From Perception to Action: Multimodal Embodied AI Seminar

Seminar: Prof. Winston Hsu (National Taiwan University)
Lunedì 16 Giugno – ore 11:30 – Aula 120 Centro
Didattico Morgagni, V.le Morgagni 40-44 Firenze

“From Perception to Action: Multimodal Embodied AI” Seminar: Prof. Winston Hsu (National Taiwan University)
Lunedì 16 Giugno – ore 11:30 – Aula 120 Centro Didattico Morgagni, V.le Morgagni 40-44

Abstract: In this talk, we will showcase a series of research works bridging “perception” and “action,” demonstrating advanced scenarios supporting robotics and automotive applications while incorporating human-in-the-loop methodologies. We will envision future possibilities for multimodal embodied AI and emphasize the importance of efficiency and sustainability in cloud- edge-hybrid inference systems.

Bio: Dr. Winston Hsu is a Professor at National Taiwan University. Previously (2021-2024), he served as the CTO and Vice President at MobileDrive, a joint venture between Foxconn and Stellantis focused on advancing digital cockpit and ADAS in HPC-based solutions. He earned his Ph.D. from Columbia University, New York, in 2007. Dr. Hsu is an active researcher in computer vision and machine intelligence, providing AI strategy consulting to several leading Taiwan-based ICT companies. He is the Founding Director of the NVIDIA AI Lab at NTU, the first NVIDIA AI Lab in Asia. Dr. Hsu was a visiting scientist at Microsoft Research Redmond (2014) and the IBM T.J. Watson Research Center (2016). Additionally, he co-founded thingnario, an AI/IoT startup specializing in renewable energy solutions. Earlier in his career, he was a founding engineer and R&D manager at CyberLink Corp.

ACM Multimedia 2015

ACM Multimedia 2015

Tutorial, short paper and four demos

Prof Tat-Seng Chua

Modelling of Micro Videos for Visual Analytics

Lecture by Prof. Tat-Seng Chuat at MICC

Most cited researchers

Prof Alberto Del Bimbo and Prof. Andrew D. Bagdanov

Wolmer Bigi, Claudio Baecchi, Alberto Del Bimbo, Automatic Interest Recognition from Posture and Behaviour

ACM MM 2020 Paper

Interest Recognition from Posture and Behaviour