国立研究開発法人 科学技術振興機構(JST)

Japan Science & Technology Agency Strategic Basic Research Program

CREST “Creation and development of core technologies interfacing human and information environments”

Final International Symposium

Tuesday, September 24, 2024
9:30 AM - 5:30 PM

AKIBA HALL

Japan Science & Technology Agency Strategic Basic Research Program

CREST “Creation and development of core technologies interfacing human and information environments”

Final International Symposium

Tuesday, September 24, 2024
9:30 AM - 5:30 PM

AKIBA HALL

The JST CREST "Symbiotic Interaction" research area started in 2017 and will conclude in the fiscal year 2024. This area has achieved remarkable results through research aligned with the strategic goal "the creation and development of core technologies interfacing human and information environments.” To commemorate the conclusion of this research area, we are hosting an international symposium. We are honored to welcome Professor Trevor Darrell from the University of California, Berkeley, Professor Masashi Sugiyama from the University of Tokyo, and Professor Shinji Nishimoto from Osaka University, who will present the latest research and future prospects on machine learning and its application to interaction with understanding. We will report on the outcomes of all research projects through oral presentations for selected topics and poster presentations for all projects. We look forward to your participation.

Update: Information about the poster presentation has been added.

Overview

Date
Tuesday, September 24, 2024,
Time
9:30 AM - 5:30 PM (Doors open at 9:00 AM)
Venue
Fujisoft Akihabara Plaza, 5th Floor, Akiba Hall (3 Neribeicho, Chiyoda-ku)
Participation Fee:Free, pre-registration required.
Capacity:180 participants for the on-site lecture.
*There will be no online streaming.

Click here to apply

For inquiries
Japan Science and Technology Agency, Department of Research Promotion, ICT
Group E-mail
crest-interaction[at]jst.go.jp
*Replace [at] with @.

Timetable

Venue “AKIBAHALL” 5th floor

Opening remarks

09:30-09:35

Kenji Mase
Emeritus Professor, Nagoya University

Research Results

09:35-09:50

“Human-Robot Interaction for Symbiotic Robots in a Public Space in a City”

Takayuki Kanda
Professor, Graduate School of Informatics Kyoto University
Invited Group Leader, Advanced Telecommunications Research Institute International

09:50-10:05

“A study on skill acquisition mechanism and development of skill transfer systems”

Hideki Koike
Professor, School of Computing Tokyo Institute of Technology

10:05-10:20

“Computational and cognitive neuroscientific approaches for understanding the tender care”

Atsushi Nakazawa
Professor, Faculty of Interdisciplinary Science and Engineering in Health Systems Okayama University

10:20-10:35

“Computational Social Touch for Symbiotic Human-Robot Interaction”

Masahiro Shiomi
Group Leader, Interaction Science Laboratories Advanced Telecommunications Research Institute International

10:35-10:50

Break

10:50-11:05

“Materialized Graphics for Multidimensional Interaction”

Hiroyuki Shinoda
Professor, Graduate School of Frontier Sciences The University of Tokyo

11:05-11:20

“Construction of representational Brain-Computer Interaction technology”

Takufumi Yanagisawa
Professor, Institute for Advanced Co-Creation Studies Osaka University

11:20-11:35

“VoicePersonae: Speaker identity cloning and protection”

Junichi Yamagishi
Professor, National Institute of Informatics Research Organization of Information and Systems

11:35-11:50

“A study on mutual understanding computing based on simultaneous contextualization and interpreting”

Michita Imai
Professor, Faculty of Science and Technology Keio University

11:50-12:50

Break

12:50-13:50
13:50-14:00

Break

Keynote Lecture

14:00-15:00

“The surprising efficacy of "ungrounded" models for image and video understanding, generation, and humanoid locomotion”

Trevor Darrell
Professor, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley

Recently released open-source text LLMs have provided significant leverage towards multimodal perception, via lightweight fusion with learned visual representations, or even--somewhat paradoxically---as a unimodal source of knowledge in another domain. I'll cover our recent work exploring this premise, including recent advances toward a modern form of visual routines a.k.a. visual programming, methods for recursive explainable visual question answering, an approach to multimodal gesture animation, and image and video generation with LLM-constrained diffusion models. As time permits I'll also discuss advances in large scale next token prediction models for vision and humanoid locomotion.

Special Lectures

15:00-15:40

“Perceptual and cognitive representations in the brain”

Shinji Nishimoto
Professor, Graduate School of Frontier Biosciences, Osaka University
Research Manager, CiNet, National Institute of Information and Communications Technology (NICT)

15:40-16:20

“Towards More Reliable Machine Learning”

Masashi Sugiyama
Professor, Graduate School of Frontier Sciences The University of Tokyo

16:20-16:35

Break

Panel Discussion

16:35-17:25

“Prospectives of Next-Generation Human-Computer Interaction: Multimodal and Symbiotic Approaches”
• The Evolution and Applications of Multimodal LLMs
• Symbiosis with Robots and AI: Next-Generation Interaction Models
• Redefining Interaction through Augmented Reality (AR) and Virtual Reality (VR)

Closing Remarks

17:25-17:30

Kenji Mase
Emeritus Professor, Nagoya University

■ Poster Interactive Session
“Presentation Room” 7th floor

Team Title Presenters / Authors
Igarashi HCI for Machine learning Takeo Igarashi
Kanda The Attentive Shopworker: Field Trial of an Autonomous Robot for Friendly Encouragement and Social Pressure Sachi Natasha
Koike Breaking the limit of sensory, motor, and cognitive skills of musicians Shinichi Furuya
Tsuda Behavioral and neural dynamics during parent-child interactions Takashi Ikeda and Hiroshi Watanabe
Nakazawa Atsushi Computational tender-care science: : Computational and cognitive neuroscientific approaches for understanding the tender care Atsushi Nakazawa, Ryo Kurazume, Miwako Honda, Wataru Sato and Miyuki Iwamoto
Capturing Contact Surfaces by a Frustrated Total Internal Reflection System Using a Curved Plate for Comparison of the Beginning of Touching Motions by Humanitude Experts and Novices Akishige Yuguchi, Mayuki Toyoda, Sung-Gwi Cho, Atsushi Nakazawa, Jun Takamatsu, Koichiro Yoshino and Tsukasa Ogasawara
Shiomi Hug effects in human-robot interaction and their applications Masahiro Shiomi, Yuya Onishi and Hidenobu Sumioka
Development of baby-like robots to facilitate social touch interaction Hidenobu Sumioka and Masahiro Shiomi
Shinoda A logical and algebraic approach to defining and measuring representations Yivan Zhang
Optical See-Through 3D Display for Augmented Reality Using Interleaved Fresnel Lens Array Hideki Kakeya and Hiroto Omori
Terada Interaction Platform based on Psychological Informatics for Information Presentation Tsutomu Terada
Hiraki CANSASI: Mobile Sensing Platform powered by Large Language Models Akio Sashima
Yanagisawa Quantizing Temporal Dynamics: A Transformative VQ-VAE Approach for Generalized Neural Decoding Nayuta Mizuguchi
Augmented Reality Brain-Computer Interface Using Slow Cortical Potentials for Phantom Limb Pain Ding Changhao
Yamagishi Exploring Fact-Checking Capabilities Across Diverse Datasets with Large Language Models Iffat Maab, Saku Sugawara and Junichi Yamagishi
Bias Detection in Political Media Across Families of Large Language Models Iffat Maab
Imai A Study on the Impressions and Characteristics of Azatoi Smiles Aika Awane
Estimation of dress preference from a few samples Tomoyuki Maekawa
Suzuki Understanding human empathic behavior through interpersonal neural entrainment in early development: Methodological challenges and findings Yasuyo Minagawa, Satoshi Morimoto, Yoko Hakuno and Kenji Suzuki
Toda Augmented speech production and hearing systems Tomoki Toda, Nobutaka Ono, Hirokazu Kameoka
Nakazawa Jin Overcoming Bounded Rationality through Symbiotic Interaction Jin Nakazawa
Nakamura Training Adapted Personalised Affective Social Skills with Cultural Virtual Agents Satoshi Nakamura

Speakers

  • Trevor Darrell photo

    Trevor Darrell

    Professor, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley

    Professor Darrell is on the faculty of the CS Division at UC Berkeley. His group develops algorithms to enable visual recognition across a variety of platforms and applications. His interests include computer vision, machine learning, computer graphics, and perception-based human computer interfaces. Prof. Darrell was on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M. and Ph.D. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988, having started his career in computer vision as an undergraduate researcher in Ruzena Bajcsy’s GRASP lab.

  • Kenji Mase photo

    Kenji Mase

    Emeritus Professor, Nagoya University

    Kenji Mase received the B.E. degree in Electrical Engineering and the M.E.and Ph.D. degrees in Information Engineering from Nagoya University in 1979, 1981 and 1992 respectively. He became professor of Nagoya University in August 2002. He is now Professor Emeritus of Nagoya University and a designated professor of Mathematical and Data Science Center. He is a Research Supervisor of JST CREST on Symbiotic Interactions since 2017. He joined the Nippon Telegraph and Telephone Corporation (NTT) in 1981 and had been with the NTT Human Interface Laboratories. He was a visiting researcher at the Media Laboratory, MIT in 1988-1989. He has been with ATR (Advanced Telecommunications Research Institute) in 1995-2002. His research expertise includes image processing, its application to multi-modal human-computer interaction, AI, wearable computers, lifelog, interaction corpus and so on. He is a Fellow of Institutes of Electronics, Information and Communication Engineers (IEICE) of Japan, and member of the Information Processing Society of Japan (IPSJ), Japan Society of Artificial Intelligence (JSAI), and a senior member of IEEE Computer Society. He was a Section Chair of IEEE Nagoya Section in 2014-2015. He was the 24th and 25th associate member of Science Council of Japan.

  • Takayuki Kanda photo

    Takayuki Kanda

    Professor, Graduate School of Informatics Kyoto University
    Invited Group Leader, Advanced Telecommunications Research Institute International

    Takayuki Kanda is a professor in Informatics at Kyoto University, Japan. He is also a Visiting Group Leader at ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan. He received his B. Eng, M. Eng, and Ph. D. degrees in computer science from Kyoto University, Kyoto, Japan, in 1998, 2000, and 2003, respectively. He is one of the starting members of Communication Robots project at ATR. He has developed a communication robot, Robovie, and applied it in daily situations, such as peer-tutor at elementary school and a museum exhibit guide. His research interests include human-robot interaction, interactive humanoid robots, and field trials.

  • Hideki Koike photo

    Hideki Koike

    Professor, School of Computing Tokyo Institute of Technology

    HIDEKI KOIKE is a professor at the School of Computing, Tokyo Institute of Technology, Japan. He received his B.E., M.E., and Ph.D. degrees from the University of Tokyo in 1986, 1988, and 1991, respectively. After working at the University of Electro-Communications, Tokyo, he joined the Tokyo Institute of Technology in 2014. During his career, Prof. Koike was a visiting researcher at the University of California, Berkeley (1994), the University of Sydney (1997), and a Cabinet Secretary of Japan (2002). His research interests include vision-based human-computer interaction, human augmentation, interactive surfaces, projector-camera systems, information visualization, and usable security. Prof. Koike is the recipient of numerous awards, including the IEEE Transactions on Haptics Best Application Paper Award (2021), ACM SIGGRAPH VRCAI Best Paper Award (2019), Laval Virtual Grad Prix Award and Interface and Materials Award (2013), and many Honorable Mention and Best Demo Awards.

  • Atsushi Nakazawa photo

    Atsushi Nakazawa

    Professor, Faculty of Interdisciplinary Science and Engineering in Health Systems Okayama University

    Atsushi Nakazawa is an professor in the Graduate School of Interdisciplinary Science and Engineering in Health Systems. He received his doctorate from the Osaka University in 2001 in Systems Engineering. Afterward, he worked at the Institute of Industrial Science, University of Tokyo, and then in Cybermedia Center, Osaka University. From 2013, he joined Kyoto University. From 2007 to 2008, he studied at Georgia Institute of Technology (GaTech), GVU Center, as a visiting researcher, and worked with Professor James M Rehg and professor Irfan Essa. From Oct. 2017, he becomes a program investigator (PI) of the JST CREST project "Computational and cognitive neuroscientific approaches for understanding the tender care". His research interests are in human behavior/mental analysis using computer vision, eye tracking, eye imaging, and motion capture systems.

  • Masahiro Shiomi photo

    Masahiro Shiomi

    Group Leader, Interaction Science Laboratories Advanced Telecommunications Research Institute International

    Masahiro Shiomi is a senior research scientist and a group leader of the Agent Interaction Design Laboratory at the Interaction Science Laboratories at ATR, Kyoto, Japan. He is also a visiting professor at Kobe University and an invited professor at Osaka University. He received his M. Eng and Ph. D. degrees in engineering from Osaka University, Osaka, Japan, in 2004 and 2007, respectively. He was a research director of a research project entitled “Computational Social Touch for Symbiotic Human-Robot Interaction,” supported by Core Research for Evolutionary Science and Technology (CREST), Japan Science and Technology Agency (JST) from 2018 to 2024. His research interests include human-robot interaction, social touch interaction, robotics for childcare, and multiple social robots. He served as a Program Chair on Ro-MAN2020, HAI2021, and HRI2022. He also served as an Associate Editor for the ACM Transactions on Human-Robot Interaction (THRI). He is a member of ACM and IEEE.

  • Hiroyuki Shinoda photo

    Hiroyuki Shinoda

    Professor, Graduate School of Frontier Sciences The University of Tokyo

    Hiroyuki Shinoda has been a professor at the University of Tokyo since 2012. His research interests include haptics, midair tactile displays, and related sensing and interaction issues in real-world information systems. He received the Best Conference Paper Award in IEEE ICRA 1999, the Best Technical Paper Award in the World Haptics Conference 2021, and from the IEEE Transactions on Haptics, the Best Paper Award and the Best Application Paper Award in 2022 and 2023, respectively. He was the Asia Haptics 2016 general chair, Euro Haptics 2018 program co-chair, IEEE World Haptics Conference 2019 general co-chair, and IEEE World Haptics Conference 2021 steering committee chair.

  • Takufumi Yanagisawa photo

    Takufumi Yanagisawa

    Professor, Institute for Advanced Co-Creation Studies Osaka University

    Dr. Takufumi Yanagisawa completed BA degrees in Physics in 1998, followed by his Master degrees in Physics at the Waseda University in Japan. Then, he completed BA degree in Medicine and obtained a license of Medical Doctor in 2004 at the Osaka University. After four years of initial neurosurgical residency, he completed his PhD at Osaka University Graduate School of Medicine in 2009. He earned board certification adopted by the Japan Neurosurgical Society in 2010 and became clinical specialists certified by Japan Epilepsy Society in 2017. He became an assistant professor in 2012, then, a lecturer at the Endowed Research Division of Clinical Neurology and Engineering at the Osaka University in 2016. He has been in his current position since April 2018. He has had extensive prior experience in neurophysiological evaluation of electrocorticographic (ECoG) signals and magnetoencephalographic (MEG) signals, and development of brain-computer interfaces (BCI) using these signals, application of the developed BCI for clinical purposes.

  • Junichi Yamagishi photo

    Junichi Yamagishi

    Professor, National Institute of Informatics Research Organization of Information and Systems

    Junichi Yamagishi received a Ph.D. degree from the Tokyo Institute of Technology (Tokyo Tech), Tokyo, Japan, in 2006. From 2007 to 2013, he was a research fellow at the Centre for Speech Technology Research, University of Edinburgh, U.K. He became an associate professor with the National Institute of Informatics, Japan, in 2013, where he is currently a professor. His research interests include speech processing, machine learning, signal processing, biometrics, digital media cloning, and media forensics. He served as a co-organizer for the bi-annual ASVspoof Challenge and the bi-annual Voice Conversion Challenge. He also served as a member of the IEEE Speech and Language Technical Committee from 2013 to 2019, as an Associate Editor for IEEE/ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (TASLP) from 2014 to 2017, as a Senior Area Editor for IEEE/ACM TASLP from 2019 to 2023, as the chairperson for ISCA SynSIG from 2017 to 2021, and as a member at large of IEEE Signal Processing Society Education Board from 2019 to 2023.

  • Michita Imai photo

    Michita Imai

    Professor, Faculty of Science and Technology Keio University

    Michita Imai is a Professor of Faculty of science and technology at Keio university and a Researcher at ATR Intelligent Robot Laboratories. He received his Ph.D. degree in Computer Science from Keio Univ. in 2002. In 1994, he joined NTT Human Interface Laboratories. He joined the ATR Media Integration & Communications Research Laboratories in 1997. He was a visiting scholar of University of Chicago from 2009-2010. His research interests include autonomous robots, human-robot interaction, speech dialogue systems, humanoid, and spontaneous behaviors. He is a member of Information and Communication Engineers Japan (IEICE-J), the Information Processing Society of Japan, the Japanese Cognitive Science Society, the Japanese Society for Artificial Intelligence, Human Interface Society, IEEE, and ACM.

  • Shinji Nishimoto photo

    Shinji Nishimoto

    Professor, Graduate School of Frontier Biosciences, Osaka University Research Manager, CiNet, NICT

    Shinji Nishimoto completed the doctoral program at the Graduate School of Engineering Science, Osaka University, in 2005, earning a Ph.D. in Science. He subsequently worked at the Helen Wills Neuroscience Institute at the University of California, Berkeley, and the Center for Information and Neural Networks (CiNet) at the National Institute of Information and Communications Technology (NICT). In 2021, he was appointed as a Professor at the Graduate School of Frontier Biosciences, Osaka University. His research focuses on the quantitative understanding of perceptual and cognitive representations in the brain, as well as the development of related applied technologies. He has received several awards, including being listed among Time Magazine's 50 Best Inventions in 2011, the Ichimura Prize in Science for Distinguished Achievement in 2016, and the JSPS Prize in 2023.

  • Masashi Sugiyama photo

    Masashi Sugiyama

    Professor, Graduate School of Frontier Sciences The University of Tokyo

    Masashi Sugiyama received a Ph.D. degree in Computer Science from Tokyo Institute of Technology, Japan, in 2001. After experiencing assistant and associate professors at the same institute, he became a professor at the University of Tokyo in 2014. Since 2016, he has concurrently served as Director of the RIKEN Center for Advanced Intelligence Project. His research interests include theories and algorithms of machine learning. He was a recipient of the Japan Academy Medal in 2017 and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology in Japan in 2022.

  • Takeo Igarashi photo

    Takeo Igarashi

    Professor, Graduate School of Information Science and Technology The University of Tokyo

    Takeo Igarashi is a Professor of Computer Science Department at The University of Tokyo. He received a Ph.D from the Department of Information Engineering at The University of Tokyo in 2000. He joined the Department of Computer Science as an assistant professor in 2002 and was promoted to a professor in 2011. His research interest is in user interfaces and interactive computer graphics in general. His early work includes the development of a sketch-based modeling system (Teddy) and a multi-touch shape deformation method. He led a JST ERATO project and a JST CREST project as a director. In these projects, he has developed interactive shape modeling techniques tailored for digital fabrication, and interaction techniques to control robotic systems working in the real world. He served as program co-chair for Pacific Graphics 2008, program co-chair for UIST 2013, general co-chair for UIST 2016, technical papers chair for SIGGRAPH ASIA 2018, technical program co-chair for ACM CHI 2021, and conference chair for ACM SIGGRAPH ASIA 2024. He received the SIGGRAPH Significant New Researcher Award in 2006, JSPS Award, CHI Academy Award in 2019, ACM UIST 2019 Lasting Impact Award, and the Asia Graphics 2020 Outstanding Technical Contributions Award.

Registration

Please register via the following registration site

registration

We will close registration once we reach the capacity limit of 180 participants

Links

This CREST research area constitutes a component area of ​​the AIP Network Lab, an implementing institution of the Ministry of Education, Culture, Sports, Science and Technology's integrated project on artificial intelligence, big data, IoT, and cybersecurity (AIP Project).