FURUYA Takahiko 古屋貴彦

Researcher Number	00770835
Other IDs
Affiliation (Current)	2025: 山梨大学, 大学院総合研究部, 准教授
Affiliation (based on the past Project Information) *help	2022 – 2024: 山梨大学, 大学院総合研究部, 准教授 2017 – 2022: 山梨大学, 大学院総合研究部, 助教 2016: 山梨大学, 総合研究部, 助教
Review Section/Research Field	Principal Investigator Basic Section 61010:Perceptual information processing-related / Multimedia database Except Principal Investigator Basic Section 60080:Database-related / Basic Section 22040:Hydroengineering-related
Keywords	Principal Investigator 深層学習 / 形状特徴量 / 自己教師あり学習 / 3次元点群 / ファインチューニング / 教師なし学習 / 3次元形状 / 機械学習 / 情報検索 / 局所特徴量 … More / 3次元形状特徴量 / キーワードタグ付与 / 3次元モデル検索 / 3次元形状解析 / キーワード検索 / 部分検索 / 3次元形状類似検索 … More Except Principal Investigator 深層学習 / 機械学習 / computer vision / 3D形状比較 / 3次元形状検索 / 3次元形状解析 / 教師無し学習 / ディープラーニング / 3次元形状類似比較 / マルチメディア検索 / マルチモーダルクエリ / 部分3D形状検索 / 拡散距離 / トランスフォーマー / 3次元点群トランスフォーマー / 3次元形状類似検索 / 3次元点群形状再構成 / 3次元点群解析 / 自己教師あり学習 / transformer / feature representation / self-supervised learning / deep learning / multimodal retrieval / 3D shape analysis / 降雨予測 / 数値気象モデル / machine learning / multimedia retrieval / 3D shape recognition / 3D shape retrieval / データ拡張 / スケッチ検索 / 3次元形状のラベル付け / 部分3次元形状比較 / 深層ニューラルネットワーク / 3D形状領域分割 / 3D形状識別 / 部分3D形状比較 / 3次元形状領域分割 / 3次元部分形状検索 / deep neural network / 3次元点群データ解析 Less

多用途にファインチューニング可能な3次元点群向け大規模解析モデルの開発と活用Principal Investigator
- Principal Investigator
  
  古屋貴彦
- Project Period (FY)
  2024 – 2026
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  University of Yamanashi
Part-based 3D shape retrieval using multi-modal query
- Principal Investigator
  
  Ohbuchi Ryutarou
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 60080:Database-related
- Research Institution
  University of Yamanashi
Unsupervised learning of general-purpose 3D shape feature and its application to analysis of minority 3D shapesPrincipal Investigator
- Principal Investigator
  
  FURUYA Takahiko
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  University of Yamanashi
Development of a heavy rainfall prediction method combining numerical weather prediction models and deep learning methods
- Principal Investigator
  
  Souma Kazuyoshi
- Project Period (FY)
  2019 – 2022
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Review Section
  
  Basic Section 22040:Hydroengineering-related
- Research Institution
  University of Yamanashi
Retrieval and detection of 3D shapes based on details of their parts
- Principal Investigator
  
  OHBUCHI Ryutarou
- Project Period (FY)
  2018 – 2020
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 60080:Database-related
- Research Institution
  University of Yamanashi
Part-based 3D model retrieval queried by keywords representing partsPrincipal Investigator
- Principal Investigator
  
  FURUYA Takahiko
- Project Period (FY)
  2016 – 2018
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Multimedia database
- Research Institution
  University of Yamanashi

All 2024 2023 2022 2021 2020 2019 2018 2017 2016

All Journal Article Presentation

[Journal Article] Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation2024
- Author(s)
  Takahiko Furuya, Zhoujie Chen, Ryutarou Ohbuchi, Zhenzhong Kuang
- Journal Title
  
  Computer Vision and Image Understanding
  
  Volume: 244 Pages: 104025-104025
- DOI
  10.1016/j.cviu.2024.104025
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K11903, KAKENHI-PROJECT-21K17763
[Journal Article] 自己注意機構を用いた3次元点群の回転不変な解析2023
- Author(s)
  刈込喜大, 古屋貴彦, 大渕竜太郎
- Journal Title
  
  画像電子学会誌
  
  Volume: 52(4) Pages: 516-526
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K11903
[Journal Article] 自己注意機構を用いた,3次元点群形状の回転不変な解析2023
- Author(s)
  刈込喜大，古屋貴彦，大渕竜太郎
- Journal Title
  
  画像電子学会誌
  
  Volume: 52 Pages: 516-526
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K17763
[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-Adapted Representations via Diffusion-Based Ranking on Latent Feature Manifold2022
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Journal Title
  
  IEEE Access
  
  Volume: 10 Pages: 116287-116301
- DOI
  10.1109/access.2022.3218909
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K11903, KAKENHI-PROJECT-21K17763, KAKENHI-PROJECT-19H02246
[Journal Article] Hyperplane patch mixing-and-folding decoder and weighted chamfer distance loss for 3D point set reconstruction2022
- Author(s)
  Takahiko Furuya, Wujie Liu, Ryutarou Ohbuchi, Zhenzhong Kuang
- Journal Title
  
  The Visual Computer
  
  Volume: 0 Issue: 10 Pages: 1-18
- DOI
  10.1007/s00371-022-02652-6
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-21K11903, KAKENHI-PROJECT-21K17763, KAKENHI-PROJECT-19H02246
[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold2021
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Journal Title
  
  arXiv preprint
  
  Volume: 2112.07082
- Open Access
- Data Source
  KAKENHI-PROJECT-21K17763
[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold2021
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Journal Title
  
  arXiv
  
  Volume: arXiv:2112.07082 Pages: 1-19
- Open Access
- Data Source
  KAKENHI-PROJECT-21K11903
[Journal Article] ショートカット接続を含む深層学習による数値気象モデル降水量予測補正の検討2020
- Author(s)
  倉上健, 相馬一義, 宮本崇, 古屋貴彦, 馬籠純, 石平博
- Journal Title
  
  土木学会論文集G（環境）
  
  Volume: 76 (5)
- NAID
  130007970704
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H02246
[Journal Article] Convolution on Rotation-invariant and Multi-scale Feature Graph for 3D Point Set Segmentation2020
- Author(s)
  Takahiko Furuya, Xu Hang, Ryutarou Ohbuchi, Jinliang Yao
- Journal Title
  
  IEEE Access
  
  Volume: 8 Pages: 140250-140260
- DOI
  10.1109/access.2020.3012613
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-19H02246, KAKENHI-PROJECT-18K11313
[Journal Article] Scale Adaptive Feature Pyramid Networks for 2D Object Detection2020
- Author(s)
  He Lifei、Jiang Ming、Ohbuchi Ryutarou、Furuya Takahiko、Zhang Min、Li Pengfei
- Journal Title
  
  Scientific Programming
  
  Volume: 2020 Pages: 1-8
- DOI
  10.1155/2020/8839979
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] Transcoding across 3D shape representations for unsupervised learning of 3D shape feature2020
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Journal Title
  
  Pattern Recognition Letters
  
  Volume: 138 Pages: 146-154
- DOI
  10.1016/j.patrec.2020.07.012
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19H02246, KAKENHI-PROJECT-18K11313
[Journal Article] Cascaded Multi-Channel Feature Fusion for Object Detection2020
- Author(s)
  He Lifei、Ohbuchi Ryutarou、Jiang Ming、Furuya Takahiko、Zhang Min
- Journal Title
  
  Proc. ICCCV'20: 2020 the 3rd International Conference on Control and Computer Vision
  
  Volume: 0 Pages: 11-16
- DOI
  10.1145/3425577.3425580
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] 敵対的生成ネットワークを用いた3次元点群形状特徴量の教師なし学習2019
- Author(s)
  上西和樹, 古屋貴彦, 大渕竜太郎
- Journal Title
  
  情報処理学会論文誌
  
  Volume: Vol.60, No.7 Pages: 1315-1324
- NAID
  170000150489
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19H02246
[Journal Article] Data augmentation via photo-to-sketch translation for sketch-based image retrieval2019
- Author(s)
  Furuya Takahiko、Ohbuchi Ryutarou
- Journal Title
  
  Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
  
  Volume: 1106925 Pages: 69-69
- DOI
  10.1117/12.2524230
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] Feature set aggregator: unsupervised representation learning of sets for their comparison2019
- Author(s)
  Furuya Takahiko、Ohbuchi Ryutarou
- Journal Title
  
  Multimedia Tools and Applications
  
  Volume: 78 Issue: 24 Pages: 35157-35178
- DOI
  10.1007/s11042-019-08078-y
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K11313, KAKENHI-PROJECT-19H02246
[Journal Article] 深層学習を用いた降水短期予測における数値気象モデル出力補正手法の構築2019
- Author(s)
  倉上健, 相馬一義, 宮本崇, 古屋貴彦, 馬籠純, 石平博
- Journal Title
  
  土木学会論文集G（環境）
  
  Volume: 75 (5)
- NAID
  130007821973
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19H02246
[Journal Article] Query by Partially-Drawn Sketches for 3D Shape Retrieval2019
- Author(s)
  S. Kuwabara, R. Ohbuchi and T. Furuya
- Journal Title
  
  Proc. 2019 International Conference on Cyberworlds (CW),
  
  Volume: - Pages: 69-76
- DOI
  10.1109/cw.2019.00020
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] 敵対的生成ネットワークを用いた3次元点群形状特徴量の教師なし学習2019
- Author(s)
  上西和樹, 古屋貴彦, 大渕竜太郎
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 60 Pages: 1315-1324
- NAID
  170000150489
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] 敵対的生成ネットワークを用いた，3 次元点群形状特徴量の教師なし学習2019
- Author(s)
  上西和樹，古屋貴彦，大渕竜太郎
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 印刷中
- NAID
  170000150489
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16K16055
[Journal Article] Annotating 3D Models and Their Parts via Deep Feature Embedding2019
- Author(s)
  Omata Kouki、Furuya Takahiko、Ohbuchi Ryutarou
- Journal Title
  
  Proc. 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  
  Volume: - Pages: 489-494
- DOI
  10.1109/icmew.2019.00090
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] 敵対的生成ネットワークを用いた，3次元点群形状特徴量の教師なし学習2018
- Author(s)
  上西和樹, 古屋貴彦, 大渕竜太郎
- Journal Title
  
  研究報告コンピュータグラフィックスとビジュアル情報学（CG）
  
  Volume: 2018-CG-170 Pages: 1-7
- NAID
  170000150489
- Data Source
  KAKENHI-PROJECT-18K11313
[Journal Article] Learning part-in-whole relation of 3D shapes for part-based 3D model retrieval2018
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Journal Title
  
  Computer Vision and Image Understanding (CVIU)
  
  Volume: 166 Pages: 102-114
- DOI
  10.1016/j.cviu.2017.11.007
- Peer Reviewed / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] 深層学習を用いた点群処理（中/上級）2023
- Author(s)
  古屋貴彦
- Organizer
  精密工学会，大規模環境の３次元計測と認識・モデル化技術専門委員会，技術講習会
- Invited
- Data Source
  KAKENHI-PROJECT-21K17763
[Presentation] 自己注意機構を用いた，3次元点群形状の回転不変な解析2022
- Author(s)
  刈込喜大，古屋貴彦，大渕竜太郎
- Organizer
  画像電子学会 VCワークショップ2022
- Data Source
  KAKENHI-PROJECT-21K11903
[Presentation] 深層学習を用いた点群処理（中/上級）2022
- Author(s)
  古屋貴彦
- Organizer
  大規模環境の３次元計測と認識・モデル化技術専門委員会，点群処理基礎技術講習会
- Invited
- Data Source
  KAKENHI-PROJECT-21K17763
[Presentation] 自己注意機構を用いた3次元点群形状の解析2021
- Author(s)
  刈込喜大, 大渕竜太郎, 古屋貴彦
- Organizer
  画像の認識・理解シンポジウム MIRU2021 （I11-16）
- Data Source
  KAKENHI-PROJECT-21K11903
[Presentation] 深層学習を用いた点群処理（中級）・3次元点群深層学習の解説と実践2021
- Author(s)
  古屋貴彦
- Organizer
  大規模環境の３次元計測と認識・モデル化技術専門委員会技術講習会
- Invited
- Data Source
  KAKENHI-PROJECT-21K17763
[Presentation] 自己注意機構を用いた3次元点群形状の解析2021
- Author(s)
  刈込喜大, 大渕竜太郎, 古屋貴彦
- Organizer
  画像の認識・理解シンポジウム（MIRU）2021
- Data Source
  KAKENHI-PROJECT-19H02246
[Presentation] ショートカット接続を含む深層学習による数値気象モデル降水量予測補正の検討2020
- Author(s)
  倉上健, 相馬一義, 宮本崇, 古屋貴彦, 馬籠純, 石平博
- Organizer
  第28回地球環境シンポジウム
- Data Source
  KAKENHI-PROJECT-19H02246
[Presentation] 向きずれの反復最小化による3次元形状向き合わせ2020
- Author(s)
  和智知幸，西川哲平，古屋貴彦，大渕竜太郎
- Organizer
  第23回画像の認識・理解シンポジウム (MIRU 2020)
- Data Source
  KAKENHI-PROJECT-19H02246
[Presentation] 特徴からの形状再構成で教師なし学習する3次元形状特徴量2019
- Author(s)
  青木祐樹, 古屋貴彦, 大渕竜太郎
- Organizer
  第25回画像センシングシンポジウム（SSII 2019）
- Data Source
  KAKENHI-PROJECT-19H02246
[Presentation] ANNOTATING 3D MODELS AND THEIR PARTS VIA DEEP FEATURE EMBEDDING2019
- Author(s)
  Kouki Omata, Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  IEEE International Conference on Multimedia and Expo 2019 workshop
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] 3次元点群のためのmixupデータ拡張を用いた形状識別DNNの効果的学習2019
- Author(s)
  村松恭平, 古屋貴彦, 大渕竜太郎
- Organizer
  第25回画像センシングシンポジウム（SSII 2019）
- Data Source
  KAKENHI-PROJECT-19H02246
[Presentation] 敵対的生成ネットワークを用いた，3次元点群形状特徴量の教師なし学習2018
- Author(s)
  上西和樹, 古屋貴彦, 大渕竜太郎
- Organizer
  コンピュータグラフィックスとビジュアル情報学 (CG) 研究会
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] Data Augmentation via Photo-to-Sketch Translation for Sketch-based Image Retrieval2018
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  International Conference on Graphics and Image Processing (ICGIP) 2018
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] Deep semantic hashing of 3D geometric features for efficient 3D model retrieval2017
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  Computer Graphics International Conference (CGI) 2017
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] 形の詳細を考慮した，手描きスケッチによる3Dモデル検索2017
- Author(s)
  桑原周太郎, 古屋貴彦, 大渕竜太郎
- Organizer
  Visual Computing/グラフィクスとCAD合同シンポジウム 2017
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] 深層学習を用いた3Dモデルへのキーワードタグ付与2017
- Author(s)
  小俣幸紀, 古屋貴彦, 大渕竜太郎
- Organizer
  Visual Computing/グラフィクスとCAD合同シンポジウム 2017
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval2016
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  British Machine Vision Conference (BMVC) 2016
- Place of Presentation
  University of York, UK
- Year and Date
  2016-09-19
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] Accurate Aggregation of Local Features by using K-sparse Autoencoder for 3D Model Retrieval2016
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  ACM International Conference on Multimedia Retrieval (ICMR) 2016
- Place of Presentation
  Columbia University, New York, USA
- Year and Date
  2016-06-06
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055
[Presentation] Aggregating sparse binarized local features by summing for efficient 3D model retrieval2016
- Author(s)
  Takahiko Furuya, Ryutarou Ohbuchi
- Organizer
  IEEE International Conference on Multimedia Big Data (BigMM) 2016
- Place of Presentation
  Howard Civil Service International House, Taipei, Taiwan
- Year and Date
  2016-04-20
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K16055

1. OHBUCHI Ryutarou (80313782)

# of Collaborated Projects: 2 results

# of Collaborated Products: 15 results
2. Souma Kazuyoshi (40452320)

# of Collaborated Projects: 1 results

# of Collaborated Products: 3 results
3. 宮本崇 (30637989)

# of Collaborated Projects: 1 results

# of Collaborated Products: 3 results
4. 馬籠純 (70377597)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
5. 石平博 (80293439)

# of Collaborated Projects: 1 results

# of Collaborated Products: 3 results
6. 馬篭純

# of Collaborated Projects: 0 results

# of Collaborated Products: 3 results

FURUYA Takahiko 古屋 貴彦

Research Projects

Research Products

Co-Researchers

多用途にファインチューニング可能な3次元点群向け大規模解析モデルの開発と活用Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Part-based 3D shape retrieval using multi-modal query

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Unsupervised learning of general-purpose 3D shape feature and its application to analysis of minority 3D shapesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Development of a heavy rainfall prediction method combining numerical weather prediction models and deep learning methods

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Retrieval and detection of 3D shapes based on details of their parts

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Part-based 3D model retrieval queried by keywords representing partsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

[Journal Article] Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] 自己注意機構を用いた3次元点群の回転不変な解析2023

Author(s)

Journal Title

Data Source

[Journal Article] 自己注意機構を用いた,3次元点群形状の回転不変な解析2023

Author(s)

Journal Title

Data Source

[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-Adapted Representations via Diffusion-Based Ranking on Latent Feature Manifold2022

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Hyperplane patch mixing-and-folding decoder and weighted chamfer distance loss for 3D point set reconstruction2022

Author(s)

Journal Title

DOI

Data Source

[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold2021

Author(s)

Journal Title

Data Source

[Journal Article] DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold2021

Author(s)

Journal Title

Data Source

[Journal Article] ショートカット接続を含む深層学習による数値気象モデル降水量予測補正の検討2020

Author(s)

Journal Title

NAID

Data Source

[Journal Article] Convolution on Rotation-invariant and Multi-scale Feature Graph for 3D Point Set Segmentation2020

Author(s)

Journal Title

DOI

FURUYA Takahiko 古屋貴彦