Hinako Mitsuoka

Curriculum Vitae — Last updated: August 2026

Graduate School of Science and Engineering, Meijo University
1-501 Shiogamaguchi, Tempaku-ku, Nagoya, Aichi 468-8502, Japan

Email: 263441509@ccmailg.meijo-u.ac.jp / ppppeach.jam@gmail.com
Web: ppppeach-jam.github.io · Google Scholar · GitHub · researchmap

Research Interests

Computer vision — semantic segmentation of biomedical images, temporal action segmentation, and efficient adaptation of vision foundation models.

Education

Professional Experience

Publications

Journal Articles

  1. Hinako Mitsuoka and Kazuhiro Hotta, "Human Brain-Inspired Network Using Transformer and Feedback Processing for Cell Image Segmentation", IEEE Access, 13, pp.50918-50930, 2025.

International Conferences (Refereed)

  1. Hinako Mitsuoka and Kazuhiro Hotta, "Prompt-Free and Efficient SAM2 Adaptation for Biomedical Semantic Segmentation via Dual Adapters", IEEE International Conference on Image Processing (ICIP2026), September 2026 (Poster).
  2. Hinako Mitsuoka and Kazuhiro Hotta, "Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation", CVPR 2026 Workshop (SAUAFG), June 2026 (Oral).
  3. Hinako Mitsuoka and Kazuhiro Hotta, "Hazard-Aware Duration Prior and F1-Adaptive Loss for Temporal Action Segmentation", VISAPP 2026, March 2026 (Oral).
  4. Hinako Mitsuoka and Kazuhiro Hotta, "Accuracy Improvement of Cell Image Segmentation Using Feedback Former", ECCV 2024 Workshop (HCV), October 2024 (Poster).
  5. Sota Kato, Hinako Mitsuoka and Kazuhiro Hotta, "Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes", ECCV 2024 Workshop (CADL), October 2024 (Oral).

Domestic Conferences

17 presentations at domestic conferences and symposia, including MIRU, ViEW, IBIS, FIT and CVIM (see Publications for the full list).

Awards & Honors

Fellowships & Scholarships

Academic Service

Skills

Python, PyTorch, OpenCV, scikit-learn, C, MATLAB, Swift, Docker, Linux, LaTeX

Memberships