Yasunori Ishii | Researchers | Panasonic AI | Panasonic Research and Development on Artificial Intelligence (AI)

Yasunori Ishii

Major: Information Engineering (Natural Science)
AI Solution Center, Business Innovation Division, Panasonic
Joined 2003

My work involves research and development of image processing based on deep learning, which is to develop algorithms to improve recognition accuracy by detecting key information from a large quantity of images. At the time when I worked on developing digital cameras, I faced difficulties in improving the developed product with algorithms, but it eventually improved. This challenging experience and the joy after success became the source of my research and development. Now, I start considering about the best algorithms when thinking of product design. Although deep learning is still in the course of development, I would like to proactively implement new technology into product development.

*The department is where the interviewee belonged to at that time

Publications

International Conference on Computer Vision Theory and Applications (VISAPP) 2020

Simultaneous Visual Context-aware Path Prediction

Haruka Iesaki, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yasunori Ishii, Kazuki Kozuka, Ryota Fujimura
Link: https://www.scitepress.org/Link.aspx?doi=10.5220/0008921307410748
IEEE/CVF International Conference on Computer Vision Workshop (ICCVW 2019)

Adherent Raindrop Removal with Self-Supervised Attention Maps and Spatio-Temporal Generative Adversarial Networks

Stefano Alletto, Casey Carlin, Luca Rigazio, Yasunori Ishii, Sotaro Tsukizawa
Link: http://openaccess.thecvf.com/content_ICCVW_2019/papers/ADW/Alletto_Adherent_Raindrop_Removal_with_Self-Supervised_Attention_Maps_and_Spatio-Temporal_Generative_ICCVW_2019_paper.pdf
NeurIPS Workshop on Systems for ML and Open Source Software

Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Yasunori Ishii, Sotaro Tsukizawa
Link: https://arxiv.org/abs/1811.08011
3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015

Deep Learning using Heterogeneous Feature Maps for Maxout Networks

Yasunori Ishii, Reiko Hagawa, Sotaro Tsukizawa
Link: https://ieeexplore.ieee.org/document/7486545
3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015

Multi-staged Deep Learning with Created Coarse and Appended Fine Categories

Reiko Hagawa, Yasunori Ishii, Sotaro Tsukizawa
Link: https://ieeexplore.ieee.org/document/7486461

RESEARCHERS

International Conference on Computer Vision Theory and Applications (VISAPP) 2020

IEEE/CVF International Conference on Computer Vision Workshop (ICCVW 2019)

NeurIPS Workshop on Systems for ML and Open Source Software

3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015

3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015