Previous Next
Avatar

Tomoyuki Suzuki

Research Scientist (CV/ML)

at CyberAgent, Inc.

Tomoyuki Suzuki is a research scientist at CyberAgent, Inc. and a Ph.D student at Keio University. He engages himself in research on computer vision and machine learning. For details, please also refer to CV.

Interests

He is generally interested in computer vision and machine learning.
Especially, video understanding, image/video/multimodal representation learning and video decomposition.

Education

  Ph.D. student in Computer Science (2021.10 - present)
        Keio University, Aoki lab.
        Adviser：Prof. Yoshimitsu Aoki

  M.S. in Computer Science and Electronic Engineering (2017.4 - 2019.3)
        Keio University, Aoki lab.
        Adviser：Prof. Yoshimitsu Aoki

  B.S. in Electronics and Electrical Engineering (2013.4 - 2017.3)
        Keio University, Aoki lab.
        Adviser：Prof. Yoshimitsu Aoki

Experience


 
 
 
 
 

Research Scientist

CyberAgent, Inc.

Aug 2020 – Present
Working on CV/ML research at AI Lab
 
 
 
 
 

Research Engineer

DeNA Co., Ltd. → Mobility Technologies Co., Ltd.

Apr 2019 – Jul 2020
Worked on CV/ML R&D (transferred to Mobility Technologies, 2020.4 - )
 
 
 
 
 

Data Scientist (long-term internship)

Recruit Holdings Co., Ltd.

Nov 2017 – Mar 2018
Worked on development of text generation system in TOWN WORK
 
 
 
 
 

Data Scientist (short-term internship)

Recruit Holdings Co., Ltd.

Aug 2017 – Sep 2017
Worked on data analysis in じゃらん
 
 
 
 
 

Researcher (internship)

National Institute of Advanced Industrial Science and Technology (AIST)

May 2017 – Mar 2019
Researched on Video recognition and Visual representation learning.
Superviser: Ph.D. Hirokatsu Kataoka
 
 
 
 
 

Member of cvpaper.challenge

cvpaper.challenge

May 2017 – Mar 2019
Joined CVPR 2018 完全読破チャレンジ

Publications

International Conferences

  • Tomoyuki Suzuki*, Hirokatsu Kataoka*, Yoshimitsu Aoki, Yutaka Satoh, “Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB”, CVPR 2018. (Acceptance rate 29.6%) [Paper] [Poster]

  • Tomoyuki Suzuki, Takahiro Itazuri, Kensho Hara, Hirokatsu Kataoka, “Learning Spatiotemporal 3D Convolution with Video Order Self-Supervision”, IEEE ECCV Workshop on Person In Context, 2018. [Paper]

  • Tomoyuki Suzuki, Munetaka Minoguchi, Ryota Suzuki, Akio Nakamura, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, “Semantic Change Detection”, IEEE ICARCV, 2018.

  • Kaori Abe, Munetaka Minoguchi, Teppei Suzuki, Tomoyuki Suzuki, Naofumi Akimoto, Yue Qiu, Ryota Suzuki, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, “Fashion Culture Database: Construction of Database for World-wide Fashion Analysis”, IEEE ICARCV 2018.

Domestic Conferences

  • 鈴木 智之, 山口 光太, “広告画像表現の事前学習”, MIRU2022.
  • 鈴木 智之, 青木 義満, “重要パッチ選択に基づく効率的動画認識”, MIRU2022.
  • 鈴木 智之, 帯金 駿, 田中 希武, 青木 義満, “敵対的学習を用いた2次元姿勢推定における教師なしドメイン適応”, SSII2019.
  • 鈴木 智之, 田中 希武, 青木 義満, “敵対的学習を用いた2次元姿勢推定における教師なしドメイン適応”, ViEW2018 (Oral).
  • 美濃口 宗尊, 鈴木 智之, 岡山 健, 中村 明生, 佐藤 雄隆, 片岡 裕雄, “大規模ファッションデータベースによる人物検出”, ViEW2018.
  • Tomoyuki Suzuki, Kensho Hara, Takahiro Itazuri, Hirokatsu Kataoka, “Self-supervised Learning for Spatiotemporal 3DCNN Towards Effective Motion Feature”, MIRU2018.
  • Tomoyuki Suzuki*, Hirokatsu Kataoka*, Yoshimitsu Aoki, Yutaka Satoh, “Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB”, MIRU2018 (Invited talk).
  • 阿部 香織, 鈴木 哲平, 鈴木 智之, 美濃口 宗尊, 中村 明生, 佐藤 雄隆, 片岡 裕雄, “世界のファッショントレンドを解析するデータベース”, SSII2018.
  • 鈴木 智之, 片岡 裕雄, “危険予測のための大規模車載ニアミスDB構築と擬似再帰ニューラルネット”, ViEW2017 (Oral).
  • 鈴木 哲平, 阿部 香織, 鈴木 智之, 鈴木 亮太, 片岡 裕雄, “弱教師付き学習による都市の文化性抽出”, ViEW2017 (Oral).
  • 鈴木 智之, 青木 義満, “行動遷移映像における姿勢特徴を中心とする学習を用いた時系列行動認識”, SSII2017.
  • 鈴木 智之, 青木 義満, “行動遷移映像における姿勢特徴を中心とする学習を用いた時系列行動認識”, DIA2017 (Oral).

Journals

  • Tomoyuki Suzuki, Yoshimitsu Aoki, “Efficient Transformer-Based Compressed Video Modeling via Informative Patch Selection”, Sensors, 23 (1), 2022. [Link]
  • 鈴木 智之, 青木 義満, “行動遷移映像における姿勢特徴を中心とする学習を用いた時系列行動認識”, 精密工学会誌, Vol.83, No.12, pp.1156-1165, 2017. [Link]

Articles

Talks

Slides


Competitions

Kaggle

id: tomoyukun (Kaggle Expert)

Others

Contact