Gabriella Pasi (University of Milano-Bicocca)
Title: On the issue of aggregation in Information Retrieval
Bio: Gabriella Pasi is Full Professor at the Department of Informatics, Systems and Communication, at the University of Milano Bicocca, Milano, Italy; within DISCo she leads the Information Retrieval Lab. Her main research activities are related to Information Retrieval and Information Filtering. In recent years she has addressed the issues of contextual search and user modelling. She is also conducting research activities related to the analysis of user generated content on social media. She has published more than 200 papers on International Journals and Books, and on the Proceedings of International Conferences. She is involved in several activities for the evaluation of research; in particular, she was appointed as an expert of the Computer Science panel for the Starting Grants (till 2011), and Consolidator Grants (2012) of the Programme Ideas at the European Research Council. Since 2013 she is the President of the European Society for Fuzzy Logic and Technologies (EUSFLAT). She is a member of the Editorial Board of several international journals, and she has delivered several keynote talks/plenary lectures at international conferences related to her research interests. She has participated to the organization of several International events, in both roles of organization and program chair.
Benjamin Piwowarski (University Pierre et Marie Curie)
Title: Texte et Représentation en Recherche d’Information
Bio: Benjamin Piwowarski est un chargé de recherche 1ère classe du CNRS au LIP6 (UPMC). Son domaine de recherche est celui de l'accès à l'information et de l'apprentissage statistique appliqué, en particulier l’apprentissage de représentations. Il a travaillé sur la recherche d'information XML (thèse 1999-2003), sur les bases de données XML (post-doctorat 2004-06 à l'université du Chili), sur l'analyse des interactions entre un utilisateur et un moteur de recherche (Yahoo! 2006-08) et sur l'application du formalisme mathématique de la physique quantique aux modèles d'accès à l'information (2008-11). Ses intérêts actuels portent sur (l’apprentissage de) représentation des données textuelles de graphes. Il a a été fortement impliqué dans l’initiative INEX (2004-07), et a organisé un workshop (IRGM’07), deux tutoriels (ECIR 2012 et ICTIR 2013), et a participé l’organisation de CORIA 2015
Mario Vento (University of Salerno)
Title: About the use of graphs in Pattern Recognition
Abstract: The talk presents an overview of how graphs have been used in Pattern Recognition; their use is strongly suggested in all those cases in which the objects of interest are represented by means of parts suitably connected with each other, so as to arrive to a description in terms of a relational graph.
The overview is aimed at reveal the rationale inspiring the papers published in these years, so as to roughly classify them. Despite the extent of scientific production in this field, it is possible to identify three historical periods, each having its own connotation common to most of the corresponding papers, which are called here as the pure, the impure and extreme periods.
The use of a graph-based pattern representation induces the need to formulate the main operations required in Pattern Recognition in terms of operations on graphs: classification, usually intended as the comparison between an object and a set of prototypes, and learning, which is the process for obtaining a model of a class starting from a set of known samples, are among the key issues that must be addressed using graph-based techniques.
Starting from the way in which these basic operations are defined and carried out it is possible to identify the above mentioned periods and the talk is focused on the most relevant techniques proposed along these years, so as to give the audience an overview of the field.
Bio: Mario Vento is a fellow scientist of the International Association Pattern Recognition (IAPR). Currently he is Full Professor of Computer Science and Artificial Intelligence at the University of Salerno (Italy), where he is the coordinator of the Artificial Vision Lab. From 2002 to 2006 he served as chairman of IAPR Technical Committee TC15 on ”Graph Based Representation in Pattern Recognition”, and from 2003 as associate editor of the ”Electronic Letters on Computer Vision and Image Analysis”. His research interests fall in the areas of Artificial Intelligence, Image Analysis, Pattern Recognition, Machine Learning and Computer Vision. More specifically, his research activity covered Real time Video analysis and interpretation for traffic monitoring and video surveillance applications, Classification Techniques, either Statistical, Syntactic and Structural, Exact and Inexact Graph Matching, Multi-Expert Classification and Learning Methodologies for Structural Descriptions. He authored over 170 research papers in International Journals and Conference Proceedings and serves as referee for many relevant journals in the field of Pattern Recognition and Machine Intelligence.