Kaede Shiohara

I am a PhD student at Computer Vision and Media Lab.
I am mainly working on face recognition, generation, and forensics for human content creation.
I am looking for a full-time research scientist position from April 2025. Please contact me by e-mail if you are interested.

CV / Email / Google Scholar / Twitter / Github

Education

The University of Tokyo
Ph.D. in Graduate School of Information Science and Technology
Department of Information and Communication Engineering
Supervisor: Prof. Toshihiko Yamasaki
2022.4 - Present

The University of Tokyo
M.S. in Graduate School of Information Science and Technology
Department of Information and Communication Engineering
Supervisor: Prof. Toshihiko Yamasaki
2020.4 - 2022.3

Osaka City University
B.S. in Under Graduate School of Engineering
Department of Electrical and Information Engineering
Supervisor: Prof. Kazunori Hayashi
2015.4 - 2019.3

Experience

MPI for Informatics
Computer Vision Research Intern
Supervisor: Vladislav Golyanik
2023.11 - Present

CyberAgent AI Lab
Computer Vision Research Intern
Mentor: Xingchao Yang
2022.8 - 2023.10

Selected Publications

PetFace: A Large-Scale Dataset and Benchmark for Animal Identification
Risa Shinoda*, Kaede Shiohara* (*Equal contribution)
European Conference on Computer Vision (ECCV), Oral, 2024.
[Paper] [Code] [Webpage]

teaser

Face2Diffusion for Fast and Editable Face Personalization
Kaede Shiohara, Toshihiko Yamasaki
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[Paper] [Code] [Webpage]

teaser

BlendFace: Re-designing Identity Encoders for Face-Swapping
Kaede Shiohara, Xingchao Yang, Takafumi Taketomi
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
[Paper] [Code] [Webpage]
Work done during an internship at CyberAgent AI Lab

teaser

Detecting Deepfakes with Self-Blended Images
Kaede Shiohara, Toshihiko Yamasaki
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2022.
[Paper] [Code] [UTokyo (ENG) / (JPN)]

teaser

Invited Talk

In Symposium on Sensing via Image Information (SSII) 2024
Topic: Identity-Preserving Face Generation

In Visual Computing (VC) 2023
Topic: Face-Swapping

In Visual Computing (VC) 2022
Topic: Deepfake Detection

In Meeting on Image Recognition and Understanding (MIRU) 2022
Topic: Deepfake Detection

Award

IEEE CS Tokyo/Japan Joint Local Chapters Young Author Award 2024
[Webpage]

Telecom System Technology Award 2022
[Webpage]

Hiroshi Harashima Academic Honorable Award 2022
[Webpage]

IE 2022.2 Best Paper Award
[Webpage]

1st place at 6th Brain(s) Contest by FUJIFILM AI Academy Brain(s)
[Webpage]

SIGNATE Competition Master
[Webpage]

Media

newsランナー
2023.7.26 TV Kansai
[Webpage]

60秒で学べるNews: AIが生むフェイク
2023.1.25 TV Tokyo
[Webpage]

報道の日2022
2022.12.18 Tokyo Broadcasting System (TBS) Television
[Webpage]

フェイク動画を見つけ出す高性能AI
子供の科学2022年7月号
[Webpage]

ディープフェイク見破れ　東大開発で脚光　「合成の跡」の見つけ方
2022.7.6 毎日新聞電子版, 2022.7.7 紙面版
[Webpage]

偽動画、東京大学は検出精度9割　米メタも封じ込め急ぐ
2022.6.6 日経新聞電子版, 2022.6.7 紙面版16面
[Webpage]

ディープフェイクの検出で世界最高性能を達成～SBIsでディープフェイク動画の高精度判定を可能に～
2022.4.6 東京大学プレスリリース
[Webpage]

Other Infomation

Reviewer Experience
CVPR'23 / ICCV'23 / CVPR'24 / ECCV'24