- Vision and Language Understanding
- Multimodal Information Understanding
- Multimodal Conversational AI
- +۵ مورد دیگر
João Magalhães is a Full Professor in the Department of Computer Science at the Faculty of Science and Technology, Universidade NOVA de Lisboa, Portugal. He serves as Group Coordinator of the Multimodal Systems Group at the NOVA Laboratory for Informatics and Computer Science and leads the NOVASearch research group at FCT/UNL. His research focuses on vision and language information understanding, with particular emphasis on multimodal information understanding, multimodal conversational AI, multimedia search and summarization, temporal and memory models, and social media information quality. His work spans both theoretical foundations and practical applications across web, social media, and clinical domains. Analysis of his recent publications reveals a strong trajectory in multimodal conversational AI systems, with increasing sophistication in handling both voice and visual inputs. His research has evolved from foundational work in cross-modal embeddings to advanced large language models for dual-goal conversational settings, demonstrating consistent innovation in the field of multimodal understanding. 1st prize winner of the second Alexa TaskBot Challenge (2023) Award-winning solution in the Alexa TaskBot Challenge (2022) Best paper award at the Portuguese NLP conference (PROPOR) (2020) Best paper nominations at ACM conferences (2018) Professor Magalhães has advised numerous graduate students through the NOVASearch group and has secured substantial research funding through projects including Amazon Alexa TaskBot Challenge (2021-2023), iFetch (2020-2023), SmartyFlow (2017-2020), COGNITUS (2016-2019), GoLocal (2016-2020), QSearch (2012-2015), ImTV (2010-2013), and CS4SE (2010-2013). He actively serves the research community as ACM Multimedia 2026 Program Committee Chair and has held leadership roles in numerous conferences including ACM Multimedia 2022 General Chair and ECIR2020 General Chair. He leads the Multimodal Systems Group within the NOVA Laboratory for Informatics and Computer Science, where his team develops cutting-edge solutions for multimodal understanding with applications in conversational AI, multimedia search, and social media analysis.










