Scholar
Akinori F. Ebihara
Google Scholar ID: kEFgLrsAAAAJ
NEC Corporation
Citations & Impact
Citations
240
H-index
9
i10-index
9
Publications
20
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- - Paper “Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test” accepted to ICLR 2025.
- - Paper “Toward Asymptotic Optimality: Sequential Unsupervised Regression of Density Ratio for Early Classification” accepted to ICASSP 2023.
- - Paper “Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series” accepted to WCCI 2021 (IJCNN track) as an oral presentation.
- - Paper “Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition” accepted to IJCB 2021.
- - Paper “Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization” accepted to ICML 2021.
- - Paper “Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy” accepted as a Spotlight presentation (top 5.57%) at ICLR 2021.
- - Paper “Specular- and Diffuse-reflection-based Face Spoofing Detection for Mobile Devices” won IJCB 2020 Google Best Paper Award.
Research Experience
- - Main research areas include bio-inspired machine learning, Sequential Probability Ratio Test (SPRT), density ratio estimation, etc.
- - Research work combines deep neural networks with advanced density ratio estimation techniques, extending Wald’s algorithm to address more complex scenarios.
Background
- A neuroscience Ph.D. working in the field of machine learning / computer vision. An orchid enthusiast. A father of sons.
Miscellany
- Hobbies: Orchid cultivation
