Daichi Azuma

prof_pic.jpg

Tokyo, Japan

azuma.daichi.n21@kyoto-u.jp

My interests are in the intersection between 3D Computer Vision, Neural Language Processing. More specially,

  • Embodied AI
  • Vision and Language Navigation
  • Robot Manipulation

news

Aug 08, 2024 We will be presenting at 日本ロボット学会学術講演会（RSJ2024）held in Osaka at September 6, 2024.
  • 3D1-04: 基盤モデルと地図モジュールを用いたゼロショットロボット質問応答の実現
Aug 07, 2024 We will be presenting a poster at MIRU2024 at August 9, 2024.
  • IS-3-137: 実世界質問応答のための拡散モデルを用いた回答可能位置の予測
Jul 01, 2024 Two papers are accepted to IROS2024.
  • Answerability Fields: Answerable Location Estimation via Diffusion Models
  • Map-based Modular Approach for Zero-shot Embodied Question Answering
For more details, check out publications page

publications

  1. citynav.png
    CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information
    Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, and Nakamasa Inoue
    In , 2024
    arXiv
  2. IROS2024/Oral
    ansfields.png
    Answerability Fields: Answerable Location Estimation via Diffusion Models
    Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, and Motoaki Kawanabe
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    arXiv Bib
  3. IROS2024
    mapbased.png
    Map-based Modular Approach for Zero-shot Embodied Question Answering
    Koya Sakamoto, Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, and Motoaki Kawanabe
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    arXiv Bib
  4. 3DV2024
    cross3dvg.png
    Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans
    Taiki Miyanishi, Daichi Azuma, Shuhei Kurita, and Motoaki Kawanabe
    In The 10th International Conference on 3D Vision (3DV), 2024
    arXiv Bib Code
  5. CVPR2022/Oral
    scanqa.png
    ScanQA: 3D Question Answering for Spatial Scene Understanding
    Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, and Motoaki Kawanabe
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    arXiv Bib PDF Code
    110 Google Scholar citations

achievements

International Conference

  • Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto and Motoaki Kawanabe, “Answerability Fields: Answerable Location Estimation via Diffusion Models”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2024), 2024.
  • Koya Sakamoto, Daichi Azuma, Taiki Miyanishi, Shuhei Kurita and Motoaki Kawanabe, “Map-based Modular Approach for Zero-shot Embodied Question Answering”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2024), 2024.
  • Taiki Miyanishi, Daichi Azuma, Shuhei Kurita and Motoaki Kawanabe, “Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans”, International Conference on 3D Vision 2024 (3DV2024), 2024.
  • Daichi Azuma*, Taiki Miyanishi*, Shuhei Kurita* and Motoaki Kawanabe, “ScanQA: 3D Question Answering for Spatial Scene Understanding”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022), pages 19129-19139, New Orleans, 2022. *: Equally contributed.

Local Conference

  • 基盤モデルと地図モジュールを用いたゼロショットロボット質問応答の実現, 第42回 日本ロボット学会学術講演会　（RSJ2024）,大阪, 2024.9, 坂本滉也, 東大地, 宮西大樹, 栗田修平, 川鍋一晃
  • 実世界質問応答のための拡散モデルを用いた回答可能位置の予測, 第27回 画像の認識・理解シンポジウム（MIRU2024）,熊本, 2024.8, 東大地, 宮西大樹, 栗田修平, 坂本滉也, 川鍋一晃
  • 異なるRGB-Dスキャンを用いたデータセット横断3D言語接地, 2023年度 人工知能学会全国大会（第37回）,熊本, 2023.6 宮西大樹, 東大地, 栗田修平, 川鍋一晃
  • 屋内環境の意味的理解に向けた3次元質問応答, 第25回 画像の認識・理解シンポジウム（MIRU2022）,兵庫, 2022.7, 東大地, 宮西大樹, 栗田修平, 川鍋一晃

Invited Talks

  • ScanQA: 3D Question Answering for Spatial Scene Understanding. MIRU2022. Daichi Azuma, Taiki Miyanishi, Shuhei Kurita and Motoaki Kawanabe

Academic Services

  • IROS2024 Reviewer