Research

  • Home
  • Publications
  • computer-vision

    • Publications

    Category

    Research Area

    Year

    • International Conferences
      computer-vision World Model 生成モデル

      Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

      [paper]

      Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta.

      Advances in Neural Information Processing Systems (NeurIPS 2025).

    • International Conferences
      computer-vision Representation Learning

      CityNav: A Large-Scale Dataset for Real-World Aerial Navigation

      [paper]

      Jungdae Lee*, Taiki Miyanishi*, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, Nakamasa Inoue (* denotes equally contributed)

      International Conference on Computer Vision (ICCV 2025)

    • International Conferences
      computer-vision

      GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

      [paper]

      Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Masato Taki, Yutaka Matsuo

      International Conference on Computer Vision (ICCV 2025)

    • Awards
      AI Application computer-vision

      2024 Research Report Ubiquitous Computing Systems, Best Paper Award (UBI): Proposal of Knowledge Distillation Method from Vision Transformer to Convolutional Neural Network

      前羽 利治，河野 慎，松尾 豊

    • International Conferences
      Computer Vision computer-vision

      Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model

      [paper] [web]

      Xin Zhang*, Jiaxian Guo*, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa

      2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

    • Journals
      computer-vision Representation Learning 理論

      HAWK-Net: Hierarchical Attention Weighted Top-K Network for Megapixel Image Classification

      Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matsuo

      IPSJ, (2023).

    • Journals
      computer-vision

      Proposal of a DeepFake Video Detection Method Using Face Angle Information

      蔭山智, 鈴木雅大, 落合桂一, 松尾豊

      電子情報通信学会和文論文誌D, (2023).

    • Journals
      computer-vision

      Robustifying Vision Transformer Without Retraining From Scratch Using Attention Based Test-Time Adaptation

      Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      New Generation Computing, (2022).[paper]

    • Journals
      computer-vision Representation Learning

      Fixing the train-test objective discrepancy: Iterative Image Inpainting for Unsupervised Anomaly Detection

      Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matuo.

      J-Stage in August Vol.30, (2022).

    • Awards
      computer-vision LLM / NLP

      25th Symposium on Image Recognition and Understanding (MIRU2022) MIRU Excellence Award: Pixel vs. Object: A Study on Optimal Image Representation in Change Capture

      土居健人, 濱口竜平, 岩澤有祐, 大西正輝, 松尾豊, 櫻田健,