国立研究開発法人 産業技術総合研究所 人間情報インタラクション研究部門 メディアインタラクション研究グループ Media Interaction Group, Human Informatics and Interaction Research Institute (HIIRI), National Institute of Advanced Industrial Science and Technology (AIST)
The Media Interaction Group targets a variety of media content (music, video, text, user activities, etc.) and conducts research on media interaction technologies that can enrich people's life. In particular, our group aims to promote content creation and utilization and enhance the creativity of the society by bridging the gap between creators and consumers. Toward this goal, we develop value-creation support technologies that facilitate content creation by complementing knowledge, experience, and technique of creators. We also develop value-enhancement support technologies that provide consumers with various means of appreciation, retrieval, recommendation, and browsing. These media technologies and interaction technologies demand a broad range of basic and applied research. We conduct research on music information processing, singing information processing, natural language processing, image and video processing, human-computer interaction, web services, signal processing, machine learning, retrieval and recommendation, data mining, visualization, computer graphics, community analysis and support, etc.
- Yuto Mandai, Katie Seaborn, Tomoyasu Nakano, Xin Sun, Yijia Wang, Jun Kato: Super Kawaii Vocalics: Amplifying the "Cute" Factor in Computer Voiceopen_in_new
- Takao Fujii, Katie Seaborn, Madeleine Steeds, Jun Kato: Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referentsopen_in_new
- Yuki Tatsukawa, I-Chao Shen, Mustafa Doga Dogan, Anran Qi, Yuki Koyama, Ariel Shamir, and Takeo Igarashi: FontCraft: Multimodal Font Design Using Interactive Bayesian Optimizationopen_in_new
- Kosetsu Tsukuda, Atsuki Maruta, Makoto P. Kato and Hideo Joho: Eliciting Implicit Information Needs in E-Commerce Search by Using the Think-Aloud Methodopen_in_new
- Tomoyasu Nakano, Masataka Goto: Using Item Response Theory to Aggregate Music Annotation Results of Multiple Annotatorsopen_in_new
- Takayuki Nakatsuka, Masahiro Hamasaki, Masataka Goto: Harnessing the Power of Distributions: Probabilistic Representation Learning on Hypersphere for Multimodal MIRopen_in_new
- Michele Newman, Lidia Morris, Jun Kato, Masataka Goto, Jason Yip, Jin Ha Lee: Purposeful Play: Evaluation and Co-Design of Casual Music Creation Applications with Childrenopen_in_new
Yuki Tatsukawa, I-Chao Shen, Anran Qi, Yuki Koyama, Takeo Igarashi, and Ariel Shamir: FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applicationsopen_in_new
Shigeo Yoshida, Yuki Koyama, and Yoshitaka Ushiku: Toward AI-Mediated Avatar-Based Telecommunication: Investigating Visual Impression of Switching Between User- and AI-Controlled Avatars in Video Chatopen_in_new
Takayuki Nakatsuka, Masahiro Hamasaki, Masataka Goto: A Cover Image Composition Method for Music Content Using Multimodal Image Retrieval and Cropping Techniquesopen_in_new
Yuki Tatsukawa, I-Chao Shen, Anran Qi, Yuki Koyama, Takeo Igarashi, and Ariel Shamir: FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applicationsopen_in_new
Media Interaction Group
Human Informatics and Interaction Research Institute (HIIRI),
National Institute of Advanced Industrial Science and Technology (AIST)
AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba, Ibaraki 305-8568, Japan