Sign in

Hirokatsu Kataoka | 片岡裕雄

@hirokatukataoka.bsky.social
144 followers 167 following 59 posts

Chief Scientist @ AIST | Academic Visitor @ Oxford VGG | PI @ cvpaper.challenge | 3D ResNet (Top 0.5% in 5-yr CVPR) | FDSL (ACCV20 Award/BMVC23 Award Finalist)

PostsRepliesMedia
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 10/03/2026
We're very happy to share our S3OD (1. Scaling, 2. Synthetic, & 3. Salient Object Detection)! The paper has been accepted at #ICLR2026. You can get the paper, demo, code, trained models, and dataset on the project page. s3odproject.github.io
030
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 12/01/2026
I published this paper, "Pre-training Vision Transformer with Formula-driven Supervised Learning," after journal paper rejections. This work was actually completed three years ago, but it's worth publicly sharing with the academic community. arxiv.org/abs/2206.091...
110
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 22/12/2025
[#CVPR2026 Workshop] Excited to announce that our workshop "Visual General Intelligence (VGI): Vision Research Toward the AGI Era" has been accepted at CVPR 2026! Please also check out the website & blog! Website: cvpr2026-vgi-workshop.limitlab.xyz Blog: hirokatsukataoka.medium.com/vision-resea...
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 05/12/2025
Slides from my #BMVC2025 talk are now available! hirokatsukataoka.net/temp/presen/... This includes the following papers: - Industrial Synthetic Segment Pre-training arxiv.org/abs/2505.13099 - S3OD: Towards Generalizable Salient Object Detection with Synthetic Data arxiv.org/abs/2510.21605
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 05/12/2025
Released HanDyVQA, ego-centric QAs for fine-grained hand-object interaction with 11.1K QAs, 10.3K segmentation masks in 112 domains. Even Gemini-2.5-Pro reaches 73% & 97% human score, revealing key issue in space-time task. Project: masatate.github.io/HanDyVQA-pro...
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 04/12/2025
We have publicly shared our "PowerCLIP," a method to align powersets of image sub-region with textual structures for precise image-text recognition. Outperforms several SotA in zero-shot classification, retrieval, robustness, and compositional tasks! arxiv.org/abs/2511.23170
051
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 04/12/2025
[ #NeurIPS2025 Spotlight ] We're very excited to share our "Domain Unlearning," this is a collaboration between Irie Lab, TUS & AIST. Selectively removing domain-specific knowledge from trained models. - Project: kodaikawamura.github.io/Domain_Unlea... - Paper: arxiv.org/abs/2510.08132
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 31/10/2025
We’ve released the ICCV 2025 Report! hirokatsukataoka.net/temp/presen/... Compiled during ICCV in collaboration with LIMIT.Lab, cvpaper.challenge, and Visual Geometry Group (VGG), this report offers meta insights into the trends and tendencies observed at this year’s conference. #ICCV2025
070
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 16/10/2025
I’m planning to attend ICCV 2025 in person! Here are my accepted papers and roles at this year’s #ICCV2025 / @iccv.bsky.social . Please check out the threads below:
131
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 02/10/2025
We organized the "Cambridge Computer Vision Workshop" at the University of Cambridge together with Elliott Wu, Yoshihiro Fukuhara, and LIMIT.Lab! It was a fantastic workshop featuring presentations, networking, and discussions. cambridgecv-workshop-2025sep.limitlab.xyz
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 02/10/2025
Finally, the accepted papers at #ICCV2025 / @iccv.bsky.social LIMIT Workshop has been publicly released! -- - OpenReview: openreview.net/group?id=the... - Website: iccv2025-limit-workshop.limitlab.xyz
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 17/09/2025
At ICCV 2025, I am organizing two workshops: the LIMIT Workshop and the FOUND Workshop. ◆ LIMIT Workshop (19 Oct, PM): iccv2025-limit-workshop.limitlab.xyz ◆ FOUND Workshop (19 Oct, AM): iccv2025-found-workshop.limitlab.xyz We warmly invite you to attend at these workshops in ICCV 2025 Hawaii!
161
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 02/09/2025
I’m thrilled to announce my invited talk at BMVC 2025 Smart Cameras for Smarter Autonomous Vehicles and Robots! supercamerai.github.io
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 03/08/2025
Our AnimalClue has been accepted to #ICCV2025 as a highlight🎉🎉🎉 We also released an official press release from AIST!! This is the collaboration between AIST x Oxford VGG. Project page: dahlian00.github.io/AnimalCluePa... Dataset: huggingface.co/risashinoda Press: www.aist.go.jp/aist_j/press...
041
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 03/08/2025
Our AgroBench has been accepted to #ICCV2025 🎉🎉🎉 We released project page, paper, code, and dataset!! Project page: dahlian00.github.io/AgroBenchPage/ Paper: arxiv.org/abs/2507.20519 Code: huggingface.co/datasets/ris... Dataset: github.com/dahlian00/Ag...
021
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 17/06/2025
We’ve released the CVPR 2025 Report! hirokatsukataoka.net/temp/presen/... Compiled during CVPR in collaboration with LIMIT.Lab, cvpaper.challenge, and Visual Geometry Group (VGG), this report offers meta insights into the trends and tendencies observed at this year’s conference. #CVPR2025
hirokatsukataoka.net
110
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 06/06/2025
[LIMIT.Lab Launched] limitlab.xyz We’ve established "LIMIT.Lab" a collaboration hub for building multimodal AI models under limited resources, covering images, videos, 3D, and text, when any resource (e.g., compute, data, or labels) is constrained.
100
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 21/05/2025
“Industrial Synthetic Segment Pre-training” on arXiv! Formula-driven supervised learning (FDSL) has surpassed the vision foundation model "SAM" on industrial data. It delivers strong transfer performance to industry while minimizing IP-related concerns. arxiv.org/abs/2505.13099
030
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 12/05/2025
I’m honored to serve as an Area Chair for CVPR 2025 for the second time. Thank you so much for the support!! cvpr.thecvf.com/Conferences/...
cvpr.thecvf.com
2025 Progam Committee
030
Reposted by Hirokatsu Kataoka | 片岡裕雄
Dima Damen @ECCV 2026 @dimadamen.bsky.social · 29/04/2025
where I apparently asked you to present your poster on 3D ResNet *in 2 minutes* in #CVPR2018... 7 years later, I am very grateful for your *50 minutes* talk and full day visit to my group... Thanks for the personal touch ☺️ 2/2
042
Reposted by Hirokatsu Kataoka | 片岡裕雄
Dima Damen @ECCV 2026 @dimadamen.bsky.social · 29/04/2025
Many thanks @hirokatukataoka.bsky.social for visiting @bristoluni.bsky.social #MaVi group during your stay @oxford-vgg.bsky.social This was a very motivating talk on training from limited synthetic data. Thanks for bringing up our first encounter #CVPR2018 .... 1/2
141
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 11/04/2025
Very excited to announce that our Formula-Driven Supervised Learning (FDSL) series now includes audio modality 🎉🎉🎉 -- Formula-Supervised Sound Event Detection: Pre-Training Without Real Data, ICASSP 2025. - Paper: arxiv.org/abs/2504.04428 - Project: yutoshibata07.github.io/Formula-SED/
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 20/03/2025
Our paper has been published ( lnkd.in/gyuPEWSA ) and issued an AIST press release (JPN: lnkd.in/gyifZauS ) on applying FDSL pre-training for microfossil recognition, showcasing an example of image recognition technology in AI for Science! 🎉🎉🎉 # The shared images are coming from our paper
100
Reposted by Hirokatsu Kataoka | 片岡裕雄
Jianyuan Wang @jianyuanwang.bsky.social · 17/03/2025
Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! Project Page: vgg-t.github.io Code & Weights: github.com/facebookrese...
34514
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 07/02/2025
[ Reached 5,000 Citations! 🎉🎉🎉 ] My research has reached 5,000 citations on Google Scholar! This wouldn’t have been possible without the support of my co-authors, colleagues, mentors, and the entire research community. Looking forward to the next phase of collaboration! 🙌
020
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 04/02/2025
[New pre-training / augmentation dataset] MoireDB – a formula-generated interference-fringe image dataset for synthetic pre-training and data augmentation 🎉🎉🎉 Paper: arxiv.org/abs/2502.01490
131
Reposted by Hirokatsu Kataoka | 片岡裕雄
Jeff Dean @jeffdean.bsky.social · 24/01/2025
Demis Hassabis, James Manyika, and I wrote up an overview of the AI research work & advances across Google in 2024 (Gemini, NotebookLM, robotics, ML for science, & advances in responsible AI+more). 🎊 Given it a read or paste it into NotebookLM to listen, if you prefer! blog.google/technology/a...
blog.google
2024: A year of extraordinary progress and advancement in AI
As we move into 2025, we’re looking back at the astonishing progress in AI in 2024.
212423
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 25/01/2025
[ Research Paper Award🏅] Our paper, "Efficient Load Interference Detection with Limited Labeled Data," has won the SICE International Young Authors Award (SIYA) 2025🎉🎉🎉 This work is the family of FDSL pre-training and its real-world application in advanced logistics using forklists.
100
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 23/01/2025
Our ICCV 2023 paper "SegRCDB" has reached 10 citations on Google Scholar! 🎉 We have proposed 'Synthetic Pre-training for Segmentation', establishing a strong baseline. - Project: dahlian00.github.io/SegRCDBPage/ - GitHub: github.com/dahlian00/Se... - Paper: openaccess.thecvf.com/content/ICCV...
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 20/01/2025
Excited to announce that our paper, "Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding ( arxiv.org/abs/2501.09278 )", is now available on arXiv pre-print 🎉🎉🎉 We propose a framework for generation-enhanced 3D dataset expansion, targeting zero-shot 3D understanding.
100
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 14/01/2025
🎉 Updated Intro Slides (Jan 2025) 🎉 📈 Most-cited work: Space-time 3D ResNet 🔬 Most-active Projects: FDSL (ACCV Award & BMVC Award Finalist; MIT Tech Review) 🎯 Current Focus: LIMIT (Building AI with Very Limited Resources) 🌍 Academic & Industry Service Slide: hirokatsukataoka.net/pdf/250114Se...
hirokatsukataoka.net
100
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 06/01/2025
アドカレ2024完成🎉🎉🎉 2024年12月実施の "cvpaper.challenge Advent Calendar 2024" が完成しました!今回は「広がる研究コミュニティ」がテーマです。 adventar.org/calendars/10... 片岡の担当記事 - オックスフォード大学研究記 note.com/cvpaperchall... - 非営利研究コミュニティを10年継続させる... note.com/cvpaperchall... - Towards trust and depth...(日本語訳担当) note.com/cvpaperchallen
000
Reposted by Hirokatsu Kataoka | 片岡裕雄
Kosta Derpanis @csprofkgd.bsky.social · 05/01/2025
Interesting, it appears the #ICCV2025 submission and supplementary materials deadlines are the SAME.
3183
Reposted by Hirokatsu Kataoka | 片岡裕雄
Kosta Derpanis @csprofkgd.bsky.social · 06/01/2025
and part 2 go.bsky.app/Gjcs339
021
Reposted by Hirokatsu Kataoka | 片岡裕雄
Omer Shapira @omershapira.com · 06/01/2025
Here’s a decent Vision / Graphics list: go.bsky.app/M7HGC3Y
121
Reposted by Hirokatsu Kataoka | 片岡裕雄
Kosta Derpanis @csprofkgd.bsky.social · 21/12/2024
New to Bsky and interested in #computervision? Check out my 2 Starter Packs of #computervision researchers. go.bsky.app/M7HGC3Y go.bsky.app/Gjcs339
13817
Reposted by Hirokatsu Kataoka | 片岡裕雄
Elliott / Shangzhe Wu @elliottwu.bsky.social · 28/11/2024
I'm building a new research lab @ Uni of Cambridge focusing on 4D computer vision and generative models. Interested in joining us as a PhD student? Apply to the Engineering program by Dec 3 🗓️ www.postgraduate.study.cam.ac.uk/courses/dire... ChatGPT's "portrait of my current life"👇 elliottwu.com
0176
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 12/12/2024
I excited to share the two papers at #ACCV2024, focusing on "Synthetic Training for Segmentation" and "Real-World Image Super-Resolution" !! 🎉🎉🎉 Synthetic Training for Segmentation openaccess.thecvf.com/content/ACCV... Real-World Image Super-Resolution openaccess.thecvf.com/content/ACCV...
openaccess.thecvf.com
ACCV 2024 Open Access Repository
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 08/12/2024
タイトル:オックスフォード大学研究記 筆者:片岡裕雄 研究コミュニティ cvpaper.challenge 〜広がる研究コミュニティー〜 Advent Calendar 2024 初日(2024年12月1日)の記事です!国際連携による研究トレンド創出・研究コミュニティ拡大を目指して数年単位でオックスフォード大学滞在予定です。国際連携の経過や大学研究室での気づきを共有です。 note.com/cvpaperchall...
note.com
オックスフォード大学研究記|cvpaper.challenge
はじめに cvpaper.challenge PI 片岡裕雄です。当記事は 研究コミュニティ cvpaper.challenge 〜広がる研究コミュニティー〜 Advent Calendar 2024 [Link]の12/1分の記事として公開しています。現在、英国・オックスフォードに来ており、オックスフォード大学では Academic Visitor として活動しています。 2024年9月よ...
000
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 06/12/2024
Our paper "Deformability-based grasp pose detection from a visible image" has been accepted to IEEE Access! 🎉🎉🎉 We introduce the concept of 'deformability', making it easier for robots to grasp objects effectively. Paper here: ieeexplore.ieee.org/document/107...
021
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 05/12/2024
「Data-centric AI入門(技術評論社)」の監修を担当させて頂きました。AI基盤モデルの昨今、Transformerなどモデルの選択肢が固定化されつつある中、データに主眼を置く重要性が益々増しています。"データ中心のAI時代" の入門書なれば幸いです。 なお、主に概要・画像・言語・ロボット・産業応用等の実践に分けて章立て、各分野錚々たる研究者により執筆されています。 gihyo.jp/book/2025/97...
gihyo.jp
Data-centric AI入門
Data-centric AIとは,機械学習の権威でありGoogleのAI研究チームを率いたAndrew Ngが2021年に提唱した,モデルよりもデータに主眼を置くというAI開発のアプローチです。過去数十年にわたりAI開発においては,固定されたデータセットに対してニューラルネットワークをはじめとしたモデルを適用し,そのモデルを改善することに関心が寄せられていました。しかし,このモデルを中心としたア...
022
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 03/12/2024
We introduced an empirical study in Smart Agricultural Technology (2023), Transformer segmentation in agricultural scenes. We verified Swin Transformer outperforms ResNet for tomato segmentation, especially with larger images and data augmentation. www.sciencedirect.com/science/arti...
010
Hirokatsu Kataoka | 片岡裕雄 @hirokatukataoka.bsky.social · 03/12/2024
Thank you so much for Yuki M. Asano and all attendees in the join workshop among FunAILab at UTN 🇩🇪, FAU 🇩🇪, and AIST 🇯🇵. We further accelerate the research collaboration including University of Oxford 🇬🇧, and join us if you're interested in our work. @yukimasano.bsky.social
040