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

Construction of hyper-multimodal image classification technology based on the cognitive, decision-making, and behavioral processes of engineers

Research Project

Project/Area Number 20K19856
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionHokkaido University

Principal Investigator

Maeda Keisuke  北海道大学, 情報科学研究院, 特任助教 (20798243)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Discontinued (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2023: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2022: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords画像分類 / 生体情報 / 機械学習 / 解釈性 / 暗黙知 / 深層学習 / 信号処理 / マルチモーダル
Outline of Research at the Start

本研究では,AI技術の実社会応用へ向けて,技術者から取得する様々な生体情報・専門画像・それに対する判断結果を用い,認知・判断・行動プロセスを組み込んだハイパーマルチモーダル画像分類技術の構築を目的とする.専門分野にAI技術を導入するためには,高い精度のみならず,確かな信頼性が不可欠となるため,技術者に近い判断が可能かつ判断根拠を提示可能なモデルを構築する必要がある.そこで,本研究では,複数の生体情報から技術者に共通の知識及び経験を抽出することで,技術者に近い判断が可能な信頼性が担保された専門画像分類技術を構築する.これにより,高い解釈性・信頼性を有するAI技術が実現する.

Outline of Final Research Achievements

This study constructed a hyper-multimodal image classification technology that incorporates cognitive, decision-making, and behavioral processes, using various biometric data, images, and classification results obtained from engineers, for real-world applications of AI technology. Specifically, by extracting knowledge and experience common to engineers from multiple biometric data, a reliable image classification technology that enables judgments similar to those of engineers can be constructed. This enables the AI to learn what engineers paid attention to and how they made judgments, and to present the basis for their judgments from the actually constructed model, thus realizing an AI with high interpretability and reliability.

Academic Significance and Societal Importance of the Research Achievements

従来のAI分野では、人間の視覚野における局所受容野の働きを模擬した学習手法が提案されているものの、これらは構造の模擬に留まっていた。近年、脳波や視線情報などの人間から得られる生体情報を用いて、画像分類の精度向上を目的とする研究が進められているが、これらは生体情報の利用による判断結果の取得のみに留まっている。そこで、本研究では、技術者の認知・判断・行動プロセスに注目することで、生体特徴と判断結果の関係性の抽出とAIの判断結果の抽出を融合した画像分類技術を構築した。本技術は、様々な専門分野に横展開可能であり、技術継承問題の解決策としての利活用も期待されることから、高い学術的意義を有する。

Report

(4 results)
  • 2023 Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (86 results)

All 2023 2022 2021 2020 Other

All Journal Article (19 results) (of which Peer Reviewed: 19 results,  Open Access: 18 results) Presentation (64 results) (of which Int'l Joint Research: 32 results,  Invited: 1 results) Remarks (3 results)

  • [Journal Article] Estimation of Degradation Degree in Road Infrastructure Based on Multi-Modal ABN Using Contrastive Learning2023

    • Author(s)
      Higashi Takaaki、Ogawa Naoki、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Sensors

      Volume: 23 Issue: 3 Pages: 1657-1657

    • DOI

      10.3390/s23031657

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] WINTER ROAD SURFACE CONDITION CLASSIFICATION USING DEEP LEARNING WITH FOCAL LOSS BASED ON TEXT AND IMAGE INFORMATION2022

    • Author(s)
      諸戸 祐哉, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 293-306

    • DOI

      10.11532/jsceiii.3.J2_293

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] CLASSIFICATION OF INSPECTION ACTION OF ENGINEERS FOR EFFICIENT VIDEO PRESENTATION TO ASSIST ASSESSMENT OF INFRASTRUCTURE FACILITY DISTRESS2022

    • Author(s)
      上川 恭平、前田 圭介、藤後 廉、小川 貴弘、長谷山 美紀
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 811-818

    • DOI

      10.11532/jsceiii.3.J2_811

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] DETERIORATION LEVEL CLASSIFICATION OF DISTRESS IMAGE CONSIDERING CORRELATION AMONG HETEROGENEOUS FEATURES AND ATTENTION MAP CONFIDENCE2022

    • Author(s)
      小川 直輝、前田 圭介、小川 貴弘、長谷山 美紀
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 704-713

    • DOI

      10.11532/jsceiii.3.J2_704

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] DISTRESS DETECTION BASED ON VISION TRANSFORMER USING EGOCENTRIC VIDEOS WHILE INSPECTING IN SUBWEY TUNNELS2022

    • Author(s)
      櫻井 慶悟、前田 圭介、藤後 廉、小川 貴弘、長谷山 美紀
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 470-478

    • DOI

      10.11532/jsceiii.3.J2_470

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Distress Detection in Subway Tunnel Images via Data Augmentation Based on Selective Image Cropping and Patching2022

    • Author(s)
      Maeda Keisuke、Takada Saya、Haruyama Tomoki、Togo Ren、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Sensors

      Volume: 22 Issue: 22 Pages: 8932-8932

    • DOI

      10.3390/s22228932

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Deterioration Level Estimation Based on Convolutional Neural Network Using Confidence-Aware Attention Mechanism for Infrastructure Inspection2022

    • Author(s)
      Ogawa Naoki、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Sensors

      Volume: 22 Issue: 1 Pages: 382-382

    • DOI

      10.3390/s22010382

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Time-Lag Aware Latent Variable Model for Prediction of Important Scenes Using Baseball Videos and Tweets2022

    • Author(s)
      Hirasawa Kaito、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Sensors

      Volume: 22 Issue: 7 Pages: 2465-2465

    • DOI

      10.3390/s22072465

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Refining Graph Representation for Cross-Domain Recommendation Based on Edge Pruning in Latent Space2022

    • Author(s)
      Hirakawa Taisei、Maeda Keisuke、Ogawa Takahiro、Asamizu Satoshi、Haseyama Miki
    • Journal Title

      IEEE Access

      Volume: 10 Pages: 12503-12509

    • DOI

      10.1109/access.2022.3142187

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Reliable Estimation of Deterioration Levels via Late Fusion Using Multi-View Distress Images for Practical Inspection2021

    • Author(s)
      Maeda Keisuke、Ogawa Naoki、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Journal of Imaging

      Volume: 7 Issue: 12 Pages: 273-273

    • DOI

      10.3390/jimaging7120273

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Feature Integration Through Semi-Supervised Multimodal Gaussian Process Latent Variable Model With Pseudo-Labels for Interest Level Estimation2021

    • Author(s)
      Kamikawa Kyohei、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      IEEE Access

      Volume: 9 Pages: 163843-163850

    • DOI

      10.1109/access.2021.3131979

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Detection of Important Scenes in Baseball Videos via Bidirectional Time Lag Aware Deep Multiset Canonical Correlation Analysis2021

    • Author(s)
      Hirasawa Kaito、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      IEEE Access

      Volume: 9 Pages: 84971-84981

    • DOI

      10.1109/access.2021.3088284

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Distress Image Retrieval for Infrastructure Maintenance via Self-Trained Deep Metric Learning Using Experts’ Knowledge2021

    • Author(s)
      Ogawa Naoki、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      IEEE Access

      Volume: 9 Pages: 65234-65245

    • DOI

      10.1109/access.2021.3074019

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Multi-Task Convolutional Neural Network Leading to High Performance and Interpretability via Attribute Estimation2020

    • Author(s)
      MAEDA Keisuke、HORII Kazaha、OGAWA Takahiro、HASEYAMA Miki
    • Journal Title

      IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

      Volume: E103.A Issue: 12 Pages: 1609-1612

    • DOI

      10.1587/transfun.2020SML0006

    • NAID

      130007948361

    • ISSN
      0916-8508, 1745-1337
    • Year and Date
      2020-12-01
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] SIMILAR INSPECTION DATA RETRIEVAL FOR ROAD STRUCTURE INSPECTION BASED ON CANONICAL CORRELATION BETWEEN EYE TRACKING DATA AND INSPECTION RECORDS2020

    • Author(s)
      MAEDA Keisuke、SAITO Ryota、TAKAHASHI Sho、OGAWA Takahiro、HASEYAMA Miki
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. F3 (Civil Engineering Informatics)

      Volume: 76 Issue: 1 Pages: 74-86

    • DOI

      10.2208/jscejcei.76.1_74

    • NAID

      130007958485

    • ISSN
      2185-6591
    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Deterioration level estimation via neural network maximizing category-based ordinally supervised multi-view canonical correlation2020

    • Author(s)
      Maeda Keisuke、Takahashi Sho、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Multimedia Tools and Applications

      Volume: - Issue: 15 Pages: 1-22

    • DOI

      10.1007/s11042-020-10040-2

    • NAID

      120007173915

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Human-Centric Emotion Estimation Based on Correlation Maximization Considering Changes With Time in Visual Attention and Brain Activity2020

    • Author(s)
      Moroto Yuya、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      IEEE Access

      Volume: 8 Pages: 203358-203368

    • DOI

      10.1109/access.2020.3036908

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Tensor-Based Emotional Category Classification via Visual Attention-Based Heterogeneous CNN Feature Fusion2020

    • Author(s)
      Moroto Yuya、Maeda Keisuke、Ogawa Takahiro、Haseyama Miki
    • Journal Title

      Sensors

      Volume: 20 Issue: 7 Pages: 2146-2146

    • DOI

      10.3390/s20072146

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] [Papers] Interpretable Convolutional Neural Network Including Attribute Estimation for Image Classification2020

    • Author(s)
      Kazaha Horii, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Journal Title

      ITE Transactions on Media Technology and Applications

      Volume: 8 Issue: 2 Pages: 111-124

    • DOI

      10.3169/mta.8.111

    • NAID

      130007825882

    • ISSN
      2186-7364
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] ユーザの視線情報を考慮したコンテンツベースの画像再検索に関する検討2023

    • Author(s)
      馮 鈺虎, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2022 Annual Research Report
  • [Presentation] クラス情報を導入したグラフ表現による教師有り潜在変数モデルの高精度化に関する検討2023

    • Author(s)
      渡部 航史, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2022 Annual Research Report
  • [Presentation] サッカー映像における時空間的関係を考慮したシュート予測の高精度化に関する検討 -競技者のチーム情報に基づく完全二部グラフの導入-2023

    • Author(s)
      五箇 亮太, 諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2022 Annual Research Report
  • [Presentation] 属性情報の階層関係を考慮したアニメイラストのマルチラベル分類に関する検討2023

    • Author(s)
      蘭 子文, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2022 Annual Research Report
  • [Presentation] Action classification based on LSTM using first and third person videos of engineers inspecting bridges2022

    • Author(s)
      Tsuyoshi Masuda, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Gaussian distributed graph constrained multi-modal Gaussian process latent variable model for ordinal labeled data2022

    • Author(s)
      Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Image Processing (ICIP 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 道路構造物の変状画像分類の高精度化に関する検討ー自己教師あり学習の導入による事前知識の活用ー2022

    • Author(s)
      東 孝明, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      第37回 信号処理シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Generative adversarial network including referring image segmentation for text-guided image manipulation2022

    • Author(s)
      Yuto Watanabe, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Distributed label dequantized Gaussian process latent variable model for multi-view data integration2022

    • Author(s)
      Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Variational Bayesian graph convolutional network for robust collaborative filtering2022

    • Author(s)
      Nozomu Onodera, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Assessment of image manipulation using natural language description: quantification of manipulation direction2022

    • Author(s)
      Yuto Watanabe, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE International Conference on Image Processing (ICIP 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Shoot event prediction from soccer videos by considering players' spatio-temporal relations2022

    • Author(s)
      Ryota Goka, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE 11th Global Conference on Consumer Electronics (GCCE 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Cross-platform recommendation considering common users' preferences based on preference propagation graphnet2022

    • Author(s)
      Kazuki Yamamoto, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama
    • Organizer
      2022 IEEE 11th Global Conference on Consumer Electronics (GCCE 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ドメイン共有ネットワークに基づく嗜好のドメイン依存性に頑健な推薦システムに関する検討2022

    • Author(s)
      山本 一輝, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和4年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] サッカー競技のスカウティング映像における選手間の時空間的関係を考慮した不確実性に基づくシュートイベント予測に関する検討2022

    • Author(s)
      五箇 亮太, 諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和4年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 協調フィルタリングにおける潜在因子モデルの埋め込み表現と人気バイアスの関係の検討2022

    • Author(s)
      岡村 洋希, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和4年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Popularity-aware graph social recommendation for fully non-interaction users2022

    • Author(s)
      Nozomu Onodera, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      The 4th ACM International Conference on Multimedia in Asia (MM Asia 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 高速道路の遮音壁画像を用いた物体検出手法による変状分類の高精度化に関する検討2022

    • Author(s)
      梁, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 地下鉄トンネルの維持管理支援のためのマルチスケール解析を導入した深層学習に基づく変状検出に関する検討2022

    • Author(s)
      高田 紗弥, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 地下鉄トンネル点検時の技術者から取得される生体信号と技術者の点検行動の関連性分析2022

    • Author(s)
      平澤 魁人, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 画像注視時の脳活動信号を用いた圧縮再構成ネットワークに基づく視覚認知内容の推定に関する検討2022

    • Author(s)
      東 孝明, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] Attention map に対する確信度を考慮可能な深層学習を用いた変状分類の高精度化に関する検討2022

    • Author(s)
      小川 直輝, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 画像中の物体情報を考慮したユーザ類似度に基づく個人に特化した注視領域の推定に関する検討2022

    • Author(s)
      諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] ユーザの動作情報を用いたコンテンツの関心度推定に関する検討 -複数ユーザを導入した特徴統合の有効性検証-2022

    • Author(s)
      上川 恭平, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 道路構造物の維持管理効率化に向けた変状画像分類の高精度化に関する検討 -テキストデータに基づく類似事例の含有率の導入-2022

    • Author(s)
      平川 泰成, 小川 直輝, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] ゴム材料開発のための generative adversarial network に基づく配合量および物性からの電子顕微鏡画像の生成に関する一検討2022

    • Author(s)
      柳 凜太郎, 藤後 廉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 知識蒸留を用いたfew-shot learningに基づく画像の感情ラベル推定に関する検討2022

    • Author(s)
      叶 穎睿, 諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] A note on realizing adversarial defense based on regularization of multi-stage squeeze-and-excitation features2022

    • Author(s)
      Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      ITE Technical Report
    • Related Report
      2021 Research-status Report
  • [Presentation] Captioning 特徴を利用したグラフ畳み込みネットワークに基づくアニメイラストのマルチラベル画像分類に関する検討2022

    • Author(s)
      蘭 子文, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] 橋梁点検時の技術者の一人称および三人称視点映像を用いた点検動作の分類に関する検討2022

    • Author(s)
      増田 毅, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2021 Research-status Report
  • [Presentation] Text-guided image manipulation for desired region using referring image segmentation2021

    • Author(s)
      Yuto Watanabe, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Defense against image captioning attacks via a robust and stable recurrent neural network2021

    • Author(s)
      Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Multi-Label image recognition based on multi-modal graph convolutional networks using captioning features2021

    • Author(s)
      Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Graph analysis-based recommendation via entity embeddings using wikipedia2021

    • Author(s)
      Nozomu Onodera, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Visual sentiment prediction using few-shot learning via distribution relations of visual features2021

    • Author(s)
      Yingrui Ye, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Analysis of social trends related to COVID-19 pandemic utilizing social media data2021

    • Author(s)
      Taisei Hirakawa, Keisuke Maeda, Takahiro Ogawa, Satoshi Asamizu, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Movie rating estimation based on weakly supervised multi-modal latent variable model2021

    • Author(s)
      Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] A trial of fine-grained classification of expert-novice level using bio-signals while inspecting subway tunnels2021

    • Author(s)
      Kaito Hirasawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE Global Conference on Consumer Electronics
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Few-shot personalized saliency prediction using person similarity based on collaborative multi-output Gaussian process regression2021

    • Author(s)
      Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Correlation-aware attention branch network using multi-modal data for deterioration level estimation of infrastructures2021

    • Author(s)
      Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Time-lag aware multi-modal variational autoencoder using baseball videos and tweets for prediction of important scenes2021

    • Author(s)
      Kaito Hirasawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Interest level estimation via multi-modal Gaussian process latent variable factorization2021

    • Author(s)
      Kyohei Kamikawa, Maeda Keisuke, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Cross-domain recommendation method based on multi-layer graph analysis with visual information2021

    • Author(s)
      Taisei Hirakawa, Keisuke Maeda, Takahiro Ogawa, Satoshi Asamizu, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Deep metric network via heterogeneous semantics for image sentiment analysis2021

    • Author(s)
      Yun Liang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Image Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Degradation level estimation of road structures via attention branch network with text data2021

    • Author(s)
      Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Consumer Electronics-Taiwan
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Estimation of visual features of viewed image from individual and shared brain information based on fMRI data using probabilistic generative model2021

    • Author(s)
      Takaaki Higashi, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Classification of expert-novice level using eye tracking and motion data via conditional multimodal variational autoencoder2021

    • Author(s)
      Yusuke Akamatsu, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Multi-modal label dequantized gaussian process latent variable model for ordinal label estimation2021

    • Author(s)
      Masanao Matsumoto, Keisuke Maeda, Naoki Saito, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Cross-domain semi-supervised deep metric learning for image sentiment analysis2021

    • Author(s)
      Yun Liang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Feature integration via semi-supervised ordinally multi-modal Gaussian process latent variable model2021

    • Author(s)
      Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Shilling attackの状況下における グラフ解析に基づく推薦システムの脆弱性の検証2021

    • Author(s)
      小野寺 望, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和3年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] Few-shot learningを用いた感情ラベル推定における複数のデータセット利用に関する初期検討2021

    • Author(s)
      叶 穎睿, 諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和3年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] 自己教師あり学習を導入した潜在変数モデルによる低次元特徴の抽出に関する検討2021

    • Author(s)
      渡部 航史, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和3年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] グラフ畳み込みネットワークに基づくアニメイラストのマルチラベル画像認識に関する検討2021

    • Author(s)
      蘭 子文, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和3年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] テキスト入力型画像操作における操作領域に着目した精度評価に関する検討2021

    • Author(s)
      渡邉 優宇人, 藤後 廉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和3年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] Human emotion estimation using multi-modal variational autoencoder with time changes2021

    • Author(s)
      Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      Global Conference on Life Sciences and Technologies
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 路面画像を用いた深層学習に基づく路面状態の分類に関する検討2021

    • Author(s)
      諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2020 Research-status Report
    • Invited
  • [Presentation] Attention Map を用いた道路構造物の変状画像分類におけるテキストデータの導入に基づく高精度化に関する検討2021

    • Author(s)
      小川 直輝, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2020 Research-status Report
  • [Presentation] 地下鉄トンネル点検時の技術者から取得される視線およびモーションデータに基づく熟練度の推定に関する検討2021

    • Author(s)
      赤松 祐亮, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2020 Research-status Report
  • [Presentation] 地下鉄トンネルの維持管理支援を目的とした深層学習に基づく変状検出の高精度化に関する検討 - 壁面の施工方法に注目した精度検証 -2021

    • Author(s)
      春山 知生, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      映像情報メディア学会技術報告
    • Related Report
      2020 Research-status Report
  • [Presentation] Study on Automatic Diagnosis Algorithm for Transmission Equipment Using AI Technology2020

    • Author(s)
      Takuya Inoue, Toshikazu Teshigawara, Yusuke Yamauchi, Sakae Taniguchi, Takahisa Ono, Hiroshi Hamada, Hiroyuki Miyoshi, Fumito Minoura Tomoki Kitashima, Masahito Hashimoto, Masashi Iwaki, Yuka Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      CIGRE - AORC Technical Meeting
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Estimation of person-specific visual attention via selection of similar persons2020

    • Author(s)
      Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
    • Organizer
      International Conference on Consumer Electronics-Taiwan
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 路面画像を用いた異常検知に基づく路面状態の識別に関する検討2020

    • Author(s)
      諸戸 祐哉, 前田 圭介, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和2年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2020 Research-status Report
  • [Presentation] RICAPに基づくデータ拡張による地下鉄トンネルにおける変状検出精度の向上に関する検討2020

    • Author(s)
      春山 知生, 前田 圭介, 藤後 廉, 小川 貴弘, 長谷山 美紀
    • Organizer
      令和2年度 電気・情報関係学会北海道支部連合大会
    • Related Report
      2020 Research-status Report
  • [Remarks]

    • URL

      https://www-lmd.ist.hokudai.ac.jp/member/keisuke-maeda/

    • Related Report
      2022 Annual Research Report
  • [Remarks] 北海道大学大学院情報科学研究院メディアダイナミクス研究室 研究室メンバー

    • URL

      https://www-lmd.ist.hokudai.ac.jp/member/keisuke-maeda/

    • Related Report
      2021 Research-status Report
  • [Remarks] 北海道大学大学院情報科学研究院メディアダイナミクス研究室 研究室メンバー

    • URL

      https://www-lmd.ist.hokudai.ac.jp/member/maeda/

    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi