Colloquium on Immersive Media: Human Behavior Understanding: from Visible to Invisible, then Generative
Title: Human Behavior Understanding: from Visible to Invisible, then Generative
Speaker: Dr. Jianquan Liu, Director & Senior Principal Researcher, NEC Corporation, Japan
Date & Time: November 13 (Thu), 2025, 16:00 – 17:00
Abstract: In this talk, Dr. Liu will present an industrial-level framework for sensing and understanding human behavior from multiple aspects. This integrative system supports an analysis of behavior derived from video footages via classic visible devices, such as fixed and 360-degree cameras, as well as innovative "invisible" tech like microwave sensors. The framework further enables the creation of informative reports and short video clips generated from large language models (LLMs). This presentation will highlight various research milestones within our framework, which have significantly contributed to both the academia and industries. Our framework is composed of a series of cutting-edge technologies that sense the data generated in the real world, transform them into readable, visible, and modellable digital forms, and finally analyze these digital data to understand the human behavior. This framework includes sensing techniques via traditional cameras [MM'16, SIGGRAPH'16], 360-degree cameras [MM'19, WACV'20, ICIP'21], and microwave sensors [MM'20]. Further, it includes behavior analysis in the realms of action recognition, object tracking, human and object interactions, scene recognition, and behavioral pattern analysis [ICMR'18], making the extraction, visualization, and summarization feasible [MM'22, NarSUM'23, ICMR'24], all to thoroughly interpret human behavior. These works will be introduced in the way of a general overview with interactive technical demos and interesting insights, for human behavior sensing and understanding by adopting effective processing techniques and designing efficient algorithms. Finally, Dr. Liu will share some challenges and directions for further understanding in the Era of Generative AI.
Biosketch: Jianquan Liu is currently a Director and Senior Principal Researcher at NEC Corporation, working on the topics of multimedia data processing. He is also a Visiting Professor at Nagoya University and an Adjunct Professor at Hosei University, Japan. Prior to NEC, he was with Tencent Inc. from 2005 to 2006. He has published 80+ papers at major international/domestic conferences and journals and filed 100+ PCT patents. He also successfully transformed these technological contributions into commercial products in the industry. For his industry contributions, Dr. Liu has received the DBSJ Young Researcher’s Achievement and Contribution Award 2024, the IEICE Achievement Award 2023, the ITE Niwa & Takayanagi Achievement Award 2023, the 69th Electrical Science and Engineering Promotion Award, and the Minister of Education, Culture, Sports, Science and Technology (MEXT) Award in 2021, the KANTO Invention and Innovation Award 2021, the IPSJ Research and Engineering Award 2020 and the IPSJ Industrial Achievement Award 2018. Currently, Dr. Liu is/was serving as a Member-at-Large of IEEE SPS Industry Board (2025-2026), the Industry Co-chair of IEEE ICIP 2023, 2025 and ACM MM 2023, 2024, 2025; the General Co-chair of IEEE MIPR 2021; the PC Co-chair of IEEE IRI 2022, ICME 2020, AIVR 2019, BigMM 2019, ISM 2018, ICSC 2018, etc. He is a senior member of ACM, IEEE, and IPSJ, and a member of IEICE, APSIPA and DBSJ, and an associate editor of IEEE TMM (2021-2024), ACM TOMM (2022-), EURASIP JIVP (2023-), IEEE MultiMedia Magazine (2019-2022), ITE Transaction on Media Technology and Applications (2021-), APSIPA Transactions on Signal and Information Processing (2022-), and the Journal of Information Processing (2017-2021). Dr. Liu received the M.E. and Ph.D. degrees from the University of Tsukuba, Japan.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- 25-2, SUNGKYUNKWAN-RO
- JONGNO-GU
- Seoul, Seoul
- South Korea 03063
- Building: International Hall
- Room Number: 9B113
- Click here for Map
- Contact Event Host
-
Professor Eun-Seok Ryu
Multimedia Computing Systems Laboratory (MCSL) http://mcsl.skku.edu/
Department of Immersive Media Engineering (Chair)
Center for Multimedia Intelligence (Director)
Department of Computer Education (J.A.)
Sungkyunkwan University (SKKU)
- Co-sponsored by Sungkyunkwan University
Speakers
Jianquan Liu of NEC
Human Behavior Understanding: from Visible to Invisible, then Generative
Abstract: In this talk, Dr. Liu will present an industrial-level framework for sensing and understanding human behavior from multiple aspects. This integrative system supports an analysis of behavior derived from video footages via classic visible devices, such as fixed and 360-degree cameras, as well as innovative "invisible" tech like microwave sensors. The framework further enables the creation of informative reports and short video clips generated from large language models (LLMs). This presentation will highlight various research milestones within our framework, which have significantly contributed to both the academia and industries. Our framework is composed of a series of cutting-edge technologies that sense the data generated in the real world, transform them into readable, visible, and modellable digital forms, and finally analyze these digital data to understand the human behavior. This framework includes sensing techniques via traditional cameras [MM'16, SIGGRAPH'16], 360-degree cameras [MM'19, WACV'20, ICIP'21], and microwave sensors [MM'20]. Further, it includes behavior analysis in the realms of action recognition, object tracking, human and object interactions, scene recognition, and behavioral pattern analysis [ICMR'18], making the extraction, visualization, and summarization feasible [MM'22, NarSUM'23, ICMR'24], all to thoroughly interpret human behavior. These works will be introduced in the way of a general overview with interactive technical demos and interesting insights, for human behavior sensing and understanding by adopting effective processing techniques and designing efficient algorithms. Finally, Dr. Liu will share some challenges and directions for further understanding in the Era of Generative AI.
Biography:
Jianquan Liu is currently a Director and Senior Principal Researcher at NEC Corporation, working on the topics of multimedia data processing. He is also a Visiting Professor at Nagoya University and an Adjunct Professor at Hosei University, Japan. Prior to NEC, he was with Tencent Inc. from 2005 to 2006. He has published 80+ papers at major international/domestic conferences and journals and filed 100+ PCT patents. He also successfully transformed these technological contributions into commercial products in the industry. For his industry contributions, Dr. Liu has received the DBSJ Young Researcher’s Achievement and Contribution Award 2024, the IEICE Achievement Award 2023, the ITE Niwa & Takayanagi Achievement Award 2023, the 69th Electrical Science and Engineering Promotion Award, and the Minister of Education, Culture, Sports, Science and Technology (MEXT) Award in 2021, the KANTO Invention and Innovation Award 2021, the IPSJ Research and Engineering Award 2020 and the IPSJ Industrial Achievement Award 2018. Currently, Dr. Liu is/was serving as a Member-at-Large of IEEE SPS Industry Board (2025-2026), the Industry Co-chair of IEEE ICIP 2023, 2025 and ACM MM 2023, 2024, 2025; the General Co-chair of IEEE MIPR 2021; the PC Co-chair of IEEE IRI 2022, ICME 2020, AIVR 2019, BigMM 2019, ISM 2018, ICSC 2018, etc. He is a senior member of ACM, IEEE, and IPSJ, and a member of IEICE, APSIPA and DBSJ, and an associate editor of IEEE TMM (2021-2024), ACM TOMM (2022-), EURASIP JIVP (2023-), IEEE MultiMedia Magazine (2019-2022), ITE Transaction on Media Technology and Applications (2021-), APSIPA Transactions on Signal and Information Processing (2022-), and the Journal of Information Processing (2017-2021). Dr. Liu received the M.E. and Ph.D. degrees from the University of Tsukuba, Japan.
Address:Japan