00e9my Leconge (Laboratoire PRISME), Fr\u00e9d\u00e9ric Rayar (Laboratoire LIFAT), Sylvie Treuillet (PRISME)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nSession Posters et d\u00e9monstrations – 1h15-2h<\/h5>\nPosters<\/h6>\n
\n\n\nTitle<\/th>\n Authors<\/th>\n Affiliation<\/th>\n<\/tr>\n \nLeveraging Domain Knowledge for Document Information Extraction<\/td>\n Arthur Hemmer<\/td>\n L3I<\/td>\n<\/tr>\n \nReconnaissance et segmentation de l’\u00e9criture manuscrite d’enfants<\/td>\n Simon Corbill\u00e9, \u00c9lisa Fromont, \u00c9ric Anquetil<\/td>\n IRISA<\/td>\n<\/tr>\n \nA comparative study for classification of French language corporate documents on imbalanced datasets<\/td>\n Tri-Cong Pham, Aur\u00e9lie Joseph, Muriel Visani, Nicolas Sidere, Mickael Coustaty<\/td>\n L3I<\/td>\n<\/tr>\n \nTransformers pour la reconnaissance de documents anciens<\/td>\n Killian Barrere, Yann Soullard, Aur\u00e9lie Lemaitre, Bertrand Co\u00fcasnon<\/td>\n IRISA<\/td>\n<\/tr>\n \nInformation Extraction from Administrative Documents<\/td>\n Dipendra Sharma Kafle<\/td>\n L3I<\/td>\n<\/tr>\n \nClassification of Untranscribed Handwritten Notarial Documents by Textual Contents<\/td>\n Jos\u00e9 Ramon Prieto Fontcuberta<\/td>\n PRHLT<\/td>\n<\/tr>\n \nD\u00e9tection de fraude de tickets de caisse en prenant en compte la s\u00e9mantique<\/td>\n Beatriz Mart\u00ednez Torn\u00e9s<\/td>\n L3I<\/td>\n<\/tr>\n \nTransformation digitale d’images de documents techniques d’ing\u00e9nierie et de plans industriels.<\/td>\n Mathieu Fran\u00e7ois<\/td>\n LIRIS<\/td>\n<\/tr>\n \nDocument Forgery Detection in the Context of Double JPEG Compression<\/td>\n Th\u00e9o Taburet, Kais Rouis, Micka\u00ebl Coustaty, Petra Gomez-Kr\u00e4mer, Nicolas Sid\u00e8re, Saddok K\u00e9bairi, Vincent Poulain d\u2019Andecy<\/td>\n L3I<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nDemonstrations (with or without poster)<\/h6>\n
\n\n\nTitle<\/th>\n Authors<\/th>\n Affiliation<\/th>\n<\/tr>\n \nGeo Comix Translator: a unique tool to speed-up translation process for comics, mangas and webtoons<\/td>\n Christophe Rigaud, Jean-Christophe Burie, Samuel Petit<\/td>\n L3I – Geo Comix<\/td>\n<\/tr>\n \nArkindex pour l’exp\u00e9rimentation en traitement de documents num\u00e9ris\u00e9s<\/td>\n M\u00e9lodie Boillet, Sol\u00e8ne Tarride et Christopher Kermorvant<\/td>\n TEKLIA<\/td>\n<\/tr>\n \nOpen Source Maif pour une IA transparente & Maitris\u00e9e<\/td>\n Laure Bonafous and S\u00e9bastien Bidault<\/td>\n MAIF<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/p>","protected":false},"excerpt":{"rendered":"
General Program Keynote Speaker Detailed sessions —————————– General program of the day \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 Booklet_Abstracts Time Program 8h15-8h45 Welcome coffee 8h45-8h50 Opening 8h50-10h10 Oral Session 1 10h10-10h30 Coffee break 10h30-11h30 Oral Session 2 11h30-11h45 Sponsors presentation 11h45-12h15 GRCE general meeting 12h15-1h15 Lunch 1h15-2h Posters and demonstrations\u2026<\/p>\n
![\"image](\"https:\/\/project.inria.fr\/sifed2022\/files\/2022\/06\/elisa_fromont.jpg\")
<\/a><\/p>\nSlides<\/a><\/p>\n Title<\/em> : Explainable Time Series Classification<\/strong><\/p>\n Abstract<\/em> : I will introduce motivations about explainability in machine learning models and deep learning models as well as state-of-the-art methods. Then, I will present original works, especially on univariate or multivariate time series classification:<\/p>\n Bio<\/em> : Elisa is a full professor at Universit\u00e9 de Rennes 1 France, since 2017 and a Junior member of the Institut Universitaire de France (2019-2024). Elisa works at IRISA research institute in the INRIA LACODAM (“Large Scale Collaborative Data Mining”) team. From 2008 until 2017, she was associate professor at Universit\u00e9 Jean Monnet in Saint-Etienne, France. She worked at the Hubert Curien research institute in the Data Intelligence team. Elisa received her Research Habilitation (HDR) in December 2015 from the University of Saint-Etienne. From 2006 until 2008, she was a postdoctoral researcher in the Machine Learning group of the Katholieke Universteit Leuven, Belgium. She received her PhD in December 2005 from Universit\u00e9 de Rennes 1.<\/p>\n Research domains :<\/em><\/p>\n —————————–<\/p>\n <td9h10-9h30<\/p>\n <\/p>","protected":false},"excerpt":{"rendered":" General Program Keynote Speaker Detailed sessions —————————– General program of the day \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 Booklet_Abstracts Time Program 8h15-8h45 Welcome coffee 8h45-8h50 Opening 8h50-10h10 Oral Session 1 10h10-10h30 Coffee break 10h30-11h30 Oral Session 2 11h30-11h45 Sponsors presentation 11h45-12h15 GRCE general meeting 12h15-1h15 Lunch 1h15-2h Posters and demonstrations\u2026<\/p>\n\n
\n
Detailed program of sessions<\/h4>\n
Oral Session 1 (slides<\/a>)<\/h5>\n
\n\n
\n Time<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n 8h50-9h10<\/td>\n Handwritting Recognition using Multi-Hypothesis based Semi-Supervised Learning for adaptation to specific documents<\/td>\n Alexandre Chapin, Yann Soullard, Aur\u00e9lie Lema\u00eetre, Bertrand Couasnon (IRISA)<\/td>\n<\/tr>\n \n 9h10-9h30<\/td>\n EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification<\/td>\n Souhail Bakkali, Zuheng Ming, Mickael Coustaty, Marcal Rusinol, Oriol Ramos Terrades (L3I)<\/td>\n<\/tr>\n \n 9h30-9h50<\/td>\n EXO-POPP : Extraction d\u2019entit\u00e9s nomm\u00e9es dans des actes de mariage manuscrits<\/td>\n Thomas Constum, Pierrick Tranouez, Thierry Paquet (LITIS)<\/td>\n<\/tr>\n \n 9h50-10h10<\/td>\n Localisation d\u2019une fraude dans des documents<\/td>\n Aur\u00e9lie Ling, Cuong van Kieu, Camille Kurtz, Nicole Vincent (LIPADE)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n Oral Session 2 (slides<\/a>)<\/h5>\n
\n\n
\n Time<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n 10h30-10h50<\/td>\n D\u00e9tection et association des queues de bulles : cas des multi-bulles<\/td>\n Christophe Rigaud (L3I), Jean-Christophe Burie (L3i), Samuel Petit (Geo Comix)<\/td>\n<\/tr>\n \n 10h50-11h10<\/td>\n Open Source Maif pour une IA transparente & Maitris\u00e9e<\/td>\n Laure Bonafous et S\u00e9bastien Bidault (MAIF)<\/td>\n<\/tr>\n \n 11h10-11h30<\/td>\n Arkindex pour l’exp\u00e9rimentation en traitement de documents num\u00e9ris\u00e9s<\/td>\n M\u00e9lodie Boillet, Sol\u00e8ne Tarride et Christopher Kermorvant (TEKLIA)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n Oral Session 3 (slides<\/a><\/h5>\n
\n\n
\n Time<\/th>\n Title<\/th>\n Authors<\/th>\n<\/tr>\n \n 3h20-3h40<\/td>\n Toward Deep neural network for pen trajectory reconstruction from kinematic sensors<\/td>\n Imbert Florent, Wassim Swaileh, Yann Soullard, Romain Tavenard, Eric Anquetil (IRISA)<\/td>\n<\/tr>\n \n 3h40-4h00<\/td>\n EyCon: Computational Approaches to the Circulation of photographs in late 19th-\/Early 20th-Century periodicals and beyond<\/td>\n Julien Schuh, Marina Giardinetti, Soumik Mallick et Daniel Foliard (LARCA)<\/td>\n<\/tr>\n \n 4h00-4h20<\/td>\n Reconnaissance de texte dans les bandes dessin\u00e9es par Smartphone<\/td>\n Cl\u00e9ment Charrier, Fr\u00e9d\u00e9ric Daubignard (Entreprise ALGONA), R\u00e9my Leconge (Laboratoire PRISME), Fr\u00e9d\u00e9ric Rayar (Laboratoire LIFAT), Sylvie Treuillet (PRISME)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n Session Posters et d\u00e9monstrations – 1h15-2h<\/h5>\n
Posters<\/h6>\n
\n\n
\n Title<\/th>\n Authors<\/th>\n Affiliation<\/th>\n<\/tr>\n \n Leveraging Domain Knowledge for Document Information Extraction<\/td>\n Arthur Hemmer<\/td>\n L3I<\/td>\n<\/tr>\n \n Reconnaissance et segmentation de l’\u00e9criture manuscrite d’enfants<\/td>\n Simon Corbill\u00e9, \u00c9lisa Fromont, \u00c9ric Anquetil<\/td>\n IRISA<\/td>\n<\/tr>\n \n A comparative study for classification of French language corporate documents on imbalanced datasets<\/td>\n Tri-Cong Pham, Aur\u00e9lie Joseph, Muriel Visani, Nicolas Sidere, Mickael Coustaty<\/td>\n L3I<\/td>\n<\/tr>\n \n Transformers pour la reconnaissance de documents anciens<\/td>\n Killian Barrere, Yann Soullard, Aur\u00e9lie Lemaitre, Bertrand Co\u00fcasnon<\/td>\n IRISA<\/td>\n<\/tr>\n \n Information Extraction from Administrative Documents<\/td>\n Dipendra Sharma Kafle<\/td>\n L3I<\/td>\n<\/tr>\n \n Classification of Untranscribed Handwritten Notarial Documents by Textual Contents<\/td>\n Jos\u00e9 Ramon Prieto Fontcuberta<\/td>\n PRHLT<\/td>\n<\/tr>\n \n D\u00e9tection de fraude de tickets de caisse en prenant en compte la s\u00e9mantique<\/td>\n Beatriz Mart\u00ednez Torn\u00e9s<\/td>\n L3I<\/td>\n<\/tr>\n \n Transformation digitale d’images de documents techniques d’ing\u00e9nierie et de plans industriels.<\/td>\n Mathieu Fran\u00e7ois<\/td>\n LIRIS<\/td>\n<\/tr>\n \n Document Forgery Detection in the Context of Double JPEG Compression<\/td>\n Th\u00e9o Taburet, Kais Rouis, Micka\u00ebl Coustaty, Petra Gomez-Kr\u00e4mer, Nicolas Sid\u00e8re, Saddok K\u00e9bairi, Vincent Poulain d\u2019Andecy<\/td>\n L3I<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n Demonstrations (with or without poster)<\/h6>\n
\n\n
\n Title<\/th>\n Authors<\/th>\n Affiliation<\/th>\n<\/tr>\n \n Geo Comix Translator: a unique tool to speed-up translation process for comics, mangas and webtoons<\/td>\n Christophe Rigaud, Jean-Christophe Burie, Samuel Petit<\/td>\n L3I – Geo Comix<\/td>\n<\/tr>\n \n Arkindex pour l’exp\u00e9rimentation en traitement de documents num\u00e9ris\u00e9s<\/td>\n M\u00e9lodie Boillet, Sol\u00e8ne Tarride et Christopher Kermorvant<\/td>\n TEKLIA<\/td>\n<\/tr>\n \n Open Source Maif pour une IA transparente & Maitris\u00e9e<\/td>\n Laure Bonafous and S\u00e9bastien Bidault<\/td>\n MAIF<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n