Publications

132 Total

Top-Rank= indicates top-ranked conference/journal in Google Scholar Metrics.
  • Erika Mori, Yue Qiu, Hirokatsu Kataoka, Yoshimitsu Aoki, “A Comprehensive Analysis of a Social Intelligence Dataset and Response Tendencies Between Large Language Models (LLMs) and Humans,” Sensors Journal, 2025.

  • Selected Papers

    YUTO SHIBATA, Keitaro Tanaka, Yoshiaki Bando, Keisuke Imoto, Hirokatsu Kataoka, Yoshimitsu Aoki, “Formula-Supervised Sound Event Detection: Pre-Training Without Real Data,” ICASSP 2025.

  • Takumi Fukuzawa, Kensho Hara, Hirokatsu Kataoka, Toru Tamaki, “Can masking background and object reduce static bias for zero-shot action recognition?,” International Conference on MultiMedia Modeling (MMM), 2025.

  • Koshi Makihara, Yukiyasu Domae, Ryo Hanai, Ixchel G. Ramirez-Alpizar, Hirokatsu Kataoka, Kensuke Harada, “Deformability-Based Grasp Pose Detection From a Visible Image,” IEEE Access, 2024.

  • Shutaro Okada, Kenji Doi, Ryota Yoshihashi, Hirokatsu Kataoka, Tomohiro Tanaka, “Constant Rate Schedule: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models,” arXiv pre-print 2411.12188, 2024.

  • Top-Rank

    Kenji Doi, Shutaro Okada, Ryota Yoshihashi, Hirokatsu Kataoka, “Real-SRGD: Enhancing Real-World Image Super-Resolution with Classifier-Free Guided Diffusion,” Asian Conference on Computer Vision (ACCV), 2024.

  • Top-Rank

    Ryota Yoshihashi, Yuya Otsuka, Kenji Doi, Tomohiro Tanaka, Hirokatsu Kataoka, “Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation,” Asian Conference on Computer Vision (ACCV), 2024.

  • Top-Rank

    Ryosuke Yamada,Ryu Tadokoro,Yue Qiu,Hirokatsu Kataoka,Yutaka Satoh, “Masked Structural Point Cloud Modeling for Learning 3D Representation,” IEEE Access, 2024.

  • Top-Rank

    Fumiya Matsuzawa, Yue Qiu, Yanjun Sun, Kenji Iwata, Hirokatsu Kataoka, Yutaka Satoh, “Subtle-Diff: A Dataset for Precise Recognition of Subtle Differences among Visually Similar Objects,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.

  • Shinichi Mae, Ryosuke Yamada, Hirokatsu Kataoka, “Keeping Segment Mask Quality with Self-generated Masks,” ECCV 2024 Workshop on Darkside of GenAIs and Beyond, 2024.

  • Top-Rank

    Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka, Koshi Makihara, Nakamasa Inoue, Rio Yokota, Yutaka Satoh, “Formula-Supervised Visual-Geometric Pre-training,” European Conference on Computer Vision (ECCV), 2024.

  • Top-Rank

    Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki, “Rethinking Image Super Resolution from Training Data Perspectives,” European Conference on Computer Vision (ECCV), 2024.

  • Top-Rank

    Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, “Scaling Backwards: Minimal Synthetic Pretraining?,” European Conference on Computer Vision (ECCV), 2024.

  • Erika Mori, Yue Qiu, Hirokatsu Kataoka, Yoshimitsu Aoki, “Advancing AI’s Social Intelligence: Combining Commonsense Reasoning with Visual Perception,” ECCV 2024 WiCV Workshop.

  • Top-Rank

    Shun Iwase, Eisaku Maeda, Nakamasa Inoue, Hirokatsu Kataoka, Ryo Nakamura, Rio Yokota, Shuya Takahashi, “On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process,” ICPR 2024.

  • Top-Rank

    Ryosuke Yamada, Ryosuke Takahashi, Go Ohtani, Erika Mori, Hirokatsu Kataoka, Yoshimitsu Aoki, “Is ImageNet Pre-training Fiar in Image Recognition?,” CVPR Workshop on Responsible Data, 2024.

  • Top-Rank

    Ryo Hayamizu, Shota Nakamura, Sora Takashima, Hirokatsu Kataoka, Ikuro Sato, Nakamasa Inoue, Rio Yokota, “SIFTer: Self-improving Synthetic Datasets for Pre-training Classification Models,” CVPR Workshop on Synthetic Dataset for Computer Vision, 2024.

  • Top-Rank

    Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka, Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

  • Yuichi Iwasaki, Hiroko Arai, Akihiro Tamada, Hirokatsu Kataoka, “Japanese mayfly family classification with a vision transformer model”, EcoEvoRxiv, 2024.

  • Top-Rank

    Yanjun Sun, Yue Qiu, Yoshimitsu Aoki, Hirokatsu Kataoka, “Guided by the Way: The Role of On-the-route Objects and Scene Text in Enhancing Outdoor Navigation”, ICRA 2024.