Risa Shinoda
Risa Shinoda
New Homepage→https://dahlian00.github.io/
Embedded Files
I am an Assistant Professor at the University of Tokyo, Yoichi Sato Lab.
I received my Ph.D. in Agricultural Engineering at Kyoto University in 2025, M.S. in Agricultural Engineering at Kyoto University in 2022, and my B.S. in Agricultural Engineering at Kyoto University in 2020.
Contact: rshinoda[at] iis.u-tokyo.ac.jp
[2026/08/21] One co-authored paper has been accepted to EMNLP 2026 (Main).
[2026/04/10] Our BioVITA has been selected for the CVPR Highlight.
[2026/02/21] One first-author paper has been accepted to CVPR 2026 (Main).
[2026/02/01] One first-author paper has been accepted to ICASSP 2026.
[2026/02/01] Two co-authored papers have been accepted to WACV 2026.
[2025/06/28] Two of my first-author papers have been accepted to ICCV 2025.
[2025/03/20] I contributed a chapter titled CV for Earth to the Japanese book CV最前線 (Frontlines of Computer Vision (共立出版).
[2024/09/26] I will be giving an invited talk at the IRL Workshop at ECCV 2024.
[2024/08/19] Our ECCV paper has been selected for an Oral presentation! (Strong Accept × 3 )
My CV can be downloaded from here .
Research
Research
Selected Publications
Selected Publications
BioVITA: Biological Dataset, Model, and Benchmark for Visual-Textual-Acoustic Alignment
Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Kuniaki Saito, Hiroaki Santo, Fumio Okura
CVPR (Main, Highlight) 2026
[paper] [project page]
AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference
Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura
ICASSP 2026
[paper] [project page]
AnimalClue: Recognizing Animals by their Traces
Risa Shinoda, Nakamasa Inoue, Iro Laina, Christian Rupprecht, Hirokatsu Kataoka
ICCV (Highlight) 2025
[paper] [project page]
AgroBench: Vision-Language Model Benchmark in Agriculture
Risa Shinoda, Nakamasa Inoue, Hirokatsu Kataoka, Masaki Onishi, Yoshitaka Ushiku
ICCV 2025
[paper] [project page]
SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images
Risa Shinoda, Kuniaki Saito, Shohei Tanaka, Tosho Hirasawa, Yoshitaka Ushiku
AAAI WS on Document Understanding and Intelligence 2025
[paper] [project page]
PetFace: A Large-Scale Dataset and Benchmark for Animal Identification
Risa Shinoda*, Kaede Shiohara* (*co-first)
ECCV Oral 2024 (Strong Accept× 3)
[paper] [project page]
OpenAnimalTracks: A Dataset for Animal Track Recognition
Risa Shinoda*, Kaede Shiohara* (*co-first)
ICIP 2024
[paper]
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
Risa Shinoda, Ryo Hayamizu, Kodai Nakashima, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka
ICCV 2023
[paper] [project page]
Others
Others
Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space
Ren Nakagawa, Yang Yang, Risa Shinoda, Hiroaki Santo, Kenji Oyama, Fumio Okura, Takenao Ohkawa
WACV 2026
[paper]
Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention
Junhao Xing, Ryohei Miyakawa, Yang Yang, Xinpeng Liu, Risa Shinoda, Hiroaki Santo, Yosuke Toda, Fumio Okura
WACV 2026
[paper]
Masks-to-Skeleton: Multi-View Mask-Based Tree Skeleton Extraction with 3D Gaussian Splatting
Xinpeng Liu, Kanyu Xu, Risa Shinoda, Hiroaki Santo, Fumio Okura
Sensors 2025
[paper]
Martyna Gruszka, Risa Shinoda, Taiki Miyanishi, Takumi Hirose, Nakamasa Inoue
CVPRW (CV4Edu), 2026
[paper]
Talking with Actionsbits - A Part-Enhanced VLM for Action and Interaction Recognition in Animals
Yang Yang ,Ren Nakagawa, Risa Shinoda ,Hiroaki Santo ,Kenji Oyama ,Takenao Ohkawa , Fumio Okura
Sensors, 2026(IF=3.5)
[paper]
Transformer-based Ripeness Segmentation for Tomatoes
Risa Shinoda, Kensho Hara, Hirokatsu Kataoka, Ryozo Noguchi
SmartAgricultural Technology, Elsevier, 2023 (IF=6.3)
[paper]AnimalTracks-17: A Dataset for Animal Track Recognition
Kaede Shiohara*, Risa Shinoda* (*equal contribution)
CVPR Workshop, CV4Animals, 2023A dataset and system for automated rose growth monitoring
Risa Shinoda, Ko Motoki, Kensho Hara, Hirokatsu Kataoka, Ryohei Nakano, Tetsuya Nakazaki, Ryozo Noguchi
CVPR Workshop, Woman in Computer Vision, 2023
[poster]Exploring the Potential of Neural Dataset Search
Ryosuke Yamada*, Risa Shinoda* (*equal contribution), Hitokatsu Kataoka
CVPR Workshop, NAS Workshop, 2023
[paper]Tomato's Ripeness Segmentor with Transformers
Risa Shioda, Kensho Hara, Hirokatsu Kataoka
CVPR Workshop, Vision for Agriculture, 2022.
Awards and Grants
Awards and Grants
Grant-in-Aid for Research Activity Start-up（科研費 研究活動スタート支援）, 動物の個体・種識別を実現する画像認識技術基盤, ￥2,730,000 [link]
Kakusei Project（覚醒プロジェクト）, AIST, 2024, ￥3,000,000 [link]
Student Encouragement Award (学生奨励賞)：MIRU2024 , 2024 [link]
Student Encouragement Award (学生奨励賞)：MIRU2023 , 2023 [link]
Young Researcher Award (若手奨励賞）: セグメンテーションタスクにおける実画像を用いない事前学習, ViEW, 2022 [link]
JSPS Research Fellowship for Young Scientists (DC2), 2022
JST (Japan Science and Technology Agency Pioneering Research Initiated by the Next Generation program), 2022-2025
DoGS Travel Grant, Kyoto University, 2022, ￥355,000
Work Experience
Work Experience
OMRON SINIC X (2023.11 ~2025.03)
Research Internship.Tokyo Institute of Technology, Shinoda Lab (2023.04 ~ 2025.06)
Research Assistant.AIST, Computer Vision team （2022.07~2025.03）
Research AssistantMicrosoft Japan (2022.04~2022.06）
Customer Support EngineerMoney Forward （2021.04~2024.10）
Software Engineer InternMicrosoft Japan（2021.09, 1 month ）
Full-Time Intern, Customer Support EngineerRakuten (2021.01~ 2021.03)
Data Scientist InternshipCyberAgent (2018.09~2018.10)
Business intern, DRAFT 2018 Winner
Invited Talks
Invited Talks
ECCV Instance Level Recognition Workshop (2024.09.30)
PetFace: A Large-Scale Dataset and Benchmark for Animal IdentificationQUAD-AI ENGAGE Workshop on AI and Digital Agriculture (2025.06.17)
Large Dataset and Model for AI in EcologyFIT: Forum on Information Technology (2025.09.03)
Computer Vision for Animals, 篠田理沙Food Production Technology Research Committee (RC93) 36th workshop (2025.12.09)
Vison and Language Models for Agriculture
Media
Media
NHKニュース (2025/08/26) 足跡やふんなどの画像から動物を推定するAIモデル開発 [Link]
産総研 (AIST) プレスリリース （2023/09/29）数式から実画像や人的コスト不要で画像領域分割AIを自動学習 [link]
MISC
MISC
Best of ICCV, Voxel51, AnimalClue: Recognizing Animals by their Traces [Link]
5分で分かる!? 有名論文ナナメ読み：Niewiadomski, T. et al. : Generative Zoo [Link]
CV最前線 (Book, 共立出版）, CV for Earth [Link]
PodCast, Open Animal Tracks, dataskeptic [Link]
CVPR 2023 ショート速報 , 光産業技術振興協会, 国際会議速報
CVPR2023 速報 [pdf]
大規模言語・視覚モデルを用いたロボティクス基盤モデル, 2023 [pdf]
CVPR2022 ショート速報, 光産業技術振興協会, 国際会議速報
Video Transformer, 2023 [Slide]
Page updated
Google Sites
Report abuse