Hinako Mitsuoka

Curriculum Vitae — Last updated: September 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, at the intersection of semantic segmentation and action recognition, with a focus on lightweight approaches that improve existing methods.

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 Workshop on Skilled Activity Understanding, Assessment and Feedback Generation (SAUAFG2026), June 2026 (Oral).
  3. Hinako Mitsuoka and Kazuhiro Hotta, "Hazard-Aware Duration Prior and F1-Adaptive Loss for Temporal Action Segmentation", International Conference on Computer Vision Theory and Applications (VISAPP2026), March 2026 (Oral).
  4. Hinako Mitsuoka and Kazuhiro Hotta, "Accuracy Improvement of Cell Image Segmentation Using Feedback Former", ECCV Workshop on Human-inspired Computer Vision (HCV2024), October 2024 (Poster).
  5. Sota Kato, Hinako Mitsuoka and Kazuhiro Hotta, "Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes", ECCV Workshop on Computational Aspects of Deep Learning (CADL2024), October 2024 (Oral).

Awards & Honors

Fellowships & Scholarships

Academic Service

Skills

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

Memberships