Yusuke Hirota
I am a final-year PhD student in the Graduate School of Information Science and Technology at Osaka University and a member of ISLab.
I work with Prof. Yuta Nakashima and Prof. Noa Garcia on the intersection of computer vision and natural language processing (Vision-and-Language).
My research interests are fairness in vision-and-language tasks, focusing on identifying societal biases in datasets and models (CVPR'22, FAccT'22, CVPR'23, CVPR'24) and developing bias mitigation strategies (CVPR'23).
I am actively looking for research positions in the industry or academia starting in 2025. If my research aligns with your interests, I welcome the opportunity to discuss potential collaborations. Please feel free to contact me.
News
[03/2024] A paper accepted at CVPR 2024.
[12/2023] Started an internship at NVIDIA Research.
[04/2023] Started an internship at Sony AI.
[03/2023] Our paper "Uncurated Image-Text Datasets: Shedding Light on Demographic Bias" has been selected as a highlight at CVPR 2023.
[02/2023] Two papers are accepted at CVPR 2023.
[04/2022] A paper accepted at ACM FAccT 2022.
[03/2022] A paper accepted at CVPR 2022 as an oral.
[07/2021] A paper accepted at ICCV CLVL 2021.
Publications
Papers
From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment
Yusuke Hirota, Ryo Hachiuma, Chao-Han Huck Yang, Yuta Nakashima
preprintWould Deep Generative Models Amplify Bias in Future Models?
Tianwei Chen, Yusuke Hirota, Mayu Otani, Noa Garcia, Yuta Nakashima
CVPR 2024Model-Agnostic Gender Debiased Image Captioning
Yusuke Hirota, Yuta Nakashima, Noa Garcia
CVPR 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
Noa Garcia, Yusuke Hirota, Yankun Wu, Yuta Nakashima
CVPR 2023, HighlightQuantifying Societal Bias Amplification in Image Captioning
Yusuke Hirota, Yuta Nakashima, Noa Garcia
CVPR 2022, OralGender and Racial Bias in Visual Question Answering Datasets
Yusuke Hirota, Yuta Nakashima, Noa Garcia
ACM FAccT 2022Visual Question Answering with Textual Representations for Images
Yusuke Hirota, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Ittetsu Taniguchi, Takao Onoye
ICCV CLVL 2021A Picture May Be Worth a Hundred Words for Visual Question Answering
Yusuke Hirota, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Ittetsu Taniguchi, Takao Onoye
preprint
Education
Apr. 2022 ~ Present Ph.D. School of Information Science and Technology, Osaka University, Japan.
Apr. 2020 ~ Mar. 2022 M.S. School of Information Science and Technology, Osaka University, Japan.
Apr. 2016 ~ Mar. 2020 B.S. School of Engineering, Osaka University, Japan.
Work Experience
Dec. 2023 ~ Present NVIDIA Research, Remote.
Apr. 2023 ~ Sep. 2023 Sony AI (AI Ethics Team), Remote.
Apr. 2022 ~ Present Research Assistant, Osaka University, Japan.
Reviewer
Conferences: CVPR ('23, '24), ICCV'23, ECCV'24
Journals: IEEE TPAMI
Skills
Programming Languages: Python
Software: Pytorch, Docker, Git, Latex
Languages: English (intermediate), Japanese (native)
Contact
Email: y-hirota [at] is [dot] ids [dot] osaka-u.ac.jp