DEAR ICMI COMMUNITY,
We are thrilled to welcome you in-person in Napoli, Italy.
The 28th International Conference on Multimodal Interaction (ICMI 2026) will be held in Napoli on 5-9 October 2026.
ICMI is the premier international forum that brings together multimodal artificial intelligence (AI) and social interaction research. Multimodal AI encompasses technical challenges in machine learning and computational modeling, such as representations, fusion, data, and systems. The study of social interactions encompasses both human-human interactions and human-computer interactions. A unique aspect of ICMI is its multidisciplinary nature, which values scientific discoveries and technical modeling achievements equally, with an eye toward impactful applications for the good of people and society.
We are keen to showcase novel input and output modalities and interactions to the ICMI community. ICMI 2026 will feature keynote speakers, technical full and short papers (including oral and poster presentations), demonstrations, exhibits, doctoral spotlight papers, and late-breaking papers. The conference will also feature workshops and grand challenges. The proceedings of all ICMI 2026 papers, including Long and Short Papers, will be published by ACM as part of their series of International Conference Proceedings and Digital Library, and the adjunct proceedings will feature the workshop papers.
The main conference days will be on 6-8 Oct 2026, while workshops/tutorials and grand challenges will be held on 5 or 9 Oct 2026.
News and Updates
[10/12/2025] Call for Workshops posted
[16/12/2026] Grand Challenge deadline extended
The proposed theme for the 2026 ICMI conference is “Context and Cultural Awareness for Multimodal Interaction.” Multimodal interaction holds particular significance in the Italian cultural and social context due to the rich and expressive communication styles deeply rooted in Italian traditions. Italians are renowned for their use of gestures and nuanced cultural expressions, which often complement or even substitute verbal communication. For a multimodal system to be deployed effectively, it must integrate this cultural background, taking into account contextual information and aligning with established communication norms.
In particular, Naples holds another significant distinction: the origins of Neapolitan song and music can be traced back to ancient myth, specifically to the enchanting and seductive song of the siren Partenope. According to the legend, Partenope, a mythical figure with a captivating voice, sang so beautifully that her melodies echoed across the seas. From the Megaride rock, where she is said to have perished, the siren’s spirit is believed to have given birth to the city of Naples, imbuing it with a unique cultural identity. This blend of myth and music has endured through the centuries, with Neapolitan songs continuing to thrive as a reflection of the city’s soul—passionate, heartfelt, and timeless. This deep connection between the myth of Parthenope and the music of Naples is not only a testament to the city’s rich cultural heritage but also exemplifies how art, in its various forms, can transcend time and space.
This year’s theme seeks to explore how systems and technologies can leverage contextual and cultural understanding enhancing the generation and recognition of multimodal interactions. It also aims to promote technologies that support natural, intuitive, and culturally aware interactions across diverse contexts. This exploration touches on several critical challenges for the community, including Data Representation to ensure that diverse cultural contexts are represented in datasets used for training multimodal systems, Bias Mitigation to address algorithmic biases that may arise from cultural and contextual differences, and Ethics and Privacy for balancing the collection of contextual and cultural data with user consent and data security.
