Theme: A Research of deep network that efficiently learns in
short time and keeps and improves product recognition accuracy against increasing number of
products
April 2012 - March 2016
The University of Electro-Communications: Bachelor of Engineering
Major: Informatics
Thesis: Implementation and Comparative Analysis of Image
Recognition System based on Deep Learning on Mobile OS
Main Research Interests: Deep Learning for Mobile, Generative Adversarial
Networks(GANs), Food (e.g. Real-Time Image Recognition, Neural Style Transfer, Generative Model)
Sub Research Interests: Information Visualization and Data Mining,
Intellectual Property, Education on Mathematics and Physics
Publications(15 International Conferences):
・Keisuke Kiritoshi, Ryosuke Tanno and Tomonori Izumitani; L1-Norm Gradient
Penalty for Noise Reduction of Attribution Maps, Proc. of IEEE CVPR Workshop on Explainable AI,
poster, Long Beach, USA (2019/06).
・Takumi Ege, Yoshikazu Ando, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai: Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation,
Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR),
oral, San Jose, USA (2019/03).
・Shu Naritomi, Ryosuke Tanno, Takumi Ege and Keiji Yanai: FoodChangeLens:
CNN-based Food Transformation on HoloLens, Proc. of International Workshop on Interface and
Experience Design with AI for VR/AR (DAIVAR), demo, Taichung, Taiwan (2018/12).
・Yuki Izumi, Daichi Horita, Ryosuke Tanno and Keiji Yanai: Real-Time Image
Classification and Transformation Apps on iOS by “Chainer2MPSNNGraph”, Proc. of NIPS WS on
Machine Learning on the Phone and other Consumer Devices (MLPCD), demo, Motreal, Canada
(2018/12).
・Ryosuke Tanno, Takumi Ege and Keiji Yanai: AR DeepCalorieCam V2: Food Calorie
Estimation with CNN and AR-based Actual Size Estimation, ACM Symposium on Virtual Reality
Software and Technology (VRST), demo, Tokyo, Japan (2018/11).
・Ryosuke Tanno, Daichi Horita, Wataru Shimoda and Keiji Yanai: Magical Rice Bowl:
Real-time Food Category Changer, Proc. of ACM Multimedia (ACM MM), demo, Seoul, Korea
(2018/10).
・Daichi Horita, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai: Food Category
Transfer with Conditional Cycle GAN and a Large-scale Food Image Dataset, Proc. of International
Workshop on Multimedia Assisted Dietary Management (MADiMa), oral, Stockholm, Sweden (2018/07).
・Ryosuke Tanno and Keiji Yanai: AR DeepCalorieCam: An iOS App for Food Calorie
Estimation with Augmented Reality, Proc. of the International Multimedia Modeling Conference
(MMM), poster, Bangkok, Thailand (2018/02).
・Ryosuke Tanno, Takumi Ege and Keiji yanai: DeepCalorieCam:
An iOS App for Dish Detection and Calorie Estimation, Proc. of ICIAP International Workshops on
Multimedia Assisted Dietary Management (MADiMa), demo, Catania, Italy (2017/09).
・Keiji Yanai and Ryosuke Tanno: Conditional Fast Style Transfer Network,
Proc. of ACM International Conference on Multimedia Retrieval (ICMR), poster, Bucharest, Romania
(2017/06).
・Ryosuke Tanno and Keiji Yanai: DeepStyleCam:DeepStyleCam: A Real-time Style
Transfer App on iOS, Proc. of International Conference on Multimedia Modelling (MMM),
demo, Reykjavik, Iceland (2017/01). (Best Demonstration Award)
・Ryosuke Tanno and Keiji Yanai: Caffe2C: A Framework for Easy Implementation of
CNN-based Mobile Applications, International Workshop On Mobile Ubiquitous Systems,
Infrastructures, Communications, And AppLications (MUSICAL 2016), oral, Hiroshima, Japan
(2016/11).
・Ryosuke Tanno, Wataru Shimoda and Keiji Yanai: DeepXCam: Very Fast CNN-based
Mobile Applications: Multiple Style Transfer and Object Recognition, Proc. of the European
Conference on Computer Vision (ECCV), demo, Amsterdam, Netherlands (2016/10).
・Ryosuke Tanno, Koichi Okamoto and Keiji Yanai: DeepFoodCam: A DCNN-based
Real-time Mobile Food Recognition System, Proc. of ACM MM Workshop on Multimedia Assisted Dietary
Management (MADiMa), demo, Amsterdam, Netherlands (2016/10).
・Keiji Yanai, Ryosuke Tanno and Koichi Okamoto: Efficient Mobile Implementation
of A CNN-based Object Recognition System, Proc. of ACM Multimedia (ACM MM), poster,
Amsterdam, Netherlands (2016/10).
Art Works:
・Ryosuke Tanno: Japanese Anime Food Image Transformation, Proc. of NeurIPS
Workshop on Machine Learning for Creativity and Design, art works, Motreal, Canada (2018/12).
Please visit AI Art Gallery → here!!.
・Ryosuke Tanno: Food Image Transformation, Proc. of ECCV Workshop on
Computer Vision for Fashion, Art and Design, art works, Munich, Germany (2018/9).
(longlist)
Please visit Computer Vision Art Gallery Site → here !!.
My first visual art with computer vision techniques is here !!.
Developed Applications (All applications related to deep learning, Mobile and Web App):
・DeepCalorieCam V2(VRST2018): Project HP and Code
・FoodChangeLens(AIVR WS2018): Project HP
・Magical Rice Bowl(ACM MM2018): Project HP and Code
・DeepCalorieCam(MMM2018): Project HP
・GAN_Qualitative_Evaluation_App(DEIM2018): Code and Demo
・DeepCalorieCam V1 AR ver(MADiMa2017)
・SceneTexEraser(MIRU2017)
・DeepMaterialCam(MIRU2017)
・DeepMaterialCam(MIRU2017)
・DeepStyleCam V2(MIRU2017): Project HP
・DeepStyleCam(MMM2017): Project HP
・DeepStyleCam β ver(MIRU2016)
・DeepFoodCam(MADiMa2016) : Project HP
Developed Applications Demo Movies
FoodChangeLens (AIVR WS2018)
Demo Movie Version 1. It was created
by Shu Naritomi and Takumi Ege.
FoodChangeLens (AIVR WS2018)
Demo Movie Version 2. It was created
by Shu Naritomi and Takumi Ege.
