Authors: Werner Bailer, Georg Thallinger, Jenny Benois-Pineau
Affiliations: JOANNEUM RESEARCH, Université Bordeaux
The 19th International Conference on Content-based Multimedia Indexing (CBMI) took place as a hybrid conference in Graz, Austria, from September 14-16, 2022, organized by JOANNEUM RESEARCH and supported by SIGMM. After the 2020 edition was postponed and held as a fully online conference in 2021, this was an important step back to a physical conference. Probably still as an effect of the COVID pandemic, the event was a bit smaller than in previous years, with around 50 participants from 18 countries (13 European countries, the rest from Asia and North America). About 60% were attending on-site, the other via web conference.
The conference program included two keynotes. The opening keynote by Miriam Redi from Wikimedia analysed the role of multimedia assets in a free knowledge ecosystem such as the one around Wikipedia. The closing keynote by Efstratios Gavves from the University of Amsterdam showcased recent progress in machine learning of dynamic information and causality in a diverse range of application domains and highlighted open research challenges.
With the aim to increase the interaction between the scientific community and the users of multimedia indexing technologies, a panel session titled “Multimedia Indexing and Retrieval Challenges in Media Archives” was organised. The panel featured four distinguished experts from the audiovisual archive domain. Brecht Declerq from meemoo, the Flemish Institute for Archive, is currently the president of FIAT/IFTA, the International Association of TV Archives. Richard Wright started as a researcher in speech processing before he became a renowned expert in digital preservation, setting up a series of successful European projects in the area. Johan Oomen manages the department for Research and Heritage at Beeld en Geluid, the Netherlands Institute of Sound and Vision. Christoph Bauer is an expert from the Multimedia Archive of the Austrian Broadcasting Corporation ORF and consults archives of the Western Balkan countries on digitisation and preservation topics. The panel tried to analyse why only a small part of research outputs makes it into productive use at archives and identified research challenges such as the need for more semantic and contextualised content descriptions, the ability to easily control the amount vs. accuracy of generated metadata and the need for novel paradigms to interact with multimedia collections beyond the textual search box. At the same time, archives face the challenge of dealing with much richer metadata, but without the quality guarantees known from manually documented content.
In addition to five regular paper sessions (presenting 16 papers in total), the 2022 conference followed the tradition of previous editions of special sessions addressing the use of multimedia indexing in specific application areas or specific settings. This year the special sessions (nine papers in total) covered multimedia in clinical applications and for the protection against natural disasters as well as machine learning from multimedia in cases where data is scarce. The program was completed with a poster & demo session, featuring seven posters and two demos.
The best paper and the best student paper of the conference were each awarded EUR 500, generously sponsored by SIGMM. The selection committee quickly found consensus to award the best paper award to Maria Eirini Pegia, Anastasia Moumtzidou, Ilias Gialampoukidis, Björn Þór Jónsson, Stefanos Vrochidis and Ioannis Kompatsiaris for their paper “BiasUNet: Learning Change Detection over Sentinel-2 Image Pairs”, and the best student paper award to Sara Sarto, Marcella Cornia, Lorenzo Baraldi and Rita Cucchiara for their paper “Retrieval-Augmented Transformer for Image Captioning”. The authors of the best papers were invited to submit an extended version to the IEEE Transactions on Multimedia journal.
Handling the hybrid setting
As a platform for the online part of the conference, an online event using GoTo Webinar has been created. The aim was still to have all presentations and Q&A live, however, speakers were asked to provide a backup video of their talk (which was only used in one case). The poster and demo session was a particular challenge in the hybrid setting. In order to allow all participants to see the contributions in the best setting, all contributions were both presented as printed posters on-site and as a short video online. After discussions took place on-site in front of the posters and demos, a Q&A session connecting the conference room and the remote presenters took place to enable also discussions with the online presenters.
Getting back to at least hybrid conferences also means having the long missed opportunities to discuss and exchange with both well-known colleagues and first-time attendees during coffee breaks and over lunch and dinner. In addition to a conference dinner on the second evening, the government of the state of Styria, of which Graz is the capital, hosted a reception for the participants in the beautiful setting of the historic Orangerie in the gardens of Graz castle. The participants had the opportunity to enjoy a guided tour through Graz on their way to the reception.
A special event was the Music meets Science concert, with the support of SIGMM. This is already the fourth concert which has been presented in the framework of the CBMI conference (2007, 2018, 2021, 2022). After a long conference day, the participants could enjoy works by Schubert and Haydn, Austrian composers which gave an aspect of local Austrian culture to the event. Reflecting the international spirit of CBMI, the concert was given by a trio of very talented young musicians with international careers from three different countries. We thank SIGMM for its support which made this cultural event happen.
The next edition of CBMI will be organised in September 2023 in Orleans, France. While it is likely that the hybrid setting is here to stay for the near future, we hope that the share of participants on site will move back towards the pre-pandemic level.