LAB LOGA page on LabLog, a review site (not the lab's official page)
Image and Media Understanding Lab
Machine-translated · View original
The lab analyzes educational data and images with AI to support people and society.
AboutAbout the lab
Exploring support for people and society through data and AI.
The Image and Media Understanding Lab conducts research on the analysis and use of learning and educational data, time-series data analysis, and image and media understanding.
Through data analysis and AI technology, the lab aims to create new methods that contribute to understanding and supporting people and society.
In learning analytics, the lab studies methods that analyze learning records to help instructors improve their teaching and help learners reflect on their learning.
To join the lab as a master's student, you take the entrance examination for the Department of Information Science and Technology, Graduate School of Information Science and Electrical Engineering.
Key terms
- Learning analytics
- Analysis that finds information useful to learners and instructors from learning histories. In Japanese, it is also called learning analysis.
- LLM
- AI that learns from large amounts of text to understand and generate text. Also known as a large language model.
- Metacognition
- How accurately one can recognize one's own state of understanding.
NewsLab news
View More ↗ResearchResearch themes
The lab aims to create new methods that contribute to understanding and supporting people and society, using data analysis and AI technology. The research page is divided into the areas of learning analytics, time-series forecasting, AI that supports people, and image processing. This page introduces the themes of the first area, learning analytics.
*Illustrative imageInterpreting learning behavior based on course material content
The lab studies a method that links differences in learning behavior to the parts of the course material that gave rise to them, and presents the results in a form that instructors can easily understand. LLMs are used only to generate explanations, with the aim of providing feedback that preserves the basis of the analysis.
*Illustrative imageLearning support based on metacognition
The lab studies methods that capture how accurately learners recognize their own state of understanding and use this for learning support. By integrating free-text reflections and test results, and estimating learners' awareness of their own knowledge with an LLM and a heterogeneous graph neural network, the lab aims to provide individualized feedback that matches the gap between what learners actually lack in knowledge and how they perceive themselves.
*Illustrative imageVisualizing learning behavior in agricultural practical training
This research objectively captures learners' activities during agricultural practical training and uses it for instructors' reflection and teaching improvement. Using 360-degree cameras and wearable cameras, the lab estimates and visualizes learners' positions, work time, and work states, aiming to support reflection, evaluation, and instruction after the training.
*Illustrative imageLearning analytics that gives an overview of the entire curriculum
This research captures the connections and progress of learning across the whole curriculum, not just in individual courses. By overlaying relationships between courses, individual learning status, trends among past students, grades, and more onto a curriculum map for visualization, the lab aims to create an environment in which learners can plan and reflect from a long-term perspective.
MembersFaculty
The members of the Image and Media Understanding Lab consist of faculty, technical staff, collaborators, and doctoral, master's, and undergraduate students.As of 2026
- ProfessorAtsushi Shimada
- Associate ProfessorFumiya Okubo
- Assistant ProfessorGen Li
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Image and Media Understanding Lab
AI Education LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceThe Artificial Intelligence in Education (AIE) Laboratory co…
Virtual Reality Interaction Design Lab (Yutaka Arakawa)Faculty of Engineering, Department of Electrical Engineering and Computer ScienceHuman-friendly cyber-physical systems (CPS) combining real-w…
Human Data Interaction LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceHuman–data interaction: design, methods, and technologies fo…
Cyber-Physical Computing LabFaculty of Engineering, Department of Electrical Engineering and Computer ScienceWe aim to create new computer system architectures based on …The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “USB webcam for PC” WrS.tm.pl / CC0 (cropped)
- Interpreting learning behavior based on course material content: “Mengulang pelajaran saat pulang sekolah” Pingcung / CC BY-SA 4.0 (cropped)
- Learning support based on metacognition: “A picture is worth a thousand words” HikingArtist / CC BY-SA 3.0 (cropped)
- Visualizing learning behavior in agricultural practical training: “Harvest (20181113-FPAC-LSC-0119)” USDAgov / Public domain (cropped)
- Learning analytics that gives an overview of the entire curriculum: “Ohio University Lecture Hall” Garden Sprite / CC0 (cropped)
- Related lab (AI教育研究室): “Learning to Code” Preply.com Images / CC BY 2.0 (cropped)
- Related lab (バーチャルリアリティー・インタラクションデザイン研究室
（荒川 豊） ): “Huawei Smartwatch (Band 4)” TheArchivistMan / CC0 (cropped) - Related lab (ヒューマン・
データ・インタラクション研究室): “APRENDIZAJE SIGNIFICATIVO” SAMMYTQM / CC BY-SA 4.0 (cropped) - Related lab (サイバーフィジカル・コンピューティング研究室): “Josephson Traveling Wave Parametric Amplifier (J-TWPA) 002” OJB Quantum / CC BY 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.