Cognitive Robotics & AI LaboratoryGraduate School of Information Sciences, Tohoku University
JPEN
HomeResearch

COGNITIVE ROBOTICS & AI LABORATORY

Research.

01 / RESEARCH FIELDS

Research

  • 01Computer vision
  • 02Robotics
  • 03Machine learning
  • 043D data recognition

02 / PRESENTATION MATERIAL

Presentation Material

  1. Feb. 2021 Information session, School of Computing, Tokyo Institute of Technology "Introductoin of Kanezaki Laboratory"
  2. Apr. 2020 Information session, School of Computing, Tokyo Institute of Technology "Introductoin of Kanezaki Laboratory"

03 / JOURNAL PUBLICATIONS

Journal Publications

  1. Kento Kawaharazuka, Shunki Itadera, Kohei Honda, Takato Horii, Asako Kanezaki, Taisuke Kobayashi, Kenji Koide, Shuhei Kurita, Koshi Makihara, Kazuki Miyazawa, Masaki Murooka, Yuki Onishi, Satoshi Yagi, and Satoshi Yamamori.

    From Instruction to Inheritance: Scaling Robot Learning Through Knowledge Circulation.

    Advanced Intelligent Systems, accepted, 2026.
    Paper

  2. Kohei Matsumoto and Asako Kanezaki.

    EED: Embodied Environment Description through Robotic Visual Exploration.

    IEEE Robotics and Automation Letters (RA-L), 2026.
    Dataset

  3. Kei Ota, Devesh K. Jha, and Asako Kanezaki.

    A Framework for Training Larger Networks for Deep Reinforcement Learning.

    Machine Learning, Springer, 2024.
    https://doi.org/10.1007/s10994-024-06547-6

  4. Yuzhe Hao, Asako Kanezaki, Ikuro Sato, Rei Kawakami, and Koichi Shinoda.

    Egocentric Human Activities Recognition with Multi-modal Interaction Sensing.

    IEEE Sensors, 2024.

  5. Haruyuki Nakagawa and Asako Kanezaki.

    Multi-Agent Visual Coordination using Optical Wireless Communication.

    IEEE Robotics and Automation Letters (RA-L), 2023.
    https://doi.org/10.1109/LRA.2023.3304905
View all+8

  1. 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

  2. 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

  3. Wonjik Kim*, Asako Kanezaki*, and Masayuki Tanaka.

    Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering.

    IEEE Transactions on Image Processing, 2020.
    *equal contributions
    IEEE Signal Processing Society (SPS) Japan Student Journal Paper Award
    Telecom Technology Student Award
    Project

  4. 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

  5. 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

  6. 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

  7. 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

  8. 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

04 / INTERNATIONAL CONFERENCES

International Conferences

  1. Kaname Kitamura and Asako Kanezaki.

    Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images.

    Asian Conference on Computer Vision (ACCV), accepted, 2026.
    Paper

  2. Haru Kondoh, Kei Ota, Asako Kanezaki, and Yueh-Hua Wu.

    CounterAlign: Counterfactual Supervision for Vision-Language-Action Models.

    The Conference on Robot Learning (CoRL), accepted, 2026.
    Paper

  3. Yuchen Che, Jingtu Wu, Hao Zheng, and Asako Kanezaki.

    COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation.

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2026.
    PaperCode

  4. Masaru Yajima, Yuma Shin, Rei Kawakami, Asako Kanezaki, and Kei Ota.

    Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole.

    IEEE International Conference on Robotics and Automation (ICRA), accepted, 2026.

  5. Haru Kondoh and Asako Kanezaki.

    Embodied Navigation with Auxiliary Task of Action Description Prediction.

    IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
    PaperCode

  6. Masaru Yajima, Kei Ota, Asako Kanezaki, and Rei Kawakami.

    Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models.

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
    Paper
View all+42

  1. Kuanting Wu, Kei Ota, and Asako Kanezaki.

    FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models.

    The 19th International Conference on Machine Vision Applications (MVA), 2025.
    Paper

  2. Jiawei Jiang, Kei Ota, Devesh K. Jha, and Asako Kanezaki.

    Modality Selection and Skill Segmentation via Cross-Modality Attention.

    The 19th International Conference on Machine Vision Applications (MVA), 2025.
    Paper

  3. Kohei Matsumoto and Asako Kanezaki.

    EED: Embodied Environment Description through Robotic Visual Exploration.

    The 6th Embodied AI workshop at CVPR, 2025.
    Dataset

  4. Yuchen Che, Ryo Furukawa, and Asako Kanezaki.

    OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation.

    The 18th European Conference on Computer Vision (ECCV), (oral), 2024.
    PaperCode

  5. Yunyi Guan and Asako Kanezaki.

    Active Object Recognition with Trained Multi-view Based 3D Object Recognition Network.

    2nd IEEE International Conference on Robotics and Automation (ICRA) Workshop on Mobile Manipulation and Embodied Intelligence, 2024.
    Paper

  6. Carlos Gutierrez-Alvarez, Rafael Flor-Rodr&iacuteguez-Rabad&aacuten, Asako Kanezaki, and Roberto Javier L&oacutepez-Sastre.

    OffNav: Offline Reinforcement Learning for Visual Semantic Navigation.

    IEEE International Conference on Robotics and Automation (ICRA) Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots, 2024.
    Paper

  7. 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), 2024.
    Paper

  8. 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), 2024.
    Paper

  9. Haru Kondoh and Asako Kanezaki.

    Multi-goal Audio-visual Navigation using Sound Direction Map.

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
    Paper

  10. 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), 2023.
    PaperDataset

  11. 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), 2023.
    Dataset

  12. 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), 2023.
    PaperCode

  13. 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), 2023.
    Paper

  14. 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), 2023.

  15. 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), 2022.
    PaperCode

  16. 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), 2022.
    PaperCode

  17. Takashi Konno, Ayako Amma, and Asako Kanezaki.

    Incremental Multi-view Object Detection from a Moving Camera.

    ACM Multimedia Asia (ACMMMA), 2020.
    Project

  18. 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), 2020.
    PDFYouTube

  19. 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), 2020.
    PDF

  20. 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.

  21. 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

  22. 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

  23. Asako Kanezaki.

    Unsupervised Image Segmentation by Backpropagation.

    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1543-1547, 2018.
    Project

  24. 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.

  25. 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

  26. 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

  27. 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

  28. Tomoaki Saito, Asako Kanezaki, and Tatsuya Harada.

    IBC127: Video Dataset for Fine-grained Bird Classification.

    IEEE International Conference on Multimedia & Expo (ICME), 2016.
    Dataset

  29. 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

  30. 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.

  31. 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.
    PDFcode

  32. 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

  33. 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.

  34. 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.

  35. 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

  36. 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

  37. 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.
    PDFDataset

  38. 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

  39. 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

  40. 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

  41. 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

  42. 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.