• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

文字を介した視覚的コミュニケーション基盤の創成

Research Project

Project/Area Number 22H00540
Research Category

Grant-in-Aid for Scientific Research (A)

Allocation TypeSingle-year Grants
Section一般
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionKyushu University

Principal Investigator

内田 誠一  九州大学, システム情報科学研究院, 教授 (70315125)

Co-Investigator(Kenkyū-buntansha) 北本 朝展  国立情報学研究所, コンテンツ科学研究系, 教授 (00300707)
中山 英樹  東京大学, 大学院情報理工学系研究科, 准教授 (00643305)
牛久 祥孝  オムロンサイニックエックス株式会社, リサーチアドミニストレイティブディビジョン, プリンシパルインベスティゲーター (10784142)
柳井 啓司  電気通信大学, 大学院情報理工学研究科, 教授 (20301179)
大町 真一郎  東北大学, 工学研究科, 教授 (30250856)
塩入 諭  東北大学, 電気通信研究所, 教授 (70226091)
黄瀬 浩一  大阪公立大学, 大学院情報学研究科, 教授 (80224939)
岩村 雅一  大阪公立大学, 大学院情報学研究科, 准教授 (80361129)
山本 和明  国文学研究資料館, 研究部, 教授 (90249433)
Project Period (FY) 2022-04-01 – 2025-03-31
Project Status Granted (Fiscal Year 2024)
Budget Amount *help
¥42,380,000 (Direct Cost: ¥32,600,000、Indirect Cost: ¥9,780,000)
Fiscal Year 2024: ¥14,430,000 (Direct Cost: ¥11,100,000、Indirect Cost: ¥3,330,000)
Fiscal Year 2023: ¥13,910,000 (Direct Cost: ¥10,700,000、Indirect Cost: ¥3,210,000)
Fiscal Year 2022: ¥14,040,000 (Direct Cost: ¥10,800,000、Indirect Cost: ¥3,240,000)
Keywords文字 / コミュニケーション / 生成AI / 機械学習 / デザイン / フォントデザイン / 情景内文字 / 古典籍 / 認知心理 / 自然言語処理 / 教育 / 障碍者支援
Outline of Research at the Start

本課題では,多分野協働体制の下,文字を介したコミュニケーション基盤モデルの創成を目的とする.具体的には,文字を介した視覚的コミュニケーションを7階層に整理した上で,データに基づく情報学的手法群と,認知心理学やデザイン学などの各種専門的知見を組み合わせ,文字情報の生成・受理モデルを構築する.さらに同モデルを応用し,独特な文字コミュニケーションを前提とする領域(古典籍・教育・福祉・ナビゲーション)に貢献する.

Outline of Annual Research Achievements

「文字を介した視覚的コミュニケーション基盤の創成」について初年度同様,極めて多角的な研究を行った.具体的には,文字画像に関する基盤技術として,拡散モデルや敵対的生成ネットワークに代表される生成AI技術を用いた文字画像や文書デザイン生成,特定のスタイルを持った活字や手書きの生成,敵対的攻撃に対して頑健な文字生成,文字スタイル分析,CLIP(対照学習)を用いた文字印象と画像の相関分析,タイポグラフィ支援(文字スタイル推薦,カーニング(文字間隔)自動設定,レイアウトデータセットの構築とそれを用いたレイアウト生成),情景内文字認識および合成,情景内文字隠蔽(選択的隠蔽を含む),情景内文字のクオリティ評価,などが挙げられる.これら多方面に広がる基盤技術は,わが国のみならず世界的にも最新の文字研究動向をカバーもしくは独自推進するレベルであると自負する.応用分野である認知心理学関連については注意機構に関する実験を行っている.古典籍分析については,くずし字データ認識や,くずし字合成,さらにくずし字の活字化などがあり,これらの成果のいくつかについては誰でも扱えるように公開されており,わが国における古典籍理解の推進に大きく寄与している.なお,これら研究のほとんどすべてにおいて,最新の機械学習手法に基づいたモデルを新たに開発している点は特筆に値する.また,世界的な書体デザイナーである小林章氏から,研究に対するフィードバックを得ている点も,研究方針が独善的にならないために重要と考えている.

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

【研究実績の概要】で述べた通り,また研究成果のリストにも列挙しているように,文字というキーワードを中心に多面的な研究を多数展開している.この多面性こそが,本課題が想定していた「視覚を介した文字コミュニケーションの多レイヤ(意図,言語,文字画像,レイアウト,提示)における理解」を深めていることに他ならない.また,研究代表者のグループでは,文字文書画像関係で世界トップ国際会議であるICDARにおいて,世界最多レベルの6編の論文が採択されている.こうしたエビデンスにより,「おおむね順調に進展」と自己評価する.

Strategy for Future Research Activity

最終年度である2024年度においても,引き続き計画に従って,当研究グループの強みである多面性を活かしつつ,「人間のコミュニケーションにおける文字の役割」の解明に関する研究を深める.また,最終年度独自のイベントとして,多面的な成果を俯瞰しつつ,それらの相互関係を理解するための研究集会を実施する.このイベントにより,さらに次の文字画像研究の方向性を計画する.

Report

(3 results)
  • 2023 Annual Research Report
  • 2022 Comments on the Screening Results   Annual Research Report
  • Research Products

    (156 results)

All 2024 2023 2022 Other

All Int'l Joint Research (6 results) Journal Article (58 results) (of which Int'l Joint Research: 13 results,  Peer Reviewed: 53 results,  Open Access: 24 results) Presentation (86 results) (of which Int'l Joint Research: 27 results,  Invited: 8 results) Book (4 results) Remarks (2 results)

  • [Int'l Joint Research] Wuhan University of Technology(中国)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] ドイツ人工知能研究センター(ドイツ)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] メルボルン大学(オーストラリア)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] LIMSI/ENIB(フランス)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] University of California, Los Angeles(米国)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] Wuhan University of Technology(中国)

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Multi-Style Shape Matching GAN for Text Images2024

    • Author(s)
      YUAN Honghui、YANAI Keiji
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E107.D Issue: 4 Pages: 505-514

    • DOI

      10.1587/transinf.2023IHP0010

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2024-04-01
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] No regret sample selection with noisy labels2024

    • Author(s)
      Song Heon、Mitsuo Nariaki、Uchida Seiichi、Suehiro Daiki
    • Journal Title

      Machine Learning

      Volume: 113 Issue: 3 Pages: 1163-1188

    • DOI

      10.1007/s10994-023-06478-8

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Cross-Domain Image Conversion by CycleDM2024

    • Author(s)
      Sho Shimotsumagari, Shumpei Takezaki, Daichi Haraguchi, Seiichi Uchida
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts2024

    • Author(s)
      Yugo Kubota, Daichi Haraguchi, Seiichi Uchida
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Font Impression Estimation in the Wild2024

    • Author(s)
      Kazuki Kitajima, Daichi Haraguchi, Seiichi Uchida
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Font Style Interpolation with Diffusion Models2024

    • Author(s)
      Tetta Kondo, Shumpei Takezaki, Daichi Haraguchi, Seiichi Uchida
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Typographic Text Generation with Off-the-Shelf Diffusion Model2024

    • Author(s)
      KhayTze Peong, Seiichi Uchida, Daichi Haraguchi
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Learning to Kern: Set-wise Estimation of Optimal Letter Space2024

    • Author(s)
      Kei Nakatsuru, Seiichi Uchida
    • Journal Title

      Proceedings of the 18th International Conference on Document Analysis and Recognition (ICDAR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging2024

    • Author(s)
      Takahiro Shirakawa, Seiichi Uchida
    • Journal Title

      Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Towards Diverse and Consistent Typography Generation2024

    • Author(s)
      Shimoda Wataru、Haraguchi Daichi、Uchida Seiichi、Yamaguchi Kota
    • Journal Title

      Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV 2024)

      Volume: - Pages: 7296-7305

    • DOI

      10.1109/wacv57701.2024.00713

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Revisiting Latent Space of GAN Inversion for Robust Real Image Editing2024

    • Author(s)
      Katsumata Kai、Vo Duc Minh、Liu Bei、Nakayama Hideki
    • Journal Title

      2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      Volume: - Pages: 5301-5310

    • DOI

      10.1109/wacv57701.2024.00523

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Japanese historical character recognition by focusing on character parts2024

    • Author(s)
      Ishikawa Takuru、Miyazaki Tomo、Omachi Shinichiro
    • Journal Title

      Pattern Recognition

      Volume: 148 Pages: 110181-110181

    • DOI

      10.1016/j.patcog.2023.110181

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] The Reality of a Head-Mounted Display (HMD) Environment Tested via Lightness Perception2024

    • Author(s)
      Kuriki Ichiro、Sato Kazuki、Shioiri Satoshi
    • Journal Title

      Journal of Imaging

      Volume: 10 Issue: 2 Pages: 36-36

    • DOI

      10.3390/jimaging10020036

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters2024

    • Author(s)
      Hao Wang, Shohei Tanaka, Yoshitaka Ushiku
    • Journal Title

      CVPR Workshop on Graphic Design Understanding and Generation

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Face Image Generation of Anime Characters Using an Advanced First Order Motion Model with Facial Landmarks2023

    • Author(s)
      OSHIBA Junki、IWATA Motoi、KISE Koichi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E106.D Issue: 1 Pages: 22-30

    • DOI

      10.1587/transinf.2022MUP0004

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2023-01-01
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Paired contrastive feature for highly reliable offline signature verification2023

    • Author(s)
      ji Xiaotong、Suehiro Daiki、Uchida Seiichi
    • Journal Title

      Pattern Recognition

      Volume: 144 Pages: 109816-109816

    • DOI

      10.1016/j.patcog.2023.109816

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] FETNet: Feature erasing and transferring network for scene text removal2023

    • Author(s)
      Guangtao Lyu, Kun Liu, Anna Zhu, Seiichi Uchida, Brian Kenji Iwana
    • Journal Title

      Pattern Recognition

      Volume: 140 Pages: 109531-109531

    • DOI

      10.1016/j.patcog.2023.109531

    • Related Report
      2023 Annual Research Report 2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Selective Scene Text Removal2023

    • Author(s)
      Hayato Mitani, Akisato Kimura and Seiichi Uchida
    • Journal Title

      Proceedings of the 34th British Machine Vision Conference (BMVC2023)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Toward Defensive Letter Design2023

    • Author(s)
      Kataoka Rentaro、Kimura Akisato、Uchida Seiichi
    • Journal Title

      Proceedings of the 7th Asian Conference on Pattern Recognition (ACPR2023)

      Volume: - Pages: 108-122

    • DOI

      10.1007/978-3-031-47634-1_9

    • ISBN
      9783031476334, 9783031476341
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Local Style Awareness of?Font Images2023

    • Author(s)
      Haraguchi Daichi、Uchida Seiichi
    • Journal Title

      Proceedings of the ICDAR 2023 Workshop on Machine Learning (ICDAR-WML2023)

      Volume: - Pages: 242-256

    • DOI

      10.1007/978-3-031-41501-2_17

    • ISBN
      9783031415005, 9783031415012
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Ambigram Generation by a Diffusion Model2023

    • Author(s)
      Shirakawa Takahiro、Uchida Seiichi
    • Journal Title

      Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR2023)

      Volume: - Pages: 314-330

    • DOI

      10.1007/978-3-031-41682-8_20

    • ISBN
      9783031416811, 9783031416828
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Contour Completion by Transformers and Its Application to Vector Font Data2023

    • Author(s)
      Nagata Yusuke、Iwana Brian Kenji、Uchida Seiichi
    • Journal Title

      Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR2023)

      Volume: - Pages: 490-504

    • DOI

      10.1007/978-3-031-41734-4_30

    • ISBN
      9783031417337, 9783031417344
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Analyzing Font Style Usage and Contextual Factors in Real Images2023

    • Author(s)
      Yasukochi Naoya、Hayashi Hideaki、Haraguchi Daichi、Uchida Seiichi
    • Journal Title

      Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR2023)

      Volume: - Pages: 331-347

    • DOI

      10.1007/978-3-031-41682-8_21

    • ISBN
      9783031416811, 9783031416828
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] ViTSTR-Transducer: Cross-Attention-Free Vision Transformer Transducer for Scene Text Recognition2023

    • Author(s)
      Buoy Rina、Iwamura Masakazu、Srun Sovila、Kise Koichi
    • Journal Title

      Journal of Imaging

      Volume: 9 Issue: 12 Pages: 276-276

    • DOI

      10.3390/jimaging9120276

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Toward a Low-Resource Non-Latin-Complete Baseline: An Exploration of Khmer Optical Character Recognition2023

    • Author(s)
      Buoy Rina、Iwamura Masakazu、Srun Sovila、Kise Koichi
    • Journal Title

      IEEE Access

      Volume: 11 Pages: 128044-128060

    • DOI

      10.1109/access.2023.3332361

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Explainable Connectionist-Temporal-Classification-Based Scene Text Recognition2023

    • Author(s)
      Buoy Rina、Iwamura Masakazu、Srun Sovila、Kise Koichi
    • Journal Title

      Journal of Imaging

      Volume: 9 Issue: 11 Pages: 248-248

    • DOI

      10.3390/jimaging9110248

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Handwritten Text Generation with Character-Specific Encoding for Style Imitation2023

    • Author(s)
      Zdenek Jan、Nakayama Hideki
    • Journal Title

      Proceedings of the 17th International Conference on Document Analysis and Recognition (ICDAR2023)

      Volume: - Pages: 313-329

    • DOI

      10.1007/978-3-031-41679-8_18

    • ISBN
      9783031416781, 9783031416798
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts2023

    • Author(s)
      Li Jiaxuan、Vo Duc Minh、Nakayama Hideki
    • Journal Title

      2023 IEEE/CVF International Conference on Computer Vision (ICCV)

      Volume: 1 Pages: 4901-4911

    • DOI

      10.1109/iccv51070.2023.00454

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] 近世戯作の洋装本化2023

    • Author(s)
      山本和明
    • Journal Title

      書物学

      Volume: 24 Pages: 78-85

    • Related Report
      2023 Annual Research Report
  • [Journal Article] Deep image compression using scene text quality assessment2023

    • Author(s)
      Uchigasaki Shohei、Miyazaki Tomo、Omachi Shinichiro
    • Journal Title

      Pattern Recognition

      Volume: 142 Pages: 109696-109696

    • DOI

      10.1016/j.patcog.2023.109696

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A Scene-Text Synthesis Engine Achieved Through Learning From Decomposed Real-World Data2023

    • Author(s)
      Tang Zhengmi、Miyazaki Tomo、Omachi Shinichiro
    • Journal Title

      IEEE Transactions on Image Processing

      Volume: 32 Pages: 5837-5851

    • DOI

      10.1109/tip.2023.3326685

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Different Mechanisms for Visual Attention at the Hand-movement Goal and Endogenous Visual Attention2023

    • Author(s)
      Wu Wei、Li Zhan、Miura Takumi、Hatori Yasuhiro、Tseng Chia-huei、Kuriki Ichiro、Sato Yoshiyuki、Shioiri Satoshi
    • Journal Title

      Journal of Cognitive Neuroscience

      Volume: 35 Issue: 8 Pages: 1246-1261

    • DOI

      10.1162/jocn_a_02005

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Cross-cultural comparison of lexical partitioning of color space2023

    • Author(s)
      Shioiri S., Tokunaga R., Kuriki I.
    • Journal Title

      Issues in Japanese Psycholinguistics from Comparative Perspectives

      Volume: 1 Pages: 41-61

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Detecting Learners' Hint Inquiry Behaviors in e-Learning Environment by using Facial Expressions2023

    • Author(s)
      Wang Guan-Yun、Nagata Hikaru、Hatori Yasuhiro、Sato Yoshiyuki、Tseng Chia-Huei、Shioiri Satoshi
    • Journal Title

      Proceedings of the Tenth ACM Conference on Learning@ Scale

      Volume: - Pages: 331-335

    • DOI

      10.1145/3573051.3596182

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] QAHOI: Query-Based Anchors for Human-Object Interaction Detection2023

    • Author(s)
      Chen Junwen、Yanai Keiji
    • Journal Title

      2023 18th International Conference on Machine Vision and Applications (MVA)

      Volume: -

    • DOI

      10.23919/mva57639.2023.10215534

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Deep attentive time warping2023

    • Author(s)
      Matsuo Shinnosuke、Wu Xiaomeng、Atarsaikhan Gantugs、Kimura Akisato、Kashino Kunio、Iwana Brian Kenji、Uchida Seiichi
    • Journal Title

      Pattern Recognition

      Volume: 136 Pages: 109201-109201

    • DOI

      10.1016/j.patcog.2022.109201

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] 情景画像中の重要テキストの検出と伝送2023

    • Author(s)
      大町真一郎, 宮崎智
    • Journal Title

      画像ラボ

      Volume: 34(4) Pages: 17-22

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Indirect Adversarial Losses via an Intermediate Distribution for Training GANs2023

    • Author(s)
      Rui Yang, Duc Minh Vo, Hideki Nakayama
    • Journal Title

      Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

      Volume: - Pages: 4641-4650

    • DOI

      10.1109/wacv56688.2023.00463

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] くずし字華ざかり2023

    • Author(s)
      山本和明
    • Journal Title

      ふみ

      Volume: 19 Pages: 10-10

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Exploring Sensor Modalities to Capture User Behaviors for Reading Detection2022

    • Author(s)
      ISLAM Md. Rabiul、VARGO Andrew W.、IWATA Motoi、IWAMURA Masakazu、KISE Koichi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E105.D Issue: 9 Pages: 1629-1633

    • DOI

      10.1587/transinf.2020ZDL0003

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2022-09-01
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Improving Noised Gradient Penalty with Synchronized Activation Function for Generative Adversarial Networks2022

    • Author(s)
      Rui Yang, Raphael Shu, Hideki Nakayama
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E105.D Issue: 9 Pages: 1537-1545

    • DOI

      10.1587/transinf.2022EDP7019

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2022-09-01
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Fonts That Fit the Music: A Multimodal Design Trend Analysis of Lyric Videos2022

    • Author(s)
      Haraguchi Daichi、Sakaguchi Shota、Kato Jun、Goto Masataka、Uchida Seiichi
    • Journal Title

      IEEE Access

      Volume: 10 Pages: 65414-65425

    • DOI

      10.1109/access.2022.3184028

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Font Generation with Missing Impression Labels2022

    • Author(s)
      Matsuda Seiya、Kimura Akisato、Uchida Seiichi
    • Journal Title

      Proceedings of the 25th International Conference on Pattern Recognition (ICPR2022)

      Volume: なし

    • DOI

      10.1109/icpr56361.2022.9956147

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] MontageGAN: Generation and Assembly of Multiple Components by GANs2022

    • Author(s)
      Shee Chean Fei、Uchida Seiichi
    • Journal Title

      Proceedings of the 25th International Conference on Pattern Recognition (ICPR2022)

      Volume: なし Pages: 1478-1484

    • DOI

      10.1109/icpr56361.2022.9956028

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Shared Latent Space of Font Shapes and Their Noisy Impressions2022

    • Author(s)
      Kang Jihun、Haraguchi Daichi、Matsuda Seiya、Kimura Akisato、Uchida Seiichi
    • Journal Title

      Proceedings of the 28th International Conference on Multimedia Modeling

      Volume: - Pages: 146-157

    • DOI

      10.1007/978-3-030-98355-0_13

    • ISBN
      9783030983543, 9783030983550
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Revealing Reliable Signatures by Learning Top-Rank Pairs2022

    • Author(s)
      Ji Xiaotong、Zheng Yan、Suehiro Daiki、Uchida Seiichi
    • Journal Title

      Proceedings of the 15th IAPR International Workshop on Document Analysis Systems (DAS2022)

      Volume: なし Pages: 323-337

    • DOI

      10.1007/978-3-031-06555-2_22

    • ISBN
      9783031065545, 9783031065552
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Font Shape-to-Impression Translation2022

    • Author(s)
      Ueda Masaya、Kimura Akisato、Uchida Seiichi
    • Journal Title

      Proceedings of the 15th IAPR International Workshop on Document Analysis Systems (DAS2022)

      Volume: なし Pages: 3-17

    • DOI

      10.1007/978-3-031-06555-2_1

    • ISBN
      9783031065545, 9783031065552
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] TrueType Transformer: Character and Font Style Recognition in Outline Format2022

    • Author(s)
      Nagata Yusuke、Otao Jinki、Haraguchi Daichi、Uchida Seiichi
    • Journal Title

      Proceedings of the 15th IAPR International Workshop on Document Analysis Systems (DAS2022)

      Volume: なし Pages: 18-32

    • DOI

      10.1007/978-3-031-06555-2_2

    • ISBN
      9783031065545, 9783031065552
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 文字とは何か? ― 深層学習により見えてきた新たな問い―2022

    • Author(s)
      内田誠一
    • Journal Title

      電子情報通信学会誌

      Volume: 105 Pages: 371-374

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Important Region Estimation Using Image Captioning2022

    • Author(s)
      Taku Suzuki, Daisuke Sato, Yoshihiro Sugaya, Tomo Miyazaki, and Shinichiro Omachi
    • Journal Title

      IEEE Access

      Volume: 10 Pages: 105546-105555

    • DOI

      10.1109/access.2022.3211260

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Visual attention around a hand location localized by proprioceptive information2022

    • Author(s)
      Shioiri, S., Sasada, T., and Nishikawa, R.,
    • Journal Title

      Cereb Cortex Commun

      Volume: 3 (1) Issue: 1 Pages: 1-18

    • DOI

      10.1093/texcom/tgac005

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Stochastically Flipping Labels of Discriminator’s Outputs for Training Generative Adversarial Networks2022

    • Author(s)
      Rui Yang, Duc Minh Vo, Hideki Nakayama
    • Journal Title

      IEEE Access

      Volume: 10 Pages: 103644-103654

    • DOI

      10.1109/access.2022.3210130

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Character-centric Story Visualization via Visual Planning and Token Alignment2022

    • Author(s)
      Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama and Nanyun Peng
    • Journal Title

      Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)

      Volume: なし Pages: 8259-8272

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning2022

    • Author(s)
      Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama
    • Journal Title

      Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)

      Volume: なし Pages: 1739-1753

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] OSSGAN: Open-Set Semi-Supervised Image Generation2022

    • Author(s)
      Kai Katsumata, Duc Minh Vo, Hideki Nakayama
    • Journal Title

      Proceedings of the 2022 IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)

      Volume: なし Pages: 11175-11183

    • DOI

      10.1109/cvpr52688.2022.01090

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Material Translation Based on Neural Style Transfer with Ideal Style Image Retrieval2022

    • Author(s)
      Benitez-Garcia Gibran、Takahashi Hiroki、Yanai Keiji
    • Journal Title

      Sensors

      Volume: 22 Issue: 19 Pages: 7317-7317

    • DOI

      10.3390/s22197317

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] 版面からわかること : 京伝『善知安方忠義伝』考2022

    • Author(s)
      山本和明
    • Journal Title

      国語と国文学

      Volume: 第99巻第6号 Pages: 1-15

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows2022

    • Author(s)
      Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, and Shinsuke Mori
    • Journal Title

      Proceedings of the 29th International Conference on Computational Linguistics

      Volume: なし Pages: 3570-3577

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] “Beyond 100%" Open research in Document Analysis2024

    • Author(s)
      Seiichi Uchida
    • Organizer
      The 41st Swedish Symposium on Image Analysis / The 7th Swedish Symposium on Deep Learning (SSBA/SSDL 2024)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 拡散モデルによる活字画像の生成2024

    • Author(s)
      下津曲 将, 竹崎隼平, 原口大地, 内田誠一
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] マルチモーダルモデルを用いた印象語によるフォント検索2024

    • Author(s)
      久保田優吾, 内田誠一, 原口大地
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] What are letters?2023

    • Author(s)
      Seiichi Uchida
    • Organizer
      The 17th International Conference on Document Analysis and Recognition (ICDAR2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 実データと機械学習を組み合わせて楽しむ2023

    • Author(s)
      内田誠一
    • Organizer
      精密工学会 画像応用技術専門委員会 2023年度第2回研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 拡散モデルによる複数人物画像の生成2023

    • Author(s)
      白川嵩大, 内田誠一
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Ambigram Generation and Ambigramability2023

    • Author(s)
      Takahiro Shirakawa, Seiichi Uchida
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] Regional Diffusionによる手書き数式認識結果の事後補正2023

    • Author(s)
      ピョンケイジ, Xiaomeng Wu, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 敵対的攻撃に頑健な文字のデザインをめざして2023

    • Author(s)
      片岡蓮太郎, 木村昭悟, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] アウトライン推定を用いた情景内文字編集へ向けて2023

    • Author(s)
      大峠仁輝, 原口大地 , 下田和, 山口光太, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] スタイル特徴は演算可能か?2023

    • Author(s)
      近藤徹多, 原口大地, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 情景内単語の選択的消去2023

    • Author(s)
      三谷勇人 , 木村昭悟, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 機械学習によるカーニング2023

    • Author(s)
      中鶴慧, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 対照学習における注意とその応用2023

    • Author(s)
      原口大地, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 事前学習済みU-Netによる画像処理パイプライン2023

    • Author(s)
      竹崎隼平, Weizhi Shi , Gantugs Atarsaikhan, 内田誠一
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] Self Attention機構を用いた画像単位でのデータ拡張の適応的選択2023

    • Author(s)
      山田敏輝, 内田誠一, 原田翔太
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] Energy-based modelを用いた信頼度較正と疑似ラベル学習への応用2023

    • Author(s)
      鳥羽真仁, 内田誠一 , 早志英朗
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 畳み込みニューラルネットワークによる重ね合わせ文字認識の挙動評価2023

    • Author(s)
      久保田優吾, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 拡散モデルを用いたアイコン生成2023

    • Author(s)
      與田悟史, 白川嵩大, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] オンライン手書き文字から筆記者特徴の抽出2023

    • Author(s)
      秋庭正樹, 原口大地, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 拡散モデルによる手書き活字変換2023

    • Author(s)
      下津曲 将, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 文字領域によるAI生成画像の見破り2023

    • Author(s)
      大西 元, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Looking beyond the "Union Catalogue Database of Japanese Texts": Future Strategies of the National Institute for Japanese Literature2023

    • Author(s)
      F. Komiyama, K. Yamamoto
    • Organizer
      European Association of Japanese Resource Specialists
    • Related Report
      2023 Annual Research Report
  • [Presentation] そあん(soan):古活字データセットを用いた現代日本語テキストからくずし字画像への変換と共有2023

    • Author(s)
      北本 朝展, 本間 淳, カラーヌワット タリン
    • Organizer
      人文科学とコンピュータシンポジウム じんもんこん2023論文集
    • Related Report
      2023 Annual Research Report
  • [Presentation] そあん(soan):現代日本語を古活字(くずし字)に変換するソフトウェアの開発2023

    • Author(s)
      北本 朝展
    • Organizer
      総合書物学シンポジウム2023「印刷をめぐる多角的なアプローチ」
    • Related Report
      2023 Annual Research Report
  • [Presentation] 生成画像を利用した少数データくずし字認識に関する検討2023

    • Author(s)
      阿部楓也, 岩井翔真, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] パーツプロトタイプを用いたくずし字認識に関する検討2023

    • Author(s)
      木下純哉, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] Prediction of preference judgments of face images using facial expressions and EEG signals2023

    • Author(s)
      S Shioiri, H Nagata, Y Sato, Y Hatori
    • Organizer
      VSS 2023
    • Related Report
      2023 Annual Research Report
  • [Presentation] Use of facial expressions to estimate level of attention while watching video lectures.2023

    • Author(s)
      R. Miao, H Kato, Y Hatori, Y Sato, S Shioiri
    • Organizer
      VSS 2023
    • Related Report
      2023 Annual Research Report
  • [Presentation] CLIPと微分可能レンダラーを用いたフォントスタイル変換2023

    • Author(s)
      泉幸太, 柳井啓司
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 人物・物体・動作デコーダの分離によるHOI検出2023

    • Author(s)
      陳俊文, 王瀛成, 柳井啓司
    • Organizer
      画像の認識・理解シンポジウム(MIRU2023)
    • Related Report
      2023 Annual Research Report
  • [Presentation] 文字とは何か? --- 画像情報学的視点からの文字の機能解明2023

    • Author(s)
      内田誠一
    • Organizer
      2022年度 第7回 中部大学CMSAIコロキウム
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Deformable Convolutionによる局所変形特徴抽出の試み2023

    • Author(s)
      北島和樹, 内田誠一
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Transformerによる輪郭欠損補完2023

    • Author(s)
      永田悠祐, 内田誠一
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Knowledge Distillation using a Multiple Reference Teacher2023

    • Author(s)
      沈 毅誠, 内田 誠一, Brian Kenji Iwana
    • Organizer
      情報処理学会コンピュータビジョンとイメージメディア研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 視覚障害者を対象としたディスプレイ操作を必要とする家庭用3Dプリンタ操作支援システム2023

    • Author(s)
      田川直弥, 岩村雅一, 南谷和範, 黄瀬浩一
    • Organizer
      ヒューマンインタフェース学会 アクセシブル・インタフェース専門研究委員会(SIGACI)
    • Related Report
      2022 Annual Research Report
  • [Presentation] Recognition of Japanese historical characters using character parts2023

    • Author(s)
      Shinichiro Omachi
    • Organizer
      Symposium of Yotta Informatics - Research Platform for Yotta-Scale Data Science 2023
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Detecting Important Information from Scene Images via Texts2023

    • Author(s)
      Shinichiro Omachi
    • Organizer
      The 6th Tohoku Uni-NTU Symposium on Interdisciplinary AI and Human Studies
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Indirect Adversarial Losses via an Intermediate Distribution for Training GANs2023

    • Author(s)
      Rui Yang, Duc Minh Vo, Hideki Nakayama
    • Organizer
      2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Font Generation with Missing Impression Labels2022

    • Author(s)
      Seiya Matsuda, Akisato Kimura, Seiichi Uchida
    • Organizer
      The 25th International Conference on Pattern Recognition (ICPR2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] MontageGAN: Generation and Assembly of Multiple Components by GANs2022

    • Author(s)
      Chean Fei Shee, Seiichi Uchida
    • Organizer
      The 25th International Conference on Pattern Recognition (ICPR2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Shared Latent Space of Font Shapes and Their Noisy Impressions2022

    • Author(s)
      Jihun Kang, Daichi Haraguchi, Seiya Matsuda, Akisato Kimura, Seiichi Uchida
    • Organizer
      The 28th International Conference on Multimedia Modeling (MMM 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Revealing Reliable Signatures by Learning Top-Rank Pairs2022

    • Author(s)
      Xiaotong Ji, Yan Zheng, Daiki Suehiro and Seiichi Uchida
    • Organizer
      The 15th IAPR International Workshop on Document Analysis Systems (DAS2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Font Shape-to-Impression Translation2022

    • Author(s)
      Masaya Ueda, Akisato Kimura and Seiichi Uchida
    • Organizer
      The 15th IAPR International Workshop on Document Analysis Systems (DAS2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] TrueType Transformer: Character and Font Style Recognition in Outline Format2022

    • Author(s)
      Yusuke Nagata, Jinki Otao, Daichi Haraguchi and Seiichi Uchida
    • Organizer
      The 15th IAPR International Workshop on Document Analysis Systems (DAS2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Challenges beyond recognition (Keynote Speech)2022

    • Author(s)
      Seiichi Uchida
    • Organizer
      1st Workshop on Deep Document Understanding (DeepDoc2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] What are characters (Keynote Speech)2022

    • Author(s)
      Seiichi Uchida
    • Organizer
      MIRAI2.0 Research & Innovation Week 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] コンテキストを考慮したテキストデザインの自動推薦2022

    • Author(s)
      下田 和, 原口 大地, 内田 誠一, 山口 光太
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Learning Top-Rank Pairs Discloses Reliable Signatures in Writer-Independent Signature Verification2022

    • Author(s)
      Xiaotong Ji, Yan Zheng, Daiki Suehiro, Seiichi Uchida,
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Vision Transformerによるパッチベース文字認識2022

    • Author(s)
      大峠 仁輝, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 識別器の斟酌学習2022

    • Author(s)
      本田 康祐, 内田 誠一, 末廣 大貴,
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 集合距離学習による手書き数式認識結果の事後補正2022

    • Author(s)
      ピョン ケイジ, 松尾 信之介, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 画素レベルVision Transformerによるフォント画像の欠損補完2022

    • Author(s)
      中鶴 慧, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Impressions-to-Font with Missing Labels2022

    • Author(s)
      Seiya Matsuda, Akisato Kimura, Seiichi Uchida
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] フォント画像のTotal disentanglement2022

    • Author(s)
      原口 大地, 下田 和, 山口 光太, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Transformer for Outline Font2022

    • Author(s)
      Yusuke Nagata, Jinki Otao, Daichi Haraguchi, Seiichi Uchida
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Shape-to-Impression Translation for Fonts2022

    • Author(s)
      Masaya Ueda, Akisato KImura, Seiichi Uchida
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 単語画像から言語情報を取り除けるか?2022

    • Author(s)
      安河内 直哉, 原口 大地, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Attention機構による深層時間ワーピング2022

    • Author(s)
      松尾 信之介, Xiaomeng Wu, Gantugs Atarsaikhan, 木村 昭悟, 柏野 邦夫, Brian Kenji Iwana, 内田 誠一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] TextVQAタスクの正答可能性判定2022

    • Author(s)
      中村亘岐, 内田誠一
    • Organizer
      電子情報通信学会パターン認識・メディア理解研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Energy-Based Modelに基づく識別器の信頼度較正2022

    • Author(s)
      鳥羽真仁, 内田誠一, 早志英朗
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Neural Style Difference Transferを用いたフォント生成2022

    • Author(s)
      近藤徹多, Gantugs Atarsaikhan, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 文字画像における敵対的サンプルの生成2022

    • Author(s)
      片岡蓮太郎, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 深層学習による選択的文字消し2022

    • Author(s)
      三谷勇人, 内田誠一
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Transformer によるデータ拡張手法の適応的選択2022

    • Author(s)
      山田敏輝, 内田誠一, 原田翔太
    • Organizer
      電気・情報関係学会九州支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 説明文からのテキスト領域を含む画像の生成に関する検討2022

    • Author(s)
      恩田浩志, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 古典籍中の少数サンプル文字種認識のための文字部位認識2022

    • Author(s)
      石川太繰, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 少数くずし字データ補強のための画像生成に関する検討2022

    • Author(s)
      阿部楓也, 岩井翔真, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 編集距離に基づいた距離学習による情景画像文字認識結果の修正に関する検討2022

    • Author(s)
      梶原颯希, 宮崎智, 大町真一郎
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Masked Image Modelingを利用した情景画像中のテキスト認識2022

    • Author(s)
      三ツ井悠翔, 宮崎智, 大町真一郎
    • Organizer
      言語処理学会第29回年次大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Towards Guided-Breath as an Intervention Within Computer-Assisted Learning2022

    • Author(s)
      Kanta Yamaoka, Andrew W. Vargo, Motoi Iwata, Koichi Kise
    • Organizer
      2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 International Symposium on Wearable Computers
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Sleep Quality Tracking and Alignment with a Simple In-the-Wild Task2022

    • Author(s)
      Andrew W. Vargo, Masayuki Fujimoto, Koichi Kise
    • Organizer
      2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 International Symposium on Wearable Computers
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Just the Right Amount of Exercise: Aerobic Exercise and Memory2022

    • Author(s)
      Andrew W. Vargo, Kentaro Ohara, Takumi Nakai, Koichi Kise
    • Organizer
      2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 International Symposium on Wearable Computers
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Evaluating Contrastive Learning for Fine-grained Reading Detection2022

    • Author(s)
      Md. Rabiul Islam, Andrew W. Vargo, Motoi Iwata, Masakazu Iwamura, and Koichi Kise
    • Organizer
      12th International Congress on Advanced Applied Informatics (IIAI-AAI)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Helping Mobile Learners Know Unknown Words through their Reading Behavior2022

    • Author(s)
      Riku Higashimura, Andrew W. Vargo, Motoi Iwata, Koichi Kise
    • Organizer
      CHI Conference on Human Factors in Computing Systems
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Analysis of Facial Expressions for the Estimation of Concentration on Online Lectures2022

    • Author(s)
      Renjun Miao, Haruka Kato, Yasuhiro Hatori, Yoshiyuki Sato, and Satoshi Shioiri
    • Organizer
      World Conference on Computers in Education(IFIP WCCE, 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Prediction of Engagement from Temporal Changes in Facial Expression2022

    • Author(s)
      Haruka Kato, Koki Takahashi, Yasuhiro Hatori, Yoshiyuki Sato, and Satoshi Shioiri,
    • Organizer
      World Conference on Computers in Education(IFIP WCCE, 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Character-centric Story Visualization via Visual Planning and Token Alignment2022

    • Author(s)
      Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama and Nanyun Peng
    • Organizer
      2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning2022

    • Author(s)
      Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama
    • Organizer
      2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] OSSGAN: Open-Set Semi-Supervised Image Generation2022

    • Author(s)
      Kai Katsumata, Duc Minh Vo, Hideki Nakayama
    • Organizer
      IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Incorporating External Knowledge for Vision and Language Systems2022

    • Author(s)
      Hideki Nakayama
    • Organizer
      2nd Workshop on Trends and Advances in Machine Learning and Automated Reasoning for Intelligent Robots and Systems
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Zero-shot Font Style Transfer with a Differentiable Renderer2022

    • Author(s)
      Kota Izumi and Keiji Yanai
    • Organizer
      ACM Multimedia Asia
    • Related Report
      2022 Annual Research Report
  • [Presentation] StyleGAN-based CLIP-guided Image Shape Manipulation2022

    • Author(s)
      uchen Qian, Kohei Yamamoto and Keiji Yanai
    • Organizer
      International Conference on Content-based Multimedia Indexing
    • Related Report
      2022 Annual Research Report
  • [Presentation] The Future of Collaborative Data-Driven Research in Japanese Studies2022

    • Author(s)
      Y.Yamamoto,K.Yamamoto,Arokay,Gramlich-Oka,Kinski,Unno
    • Organizer
      The 2022 ASCJ Conference
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Toward the Model Building for Data-Driven Problem Solving in the Humanities2022

    • Author(s)
      渡部泰明,山本和明,海野圭介,菊池信彦,松田訓典,大山敬三
    • Organizer
      DH2022 Tokyo Local Oraganizers'session
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows2022

    • Author(s)
      Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, and Shinsuke Mori
    • Organizer
      The 29th International Conference on Computational Linguistics
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Book] デジタルアーカイブ・ベーシックス『共振するデジタル人文学とデジタルアーカイブ』2023

    • Author(s)
      山本和明
    • Total Pages
      232
    • Publisher
      勉誠出版
    • ISBN
      9784585303022
    • Related Report
      2023 Annual Research Report
  • [Book] 近世後期江戸小説論攷2023

    • Author(s)
      山本和明
    • Total Pages
      472
    • Publisher
      勉誠出版
    • ISBN
      9784585390220
    • Related Report
      2022 Annual Research Report
  • [Book] 機械学習の可能性2022

    • Author(s)
      計測自動制御学会、浮田 浩行、濱上 知樹、藤吉 弘亘、大町 真一郎、戸田 智基、岩崎 敦、小林 泰介、鈴木 亮太、木村 雄喜、橋本 大樹、玉垣 勇樹、水谷 麻紀子、永田 毅、木村 光成、李 晃伸、川嶋 宏彰
    • Total Pages
      240
    • Publisher
      コロナ社
    • ISBN
      9784339033854
    • Related Report
      2022 Annual Research Report
  • [Book] IT Text 深層学習2022

    • Author(s)
      柳井 啓司、中鹿 亘、稲葉 通将
    • Total Pages
      288
    • Publisher
      オーム社
    • ISBN
      9784274228889
    • Related Report
      2022 Annual Research Report
  • [Remarks] ヒューマンインタフェース研究室

    • Related Report
      2023 Annual Research Report
  • [Remarks] ヒューマンインタフェース研究室

    • Related Report
      2022 Annual Research Report

URL: 

Published: 2022-04-19   Modified: 2024-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi