| ホーム | メンバー | 研究内容 | アクセス |

| English | 

主な研究項目
  • コンピュータビジョン
  • ロボティクス
  • 機械学習
  • 3Dデータ認識
資料


論文
  1. Yuzhe Hao, Asako Kanezaki, Ikuro Sato, Rei Kawakami, and Koichi Shinoda.
    Egocentric Human Activities Recognition with Multi-modal Interaction Sensing.
    IEEE Sensors, accepted, 2024.

  2. Haruyuki Nakagawa and Asako Kanezaki.
    Multi-Agent Visual Coordination using Optical Wireless Communication.
    IEEE Robotics and Automation Letters (RA-L), accepted, 2023.
    https://doi.org/10.1109/LRA.2023.3304905

  3. Hao Zheng, Qiang Zhang, and Asako Kanezaki.
    DAC: Disentanglement-and-Calibration Module for Cross-Domain Few-Shot Classification.
    IEEE Access, Vol. 11, No. 23552466, pp. 82665-82673, 2023.
    https://doi.org/10.1109/ACCESS.2023.3294984

  4. 太田佳，金崎朝子.
    動的環境下におけるロボットの動作生成.
    日本ロボット学会誌, Vol.39, No.7, pp. 581-586, 2021.

  5. Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida.
    RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-view Images.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol.43, Issue 1, pp. 269-283, 2021.
    https://doi.org/10.1109/TPAMI.2019.2922640  
    Project

  6. Wonjik Kim*, Asako Kanezaki*, and Masayuki Tanaka.
    Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering.
    IEEE Transactions on Image Processing, accepted, 2020.
    *equal contributions
    Project

  7. Raphael Druon, Yusuke Yoshiyasu, Asako Kanezaki, and Alassane Watt.
    Visual Object Search by Learning Spatial Context.
    IEEE Robotics and Automation Letters (RA-L), Vol.5, Issue 2, pp.1279-1286, 2020. (presented in ICRA'20)
    https://doi.org/10.1109/LRA.2020.2967677

  8. Asako Kanezaki, Jirou Nitta, and Yoko Sasaki.
    GOSELO: Goal-Directed Obstacle and Self-Location Map for Robot Navigation using Reactive Neural Networks.
    IEEE Robotics and Automation Letters (RA-L), Vol.3, Issue 2, pp.696-703, 2018. (presented in ICRA'18)
    https://doi.org/10.1109/LRA.2017.2783400
    Project

  9. Nevrez Imamoglu, Wataru Shimoda, Chi Zhang, Yuming Fang, Asako Kanezaki, Keiji Yanai, and Yoshifumi Nishida.
    An Integration of Bottom-up and Top-Down Salient Cues on RGB-D Data: Saliency from Objectness vs. Non-Objectness.
    Signal, Image and Video Processing (Springer), Vol.12, Issue 2, pp.307-314, 2017.
    https://doi.org/10.1007/s11760-017-1159-7

  10. Zoltan-Csaba Marton, Ferenc Balint-Benczedi, Oscar Martinez Mozos, Nico Blodow, Asako Kanezaki, Lucian Cosmin Goron, Dejan Pangercic, and Michael Beetz.
    Part-Based Geometric Categorization and Object Reconstruction in Cluttered Table-Top Scenes.
    Journal of Intelligent & Robotic Systems, pp.35-56, 2014.
    http://dx.doi.org/10.1007/s10846-013-0011-8

  11. Asako Kanezaki, Tatsuya Harada, and Yasuo Kuniyoshi.
    Partial Matching of Real Textured 3D Objects Using Color Cubic Higher-order Local Auto-Correlation Features.
    The Visual Computer, Vol.26, No.10, pp.1269-1281, 2010.
    https://doi.org/10.1007/s00371-010-0521-3

  12. 原田達也, 金崎朝子, 國吉康夫.
    三次元環境地図からの物体探索タスク応用を目指したカラー立体高次局所自己相関特徴の開発.
    日本ロボット学会誌, Vol.27, No.7, pp.749-758, 2009.
会議発表（海外）
  1. Kei Ota, Devesh Jha, Krishna Murthy Jatavallabhula, Asako Kanezaki, and Joshua B. Tenenbaum.
    Tactile Estimation of Extrinsic Contact Patch for Stable Placement.
    IEEE International Conference on Robotics and Automation (ICRA), accepted, 2024.

  2. Haruyuki Nakagawa, Yoshitaka Miyatani, and Asako Kanezaki.
    Linking Vision and Multi-Agent Communication through Visible Light Communication using Event Cameras.
    Int. Joint Conf. on Autonomous Agents & Multiagent Systems (AAMAS), accepted, 2024.
    Paper

  3. Haru Kondoh and Asako Kanezaki.
    Multi-goal Audio-visual Navigation using Sound Direction Map.
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), accepted, 2023. 　　　　
    Paper

  4. Nanami Kotani and Asako Kanezaki.
    Point Anywhere: Directed Object Estimation from Omnidirectional Images.
    Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters (SIGGRAPH '23 Posters), accepted, 2023.
    Paper   Dataset

  5. Wenru Zheng, Ryota Yoshihashi, Rei Kawakami, Ikuro Sato, and Asako Kanezaki.
    Multi Event Localization by Audio-Visual Fusion with Omnidirectional Camera and Microphone Array.
    6th CVPR Workshop on Multimodal Learning and Applications (MULA), accepted, 2023.
    Dataset

  6. Hao Zheng, Runqi Wang, Jianzhuang Liu, and Asako Kanezaki.
    Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification.
    International Conference on Learning Representations (ICLR), accepted, 2023.
    Paper   Code

  7. Kei Ota, Hsiao-Yu Tung, Kevin A. Smith, Anoop Cherian, Tim K. Marks, Alan Sullivan, Asako Kanezaki, and Joshua B. Tenenbaum.
    H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions.
    IEEE International Conference on Robotics and Automation (ICRA), accepted, 2023.
    Paper

  8. Yuzhe Hao, Kuniaki Uto, Asako Kanezaki, Ikuro Sato, Rei Kawakami, and Koichi Shinoda. 　　
    EvIs-Kitchen: Egocentric Human Activities Recognition with Video and Inertial Sensor data. 　　
    Multimedia Modeling (MMM), accepted, 2023. 　　

  9. Hana Hoshino, Kei Ota, Asako Kanezaki, and Rio Yokota.
    OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching.
    IEEE International Conference on Robotics and Automation (ICRA), accepted, 2022.
    Paper   Code

  10. Rui Fukushima, Kei Ota, Asako Kanezaki, Yoko Sasaki, and Yusuke Yoshiyasu.
    Object Memory Transformer for Object Goal Navigation.
    IEEE International Conference on Robotics and Automation (ICRA), accepted, 2022. 　　　　　　　　
    Paper   Code

  11. Takashi Konno, Ayako Amma, and Asako Kanezaki.
    Incremental Multi-view Object Detection from a Moving Camera.
    ACM Multimedia Asia (ACMMMA), accepted, 2020.
    Project

  12. Kei Ota, Devesh K. Jha, Tadashi Onishi, Asako Kanezaki, Yusuke Yoshiyasu, Yoko Sasaki, Toshisada Mariyama, Daniel Nikovski.
    Deep Reactive Planning in Dynamic Environments.
    The Conference on Robot Learning (CoRL), accepted, 2020.
    PDF YouTube

  13. Kei Ota, Yoko Sasaki, Devesh K. Jha, Yusuke Yoshiyasu, and Asako Kanezaki.
    Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path.
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020), accepted, 2020.
    PDF

  14. Yoko Sasaki, Syusuke Matsuo, Asako Kanezaki, and Hiroshi Takemura.
    A3C Based Motion Learning for an Autonomous Mobile Robot in Crowds.
    IEEE International Conference on System Man and Cybernetics (SMC2019), pp.1046-1052, 2019.

  15. Nevrez Imamoglu, Guanqun Ding, Yuming Fang, Asako Kanezaki, Toru Kouyama, and Ryosuke Nakamura.
    Salient object detection on hyperspectral images using features learned from unsupervised segmentation task.
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2192-2196, 2019.
    PDF

  16. Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida.
    RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5010-5019, 2018.
    Project

  17. Asako Kanezaki.
    Unsupervised Image Segmentation by Backpropagation.
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1543-1547, 2018.
    Project

  18. Mikiko Oono, Yoshifumi Nishida, Koji Kitamura, Asako Kanezaki, and Tatsuhiro Yamanaka.
    "Change the changeable" framework for implementation research in health.
    the 10th International Conference on Computer Supported Education (CSEDU), (oral), 2017.

  19. Ryohei Kuga, Asako Kanezaki, Masaki Samejima, Yusuke Sugano, and Yasuyuki Matsushita.
    Multi-modal U-Nets for Multi-task Scene Understanding.
    IEEE/ISPRS 4th Joint Workshop on Multi-Sensor Fusion for Dynamic Scene Understanding, pp.403-411, (oral), 2017.
    PDF

  20. Manolis Savva, Fisher Yu, Hao Su, Asako Kanezaki, Takahiko Furuya, Ryutarou Ohbuchi, Zhichao Zhou, Rui Yu, Song Bai, Xiang Bai, Masaki Aono, Atsushi Tatsuma, S. Thermos, A. Axenopoulos, G. Th. Papadopoulos, P. Daras, Xiao Deng, Zhouhui Lian, Bo Li, Henry Johan, Yijuan Lu, and Sanjeev Mk.
    SHREC'17 Track: Large-Scale 3D Shape Retrieval from ShapeNet Core55.
    Eurographics Workshop on 3D Object Retrieval 2017, 2017.
    PDF

  21. Binh-Son Hua, Quang-Trung Truong, Minh-Khoi Tran, Quang-Hieu Pham, Asako Kanezaki, Tang Lee, HungYueh Chiang, Winston Hsu, Bo Li, Yijuan Lu, Henry Johan, Shoki Tashiro, Masaki Aono, Minh-Triet Tran, Viet-Khoi Pham, Hai-Dang Nguyen, Vinh-Tiep Nguyen, Quang-Thang Tran, Thuyen V. Phan, Bao Truong, Minh N. Do, Anh-Duc Duong, Lap-Fai Yu, Duc Thanh Nguyen, and Sai-Kit Yeung.
    SHREC'17: RGB-D to CAD Retrieval with ObjectNN Dataset.
    Eurographics Workshop on 3D Object Retrieval 2017, 2017.
    PDF

  22. Tomoaki Saito, Asako Kanezaki, and Tatsuya Harada.
    IBC127: Video Dataset for Fine-grained Bird Classification.
    IEEE International Conference on Multimedia & Expo (ICME), 2016.
    Dataset

  23. Katsunori Ohnishi, Atsushi Kanehira, Asako Kanezaki, and Tatsuya Harada.
    Recognizing Activities of Daily Living with a Wrist-mounted Camera.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (spotlight), 2016.
    Project

  24. Chie Kamada, Asako Kanezaki, and Tatsuya Harada.
    Probabilistic Semi-Canonical Correlation Analysis.
    the 23rd Annual ACM International Conference on Multimedia (ACMMM 2015), pp.1131-1134, 2015.

  25. Asako Kanezaki and Tatsuya Harada.
    3D Selective Search for Obtaining Object Candidates.
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), pp.82-87, 2015.
    PDF code

  26. Asako Kanezaki, Emanuele Rodolà, Daniel Cremers, and Tatsuya Harada.
    Learning Similarities for Rigid and Non-Rigid Object Detection.
    International Conference on 3D Vision (3DV 2014), pp.720-727, 2014.
    PDF

  27. Sho Inaba, Asako Kanezaki, and Tatsuya Harada.
    Automatic Image Synthesis from Keywords Using Scene Context.
    the 22nd Annual ACM International Conference on Multimedia (ACMMM 2014), pp.1149-1152, 2014.

  28. Masaru Mizuochi, Asako Kanezaki, and Tatsuya Harada.
    Clothing Retrieval Based on Local Similarity with Multiple Images.
    the 22nd Annual ACM International Conference on Multimedia (ACMMM 2014), pp.1165-1168, 2014.

  29. Asako Kanezaki, Yusuke Mukuta, and Tatsuya Harada.
    Mirror Reflection Invariant HOG descriptors for Object Detection.
    IEEE 21st International Conference on Image Processing (ICIP 2014), pp.1594-1598, 2014.
    PDF

  30. Asako Kanezaki, Sho Inaba, Yoshitaka Ushiku, Yuya Yamashita, Hiroshi Muraoka, Yasuo Kuniyoshi, and Tatsuya Harada.
    Hard Negative Classes for Multiple Object Detection.
    IEEE International Conference on Robotics and Automation (ICRA 2014), pp.3066-3073, 2014.
    PDF

  31. Asako Kanezaki, Yasuo Kuniyoshi, and Tatsuya Harada.
    Weakly-supervised Multi-class Object Detection Using Multi-type 3D Features.
    the 21st Annual ACM International Conference on Multimedia (ACMMM 2013), pp.605-608, 2013.
    PDF Dataset

  32. Asako Kanezaki, Tatsuya Harada, and Yasuo Kuniyoshi.
    Scale and Rotation Invariant Color Features for Weakly-Supervised Object Learning in 3D Space.
    IEEE ICCV Workshop on 3D Representation and Recognition (3dRR-11), 2011.
    PDF

  33. Asako Kanezaki, Zoltan-Csaba Marton, Dejan Pangercic, Tatsuya Harada, Yasuo Kuniyoshi, and Michael Beetz.
    Voxelized Shape and Color Histograms for RGB-D.
    IEEE IROS Workshop on Active Semantic Perception and Object Search in the Real World (ASP-AVS-11), 2011.
    PDF

  34. Asako Kanezaki, Takahiro Suzuki, Tatsuya Harada, and Yasuo Kuniyoshi.
    Fast Object Detection for Robots in a Cluttered Indoor Environment Using Integral 3D Feature Table.
    IEEE International Conference on Robotics and Automation (ICRA 2011), pp.4026-4033, 2011.
    PDF

  35. Asako Kanezaki, Hideki Nakayama, Tatsuya Harada, and Yasuo Kuniyoshi.
    High-speed 3D Object Recognition Using Additive Features in A linear Subspace.
    2010 IEEE International Conference on Robotics and Automation (ICRA 2010), pp.3128-3134, 2010.
    2010 IEEE Robotics and Automation Society Japan Chapter Young Award (ICRA 2010)
    PDF

  36. Asako Kanezaki, Tatsuya Harada, and Yasuo Kuniyoshi.
    Partial Matching for Real Textured 3D Objects using Color Cubic Higher-order Local Auto-Correlation Features.
    Eurographics Workshop on 3D Object Retrieval 2009, pp.9-12, 2009.

会議発表（国内）
  1. 小谷 七海，金崎 朝子.
    注目領域の抽出に基づく全天球画像からの指示物体推定
    Meeting on Image Recognition and Understandings (MIRU), IS2-66, 2023.

  2. 合楽 慧，金崎 朝子.
    画像の意味的領域分割を用いた強化学習による室内環境探索
    Meeting on Image Recognition and Understandings (MIRU), IS2-109, 2023.

  3. 近藤 暖，金崎 朝子.
    動的複数音源定位手法を用いたマルチゴール視聴覚ナビゲーション
    Meeting on Image Recognition and Understandings (MIRU), IS3-109, 2023.

  4. Yunyi Guan and Asako Kanezaki.
    Active Object Recognition in Discrete and Continuous View Settings
    Meeting on Image Recognition and Understandings (MIRU), IS1-111, 2023.

  5. 神山 慶伍，太田 佳，高波 亮介，金崎 朝子.
    強化学習エージェントの軌跡を用いたサンプルベース経路計画
    Pattern Recognition and Media Understanding (PRMU), pp. 1-6, 2022.

  6. 中川 遥之，金崎 朝子.
    光無線通信を用いたマルチエージェント強化学習
    Meeting on Image Recognition and Understandings (MIRU), IS1-37, 2022.

  7. 熊坂 雅之，金崎 朝子.
    セグメンテーション画像を入力としたシーン分類手法の検討
    Meeting on Image Recognition and Understandings (MIRU), IS2-32, 2022.

  8. 北山 翼，川上 玲，佐藤 育郎，吉橋 亮太，金崎 朝子.
    球面畳み込みの時間軸拡張による全天球映像からの行動種別の領域分割
    Meeting on Image Recognition and Understandings (MIRU), IS1-68, 2022.

  9. Wenru Zheng, Rei Kawakami, Ikuro Sato, Ryota Yoshihashi, and Asako Kanezaki.
    Event Recognition by Audio-Visual Fusion with Omnidirectional Camera and Microphone Array
    Meeting on Image Recognition and Understandings (MIRU), IS2-65, 2022.

  10. 加納諒也，和田一義，金崎朝子，冨沢哲雄，谷川民生.
    深層学習による物体認識のためのマーカの検討 ～第一報：AlexNetによる認識率の比較～
    日本機械学会ロボティクス・メカトロニクス講演会, 2019.

  11. 佐々木洋子，松尾修佑，金崎朝子，竹村裕.
    歩行者観測履歴を用いた深層強化学習による車輪ロボットの雑踏切り抜け動作生成
    日本機械学会ロボティクス・メカトロニクス講演会, 2019.

  12. 佐々木 洋子，坂東 宜昭，金崎 朝子.
    科学館での自律移動ロボット実証実験 ～ロボットは人混みで音を聞き分けられるか!?～
    第52回人工知能学会 AI チャレンジ研究会, 2018.

  13. 渋谷 薫, 金崎 朝子, 大西 正輝.
    深層学習による画像識別問題に帰着した人の流れのシミュレーション
    Meeting on Image Recognition and Understandings (MIRU), 2018.

  14. 金崎 朝子, 松下 康之, 西田 佳史.
    視点教示なし多視点画像深層学習による物体のカテゴリ・姿勢同時推定
    第24回 画像センシングシンポジウム (SSII), 2018.

  15. 藤橋 一輝, 木村 雅之, 金崎 朝子, 小澤 順.
    半教師あり学習による商品画像中の個数と位置の同時推定
    第32回 人工知能学会全国大会 (JSAI), 2018.

  16. 鈴木 亮太, QIU YUE, 金崎 朝子, 岩田 健司, 佐藤 雄隆.
    物体認識技術を活用したインタラクティブVR空間の構成
    第23回 画像センシングシンポジウム (SSII), 2017.

  17. 西田 佳史, 北村 光司, 佐々木 洋子, 金崎 朝子, Shi Boxin, 大野 美喜子, 楠本 欣司.
    繋げる人工知能 ：生活機能レジリエント社会のための スマートリビングネットを用いた生活知能研究
    第17回 SICEシステムインテグレーション部門講演会, 2016.

  18. 金崎 朝子.
    三次元情報を活用した物体検出の三手法
    Vision Enginieering Workshop (ViEW), OS5-01, pp.284-287, 2015.

  19. 金崎 朝子, Emanuele Rodolà, 原田 達也.
    グラフマッチング学習を用いたRGB-D画像からの物体検出
    第20回 ロボティクスシンポジア, pp.432-437, 2015.

  20. 金崎 朝子, Emanuele Rodolà, Daniel Cremers, 原田 達也.
    対応点集合類似度学習を用いた剛体・非剛体物体検出
    Pattern Recognition and Media Understanding (PRMU), pp.13-18, 2014.

  21. 金崎 朝子, Emanuele Rodolà, 原田 達也.
    RGB-D画像からの物体検出における対応点集合類似度の学習
    the 32th Annual Conference of the Robotics Society of Japan (RSJ), 3I2-03, 2014.
    2015 研究奨励賞．第30回 日本ロボット学会 学術講演会（RSJ）

  22. 金崎 朝子, 稲葉 翔, 牛久 祥孝, 山下 裕也, 村岡 宏是, 原田 達也, 國吉 康夫.
    大規模画像データセットを用いたマルチクラス物体検出器の同時学習 〜物体毎に特化した負例クラスの導入〜
    Pattern Recognition and Media Understanding (PRMU), pp.105-112, 2012.
    2012 研究奨励賞. 電子情報通信学会パターン認識・マルチメディア理解研究会 (PRMU)

  23. 金崎 朝子, 原田 達也, 國吉 康夫.
    多種類の三次元特徴量を用いた物体セグメンテーションの弱教師付き学習
    Meeting on Image Recognition and Understandings (MIRU), OS14-03, 2012.

  24. 稲葉 翔, 村岡 宏是, 山下 裕也, 牛久 祥孝, 金崎 朝子, 原田 達也, 國吉 康夫.
    学習時間に着目した効率的な大規模画像分類
    Meeting on Image Recognition and Understandings (MIRU), OS6-03, 2012.

  25. 金崎 朝子, 原田 達也, 國吉 康夫.
    カラー三次元積分特徴と線形部分空間法による実世界からの高速物体検出
    Meeting on Image Recognition and Understandings (MIRU), IS1-59, pp.448-455, 2010.

  26. 金崎 朝子, 原田 達也, 國吉 康夫.
    積分特徴と部分空間法を用いた高速三次元物体認識の実データへの適用
    Pattern Recognition and Media Understanding (PRMU), pp.207-212, 2009.

  27. 金崎 朝子, 中山 英樹, 原田 達也, 國吉 康夫.
    部分空間法とカラー立体高次局所自己相関特徴を用いた高速三次元物体認識
    Meeting on Image Recognition and Understandings (MIRU), OS4-3:103-OS4-3:110, 2009.

  28. 金崎 朝子, 原田 達也, 國吉 康夫.
    三次元環境地図からの物体探索タスク応用を目指したカラー立体高次局所自己相関特徴の開発
    the 26th Annual Conference of the Robotics Society of Japan (RSJ), 1L3-06, 2008.