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

Human behavior sensing by integrated analysis of first, second, and third-person point of view videos

Research Project

Project/Area Number 20H04205
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionThe University of Tokyo

Principal Investigator

Sato Yoichi  東京大学, 生産技術研究所, 教授 (70302627)

Co-Investigator(Kenkyū-buntansha) 菅野 裕介  東京大学, 生産技術研究所, 准教授 (10593585)
Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2023: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2022: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2021: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥5,590,000 (Direct Cost: ¥4,300,000、Indirect Cost: ¥1,290,000)
Keywords一人称視点映像解析 / 人物行動理解 / 人物行動センシング / 動作認識 / 複数視点統合 / コンピュータビジョン
Outline of Research at the Start

映像解析による人物行動センシングは様々な応用分野で欠くことのできない基盤技術となっている。しかしながら、これまでは固定視点映像、自己視点映像、他者視点映像という異なる視点からの映像が個別に用いられていたため、センシングされる行動の粒度や継続性等の限界が存在した。また、人とのインタラクションにおける行動について、単一の自己視点映像や他者視点映像では、互いとのやり取りの中での解析が出来なかった。本研究課題では、固定視点・自己視点・他者視点という異なる視点映像の統合解析を他に先駆けて実現し、これまでの映像からの人物行動センシングが抱えるこれらの課題の解決を目指す。

Outline of Final Research Achievements

In this project, we conducted research on the sensing of human behavior by integrated analysis of videos from different viewpoints (self-viewpoint, other viewpoint, and fixed viewpoint) in four aspects: 1. Feature learning for comprehensive analysis of multiple viewpoint videos by self-supervised learning, 2. Spatio-temporal alignment of videos from different viewpoints, 3. Human behavior understanding by integration of self-viewpoint and fixed viewpoint videos, and 4. Interaction analysis by integration of self-viewpoint and other viewpoint videos.

Academic Significance and Societal Importance of the Research Achievements

映像に基づく人物行動理解技術は、様々なアプリケーションドメインにおいて書くことが出来ない重要な基盤技術であり、これまでもコンピュータビジョンの分野において活発に研究が進められてきた。これまでは、固定視点映像、自己視点映像、他者視点映像という異なる視点映像が別々に扱われていたのに対し、本研究課題では、他に先駆けて固定視点・自己視点・他者視点という異なる視点映像の統合解析に取り組み、映像に基づく人物行動理解の高度化に貢献する成果を得ることができた。

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (25 results)

All 2023 2022 2021 2020

All Journal Article (3 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 3 results,  Open Access: 1 results) Presentation (22 results) (of which Int'l Joint Research: 15 results,  Invited: 1 results)

  • [Journal Article] Semantic Image Segmentation by Dynamic Discriminative Prototypes2023

    • Author(s)
      Kaipeng Zhang and Yoichi Sato
    • Journal Title

      IEEE Transactions on Multimedia

      Volume: 26 Pages: 737-749

    • DOI

      10.1109/tmm.2023.3270637

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey2023

    • Author(s)
      Ohkawa Takehiko、Furuta Ryosuke、Sato Yoichi
    • Journal Title

      International Journal of Computer Vision

      Volume: 131 Issue: 12 Pages: 3193-3206

    • DOI

      10.1007/s11263-023-01856-0

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Spatio-Temporal Perturbations for Video Attribution2022

    • Author(s)
      Zhenqiang Li, Weimin Wang, Zuoyue Li, Yifei Huang, and Yoichi Sato
    • Journal Title

      IEEE Transactions on Circuits and Systems for Video Technology

      Volume: 32 Issue: 4 Pages: 2043-2056

    • DOI

      10.1109/tcsvt.2021.3081761

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Weakly Supervised Temporal Sentence Grounding with Uncertainty-Guided Self-training2023

    • Author(s)
      Yifei Huang, Lijin Yang, and Yoichi Sato
    • Organizer
      IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] DeCo : Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking2023

    • Author(s)
      Lijin Yang, Quang Kong, Hsuan-Kung Yang, Wadim Kehl, Yoichi Sato, and Norimasa Kobori
    • Organizer
      IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotations2023

    • Author(s)
      Takuma Yagi, Misaki Ohashi, Yifei Huang, Ryosuke Furuta, Shungo Adachi, Toutai Mitsuyama, and Yoichi Sato
    • Organizer
      Joint International 3rd Ego4D and 11th EPIC Workshop
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Proposal-based Temporal Action Localization with Point-level Supervision2023

    • Author(s)
      Yuan Yin, Yifei Huang, Ryosuke Furuta, and Yoichi Sato
    • Organizer
      British Machine Vision Conference
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 大規模言語モデルを用いた学習カテゴリの自動決定による映像からのオープン語彙物体状態認識2023

    • Author(s)
      舘野将寿、八木拓真、古田諒佑、佐藤洋一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2023 Annual Research Report
  • [Presentation] 一人称視点映像を対象としたfew-shotアクティビティ認識2023

    • Author(s)
      佐藤禎哉、高木基宏、古田諒佑、菅野裕介、佐藤洋一
    • Organizer
      画像の認識・理解シンポジウム
    • Related Report
      2023 Annual Research Report
  • [Presentation] FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation2023

    • Author(s)
      八木 拓真, 大橋 実咲, 黄 逸飛, 古田 諒佑, 足達 俊吾, 光山 統泰, 佐藤 洋一
    • Organizer
      日本バイオインフォマティクス学会年会
    • Related Report
      2023 Annual Research Report
  • [Presentation] FineBio:密な階層アノテーションを付与したバイオ実験映像データセット2023

    • Author(s)
      八木 拓真, 大橋 実咲, 黄 逸飛, 古田 諒佑, 足達 俊吾, 光山 統泰, 佐藤 洋一
    • Organizer
      日本分子生物学会年会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Compound Prototype Matching for Few-shot Action Recognition2022

    • Author(s)
      Yifei Huang, Lijin Yang, and Yoichi Sato
    • Organizer
      European Conference on Computer Vision (ECCV 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Interact before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition2022

    • Author(s)
      Lijin Yang, Yifei Huang, Yusuke Sugano, and Yoichi Sato
    • Organizer
      IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos2022

    • Author(s)
      Zecheng Yu, Yifei Huang, Ryosuke Furuta, Takuma Yagi, Yusuke Gotsu, and Yoichi Sato
    • Organizer
      IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Domain Adaptive Hand Keypoint and Pixel Localization in the Wild2022

    • Author(s)
      Takehiko Ohkawa, Yu-Jhe Li, Qichen Fu, Ryosuke Furuta, Kris Kitani, and Yoichi Sato
    • Organizer
      European Conference on Computer Vision (ECCV 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Surgical Skill Assessment via Video Semantic Aggregation2022

    • Author(s)
      Zhenqiang Li, Ling Gu, Weimin Wang, Ryosuke Nakamura, and Yoichi Sato
    • Organizer
      International Conference on Medical Computing and Computer Assisted Invention (MICCAI 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction2021

    • Author(s)
      Takuma Yagi, Md Tasnimul Hasan, and Yoichi Sato
    • Organizer
      British Machine Vision Conference (BMVC 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips2021

    • Author(s)
      Lijin Yang, Yifei Huang, Yusuke Sugano, and Yoichi Sato
    • Organizer
      British Machine Vision Conference (BMVC 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Neural Routing by Memory2021

    • Author(s)
      Kaipeng Zhang, Zhenqiang Li, Zhifeng Li, Wei Liu, and Yoichi Sato
    • Organizer
      The 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 誘導付き逐次ラベル訂正に基づく映像からの手・物体接触判定2021

    • Author(s)
      八木拓真、Md. Tasnimul Hasan、佐藤洋一
    • Organizer
      画像の認識・理解シンポジウム(MIRU 2021)
    • Related Report
      2021 Annual Research Report
  • [Presentation] Cross-view Non-local Neural Networks for Joint Representation Learning between First and Third Person Videos2021

    • Author(s)
      Zhehao Zhu, Yusuke Sugano and Yoichi Sato
    • Organizer
      画像の認識・理解シンポジウム(MIRU 2021)
    • Related Report
      2021 Annual Research Report
  • [Presentation] Cross-View Non-Local Neural Networks for Joint Representation Learning Between First and Third Person Videos2021

    • Author(s)
      Zhehao Zhu, Yusuke Sugano, and Yoichi Sato
    • 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
      2020 Annual Research Report
  • [Presentation] Toward Visually Explaining Video Classification Networks by Pertubation-based Method2021

    • Author(s)
      Zhenqiang Li, Weimin Wang, Zuoyue Li, Yifei Huang, and Yoichi Sato
    • Organizer
      IEEE Winter Conference on Applications of Computer Vision (WACV 2021)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Improving Action Segmentation via Graph Based Temporal Reasoning2020

    • Author(s)
      Yifei Huang, Yusuke Sugano, and Yoichi Sato
    • Organizer
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Analyzing Human Activity and Attention from First-Person Perspectives2020

    • Author(s)
      Yoichi Sato
    • Organizer
      International Workshop on Egocentric Perception, Interaction and Computing
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research / Invited

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi