LAB LOGA page on LabLog, a review site (not the lab's official page)
Yanai Lab
Machine-translated · View original
A lab that uses deep learning to recognize and generate images and video.
AboutAbout the lab
Recognizing and generating images and video with deep learning
The Yanai Lab uses deep learning to study how to make computers understand the content of images and video.
Beyond recognition, the lab also works on transforming and generating images, and on estimating calorie and nutrient content from meal images.
The lab's research keywords are image and video recognition and generation, deep learning, Web multimedia mining, and deep learning mobile apps.
Key terms
- Deep learning
- A method in which a computer learns from large amounts of data to perform tasks such as image recognition and generation.
- General image recognition
- Technology that lets computers understand what appears in a wide variety of images, such as lions, mountains, airplanes, and cars.
- Web multimedia mining
- A method of collecting large amounts of images and video from the Web, and extracting and analyzing information from them.
NewsLab news
View More ↗ResearchResearch themes
The lab uses deep learning to study image and video recognition, which makes computers understand the content of images and video. Recently, it has also been working on image and video generation with deep learning and on semantic image transformation.
*Illustrative imageImage recognition from limited data and video
General image recognition with deep learning has reached accuracy that surpasses humans, but learning from a small number of samples, recognizing video, and handling a variety of tasks with a single network remain difficult challenges. The lab studies these problems.
*Illustrative imageImage generation and transformation
The lab uses deep learning to transform and generate images. It studies how to generate and transform images so that the output looks realistic, or is recognizable as an object of a specific category.
*Illustrative imageCalorie estimation from meal images
Recognizing the type of meal can now be done with high accuracy, so the lab is working on estimating calorie and nutrient content from appearance alone. Recently, it has been working to obtain the 3D shape and volume of a meal from a single image, aiming at accurate calorie estimation.
MembersFaculty
The Yanai Lab consists of a professor, doctoral, master's, and undergraduate students, and Japanese government-sponsored research students.As of 2026
- ProfessorKeiji Yanai
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 Yanai Lab
Nakashika LabSchool of Informatics and Engineering, Class I (Informatics)Speech recognition / speech synthesis / image recognition / …
Nagahama LabSchool of Informatics and Engineering, Class I (Informatics)Multi-agent systems / data science / human-machine collabora…
Hirota-Nojima LabSchool of Informatics and Engineering, Class I (Informatics)Image recognition / user interfaces / VR / AR
Takagi LabSchool of Informatics and Engineering, Class I (Informatics)Educational and learning support systems / educational techn…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: “CLEVR1080” Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Fei-Fei Li, Larry Zitnick, Ross Girshick / CC BY-SA 4.0 (cropped)
- Image recognition from limited data and video: “Security camera” Wikideas1 / CC0 (cropped)
- Image generation and transformation: “Style transfer” Mehrdad Yazdani / CC BY-SA 4.0 (cropped)
- Calorie estimation from meal images: “Dinner meal MyPlate 20210810-FNS-UNC-0016” U.S. Department of Agriculture / Public domain (cropped)
- Related lab (Nakashika Lab): “Siemens Studio for Electronic Music - Console, Signal generator, Tape recorders - Deutsches Museum, 2010” pixabay: Stefan Schweihofer / CC0 (cropped)
- Related lab (Nagahama Lab): “Autonomous Delivery Vehicle Pileup” Mbrickn / CC BY-SA 4.0 (cropped)
- Related lab (Hirota-Nojima Lab): “HAPTION Virtuose 6 Degrees of Freedom Force-Feedback in Immersive Simulation” HAPTION / CC BY-SA 3.0 (cropped)
- Related lab (Takagi Lab): “Teacher training in Naura” Elhegamohamed / CC BY-SA 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.