BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2// METHOD:PUBLISH X-WR-CALNAME;VALUE=TEXT:Eventi DIAG BEGIN:VTIMEZONE TZID:Europe/Paris BEGIN:STANDARD DTSTART:20221030T030000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD BEGIN:DAYLIGHT DTSTART:20230326T020000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:calendar.25669.field_data.0@www.ugovricerca.uniroma1.it DTSTAMP:20260407T183615Z CREATED:20230316T160522Z DESCRIPTION:Care colleghe e colleghi\,con la presente vi informo che in ott emperanza ai requisiti previsti dalla procedura valutativa per n.1 posto d i Ricercatore a tempo determinato tipologia A - SC 09/H1 SSD ING-INF/05 - Dipartimento di Ingegneria Informatica Automatica e Gestionale 'A. Ruberti '\, Codice Bando 2023RTDAPNRR126 \, pubblicato su Gazzetta Ufficiale N. 5  del 20.01.2023\, si terrà Lunedi' 20 Marzo alle ore 14:00 in aula magna il  seminario di Giovanni Trappolini che illustrerà le sue attività di ricerc a svolte e in corso di svolgimento. Il seminario sarà anche trasmesso in m odalità telematica su Zoom. Per partecipare da remoto connettersi all'indi rizzo seguente:https://uniroma1.zoom.us/j/89155884158?pwd=VngyRUJzanhEc1Jo eElycTRtN2QrUT09Meeting ID: 891 5588 4158Passcode: 921785Titolo: Multimoda l Neural DatabasesAbstract:The rise in loosely-structured data available t hrough text\, images\, and other modalities has called for new ways of que rying them. Multimedia Information Retrieval has filled this gap and has w itnessed exciting progress in recent years. Tasks such as search and retri eval of extensive multimedia archives have undergone massive performance i mprovements\, driven to a large extent by recent developments in multimoda l deep learning. However\, methods in this field remain limited in the kin ds of queries they support and\, in particular\, their inability to answer database-like queries.In this talk\, we will provide an overview of the c onsolidated 'historical' advances in the field of Neural Databases. We the n proceed to explore a new framework\, that of Multimodal Neural Databases (MMNDBs). MMNDBs can answer complex database-like queries that involve re asoning over different input modalities\, such as text and images\, at sca le. MMNDBs is the first architecture able to overcome the limitations of b oth MMIR and vanilla NDB. We compare it with several baselines\, showing t he limitations of the current state of the art. Preliminary results shown by these techniques show the potential of these new techniques to process unstructured data coming from different modalities\, paving the way for fu ture research in the area.Short bio:Giovanni Trappolini is a post-doctoral researcher at the Department of Computer Engineering of the Sapienza Univ ersity of Rome\, where he works as a member of the RSTLess Research Group led by Professor Fabrizio Silvestri focusing on  multimodal deep learning. He received his PhD in Machine Learning under the supervision of Emanuele Rodolà\, with a thesis on geometric deep learning. In particular\, during his doctoral studies\, he developed novel algorithms for geometric deep l earning\, a subfield of machine learning that focuses on learning from non -Euclidean data such as graphs and manifolds. His current research activit ies focus on applying deep learning techniques to multimodal data\, with t he aim of developing models that can effectively process and integrate inf ormation from different sources such as text\, images\, and audio. He has published several papers in top-tier conferences and journals\, including NeurIPS and ECCV.  DTSTART;TZID=Europe/Paris:20230320T140000 DTEND;TZID=Europe/Paris:20230320T150000 LAST-MODIFIED:20230316T161827Z LOCATION:Aula Magna DIAG SUMMARY:Seminario pubblico di Giovanni Trappolini (Procedura valutativa per n.1 posto di Ricercatore a tempo determinato tipologia A - SC 09/H1 SSD I NG-INF/05) - Giovanni Trappolini URL;TYPE=URI:http://www.ugovricerca.uniroma1.it/node/25669 END:VEVENT END:VCALENDAR