Apps
Games
Notes
Blog
About

Nao Nakagawa

作成者: Nao Nakagawa
公開: 2023/2/5
更新: 2024/11/11

    I am a software engineer with experience in both theoretical and applied machine learning research during my postgraduate studies. During my Master's degree, I studied representation learning and generative models, such as variational autoencoders (VAEs), and focused on the formulation of generative models to obtain concise and meaningful representations that helps our comprehension of big data. Our papers are published on several venues (ICIP, ICLR etc).

    Papers & Publications

    Journal papers (peer-reviewed)

    ConcVAE: Conceptual Representation Learning
    Ren Togo, Nao Nakagawa, Takahiro Ogawa, Miki Haseyama
    IEEE TNNLS (early access) (IF: 10.4) code & project page
    Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior
    Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama
    IEEE Access (IF: 3.367) (2022 IEEE Sapporo Section Encouragement Award)

    Conferences (peer-reviewed)

    Gromov-Wasserstein Autoencoders
    Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama
    ICLR 2023 arXiv code & project page featured at 机器之心 (zh)
    自然言語における恣意性を用いた潜在変数モデルに基づく概念表現学習
    中川 真, 藤後 廉, 小川 貴弘, 長谷山 美紀
    MIRU 2022 (accepted as a short oral presentation)
    Interpretable Representation Learning on Natural Image Datasets via Reconstruction in Visual-Semantic Embedding Space
    Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama
    ICIP 2021 poster & video
    Face Synthesis via User Manipulation of Disentangled Latent Representation
    Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama
    GCCE 2020 (Excellent Demo! Award Gold Prize)

    Workshop papers (unreviewed)

    Exponential Dissimilarity-Dispersion Family for VAE-based Domain-Specific Representation Learning
    Ren Togo, Nao Nakagawa, Takahiro Ogawa, Miki Haseyama
    MIRU 2024 (poster presentation)
    A Note on Disentanglement Using Deep Generative Model Based on Variational Autoencoder
    —Introduction of Regularization Losses Based on Metrics of Disentangled Representation—
    Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama
    ITE-ME 2021
    学習済みセマンティックセグメンテーションモデルを用いたdisentanglementに関する検討
    中川 真, 藤後 廉, 小川 貴弘, 長谷山 美紀
    令和2年度 電気・情報関係学会北海道支部連合大会

    Education

    Hokkaido University, Japan
    Master of Information Science and Technology
    Apr. 2021 – Mar. 2023
    Hokkaido University, Japan
    Bachelor of Engineering
    Apr. 2017 – Mar. 2021

    Experience

    Software Engineer
    Apr. 2023 – present
    Web Application Engineer (part time)
    Laboratory of Media Dynamics, Hokkaido University
    興味・関心・嗜好・知識・経験等の非言語情報を理解するAI
    Oct. 2021 – Oct. 2022
    Teaching Assistant (part time)
    Hokkaido University
    The courses of メディアネットワーク実験IA and メディアネットワーク実験IIA
    Apr. 2021 – Mar. 2023
    Software Engineer, Data Analyst (part time)
    Hitachi Hokudai Lab., Hitachi, Ltd.
    Hitachi Hokudai Lab. & Hokkaido University Contest 2020
    Jul. 2020 – Dec. 2020