DLS Talk by Elisabeth André, University of Augsburg - Feb. 8, 2024 скачать в хорошем качестве

DLS Talk by Elisabeth André, University of Augsburg - Feb. 8, 2024

Title: Socio-Affective Signals as Facilitators of Human-Human and Human-Agent Interaction Abstract: Social interactions profoundly shape our human life. This presentation explores the potential of imbuing machines with socially-aware interfaces, creating pathways for more natural and intuitive interactions between humans and technology. I will introduce computational methodologies aimed at instilling socially interactive behaviors in robots and virtual characters, covering the following three essential components: Social Perception, Socially-Aware Behavior Synthesis, and Learning Socially-Aware Behaviors. In addition to exploring analytical methods rooted in cognitive and social science theories, I will delve into data-driven approaches that empower artificial agents to acquire socially interactive behaviors from observations of human-human interactions or from real-life engagements with human interlocutors. I will also discuss the potential and challenges associated with neural behavior generation techniques, which offer the promise of elevating virtual agents and social robots to new levels of human-likeness. Particularly, the talk will address conditional motion synthesis with transformer models and diffusion models tailored for human behavior imitation and generation. Throughout the presentation, I will provide practical insights and examples derived from our work across various application domains. I will also demonstrate how analytic and generative AI may be used to enrich human-human interactions of people with special needs. Bio: Elisabeth André is a full professor of Computer Science and Founding Chair of Human-Centered Artificial Intelligence at Augsburg University in Germany. She has a long track record in multimodal human-machine interaction, embodied conversational agents, social robotics, affective computing and social signal processing. Her work has won many awards including the Gottfried Wilhelm Leibnitz Prize 2021 of the German Research Foundation (DFG), with 2.5 Mio € the highest endowed German research award. In 2017, she was elected to the CHI Academy, an honorary group of leaders in the field of Human-Computer Interaction. To honor her achievements in bringing Artificial Intelligence techniques to Human-Computer Interaction, she was awarded a EurAI fellowship (European Coordinating Committee for Artificial Intelligence) in 2013. In 2019, she was named one of the 10 most influential figures in the history of AI in Germany by National Society for Informatics (GI). Elisabeth André is a member of the Bavarian Academy of Sciences and Humanities, the Academy of Europe, the Asia-Pacific Artificial Intelligence Association and the German Academy of Sciences Leopoldina. For more information, see: www.cs.ubc.ca/dls