João Magalhães

Full Professor

Multimodal Systems

Country: Portugal

Affiliation: Universidade Nova de Lisboa



João Magalhães (PhD, Imperial College London, UK, 2008) is a Full Professor at the Dep. of Computer Science at Universidade NOVA de Lisboa. He is the coordinator of the Multimodal Systems Group of the NOVA LINCS research center (NOVA Laboratory for Computer Science and Informatics), composed of 20 senior researchers working in the area of HCI, CV, NLP, IR, DL and their applications to real-world problems. Before joining Universidade NOVA de Lisboa in 2009, he was a Research Assistant at The University of Sheffield. He researches AI algorithms that aim to advance vision and language understanding, in particular: foundational vision and language models, multimedia search, multimodal conversational AI, and multimodal temporal models. He is passionate about the generalization of his vision and language research to different real-world domains.Throughout his career he has coordinated and participated in multidisciplinary research projects, includingImTV, a UTAustin|Portugal project, COGNITUS, an H2020 project led by the BBC, GoLocal a CMU|Portugal project, iFetch a Portugal|CMU project led by Farfertch, Alexa Taskbot a research challenge sponsored by Amazon Science and GenerativeVidWiz a project sponsored by Google Research. He has been an deeply involved in the organization of international conferences in positions trust, with particular emphasis to the positions of General Chair of ACM Multimedia 2022 and ECIR 2020, and PC Chair forACM Multimedia 2026. These top-level roles are the result of a coherent track-record of community service for different top-level conferences, e.g., Authors Advocate for ACM Multimedia 2024, PC member for ACM SIGIR, ECIR, ACM Multimedia, ACM ICMR, ACM CIKM, and ACM WSDM, Tutorial Chair for IEEE ICME 2020, Publicity Chair for the ACM ICMR 2014 and Demo Chair for ECIR 2015. He is currently member of the Steering Committee of ACM Multimedia, member of the Steering Committee of the European Summer School in Information Retrieval and Associate Editor of ACM Trans. on MultimediaComputing, Communications, and Applications. Previously, he was member of the Steering Committee of theSpecial Group in Information Retrieval (2019-2021) of the British Computer Science. From 1997 to 2003 he worked in the private sector, where he made contributions to the ISO MPEG Technical Committee, in particular to the MPEG-7 standard on “Multimedia content description interface” and MPEG-21 standard which defines a “open framework for end-to-end multimedia creation, delivery and consumption”. Both contributions were aligned with his research in content-based multimedia retrieval. The work of his group work has been awarded or nominated for several awards and distinctions: in 2023 and 2022 his group was awarded the 1st place and 2nd place respectively in the Amazon Science Alexa Challenge Taskbot, a conversational AI challenge to incorporate multimodal (voice and vision) user data, in 2020 a best paper award at NLP conference for Portuguese (PROPOR), in 2018 two nominations for best paper at ACM Conf. on the Theory of Information Retrieval and ACM Conf. in Multimedia Retrieval, best student paper at Advances in Computer Entertainment 2015, best paper award at ACM Conf. in Image and Video Retrieval 2007.