Qing YU

Research Scientist

About Me

Hi, my name is Qing YU. I am currently a research scientist at LY Corp. and a project researcher with The University of Tokyo, Japan. I am a member of Virtual Human Lab at LY Corp. I am also a member of Aizawa Labratory and working with Prof. Kiyoharu Aizawa. My research interest is in Computer Vision, including Image Recognition, Open-set Recognition and Classifier Adaption. I was a recipient of Research Fellowships for Young Scientists (DC1) (2020-2023) and I was a recipient of The University of Tokyo Fellowship (2018-2020). I am most skilled in: Python and PyTorch. Full CV is here.

Publications

Preprints

  • Qing Yu, Go Irie and Kiyoharu Aizawa
    Open-Set Domain Adaptation with Visual-Language Foundation Models
    arXiv, 2023.
    [Paper]

  • Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa
    Zero-Shot In-Distribution Detection in Multi-Object Settings Using Vision-Language Foundation Models
    arXiv, 2023.
    [Paper] [Code]

International Conferences

  • Kent Fujiwara, Mikihiro Tanaka and Qing Yu
    Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models
    European Conference on Computer Vision (ECCV), 2024.
    [Website] [Paper]

  • Qing Yu, Mikihiro Tanaka and Kent Fujiwara
    Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    [Website] [Paper] [Code]

  • Atsuyuki Miyai, Qing Yu, Go Irie and Kiyoharu Aizawa
    LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning
    Neural Information Processing Systems (NeurIPS), 2023.
    [Paper] [Code]

  • Jiafeng Mao, Qing Yu, Go Irie and Kiyoharu Aizawa
    Noise-Avoidance Sampling for Annotation Missing Object Detection
    IEEE International Conference on Image Processing (ICIP), 2023.
    [Paper]

  • Qing Yu and Kent Fujiwara
    Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Action Recognition
    AAAI Conference on Artificial Intelligence (AAAI), 2023.
    [Paper] [Code]

  • Atsuyuki Miyai, Qing Yu, Daiki Ikami, Go Irie and Kiyoharu Aizawa
    Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
    Winter Conference on Applications of Computer Vision (WACV), 2023.
    [Paper] [Code]

  • Qing Yu, Daiki Ikami, Go Irie and Kiyoharu Aizawa
    Self-Labeling Framework for Novel Category Discovery over Domains
    AAAI Conference on Artificial Intelligence (AAAI), 2022.
    [Paper] [Code]

  • Jiafeng Mao, Qing Yu, Yoko Yamakata and Kiyoharu Aizawa
    Noisy Annotation Refinement for Object Detection
    British Machine Vision Conference (BMVC), 2021.
    [Paper]

  • Qing Yu, Atsushi Hashimoto and Yoshitaka Ushiku
    Divergence Optimization for Noisy Universal Domain Adaptation
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [Paper] [Code]

  • Qing Yu, Daiki Ikami, Go Irie and Kiyoharu Aizawa
    Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
    European Conference on Computer Vision (ECCV), 2020.
    [Paper] [Code]

  • Qing Yu and Kiyoharu Aizawa
    Unknown Class Label Cleaning for Learning with Open-Set Noisy Labels
    IEEE International Conference on Image Processing (ICIP), 2020.
    [Paper] [Code]

  • Jiafeng Mao, Qing Yu and Kiyoharu Aizawa
    Noisy Localization Annotation Refinement For Object Detection
    IEEE International Conference on Image Processing (ICIP), 2020.
    [Paper]

  • Takumi Kawashima, Qing Yu, Akari Asai, Daiki Ikami and Kiyoharu Aizawa
    The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals
    International Conference on Pattern Recognition (ICPR), 2020.
    [Paper]

  • Qing Yu and Kiyoharu Aizawa
    Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy
    IEEE International Conference on Computer Vision (ICCV), 2019.
    [Paper] [Code]

  • Qing Yu, Masashi Anzawa, Sosuke Amano, Makoto Ogawa and Kiyoharu Aizawa
    Food Image Recognition by Personalized Classifier
    IEEE International Conference on Image Processing (ICIP), 2018.
    [Paper]

Journal

  • Qing Yu, Go Irie and Kiyoharu Aizawa
    Self-Labeling Framework for Open-Set Domain Adaptation with Few Labeled Samples
    IEEE Transactions on Multimedia, 2023.
    [Paper]

  • Jiafeng Mao, Qing Yu and Kiyoharu Aizawa
    Noisy Localization Annotation Refinement for Object Detection
    IEICE TRANS INF SYST, 2021.

  • Qing Yu, Masashi Anzawa, Sosuke Amano and Kiyoharu Aizawa
    Personalized Food Image Classifier Considering Time-Dependent and Item-Dependent Food Distribution
    IEICE TRANS INF SYST, 2019.

Domestic
Conferences

  • Fourteen Papers

Experience

LY Corp.

Research Scientist

October 2023 - Current

Worked on Motion Recognition and Generation with Virtual Human Lab.

LINE

Research Scientist

April 2023 - September 2023

Worked on Motion Recognition and Generation with Virtual Human Lab.

LINE

Research Intern

December 2021 - May 2022

Worked on Motion Recognition with CV Lab.

OMRON SINIC X

Research Intern

July 2019 - December 2019, August 2020 - September 2021

Worked on Domain Adaptation.

Learn.AI

Teaching Assistant

April 2018 - March 2020

An open course at UTokyo which offers the basics of CS and AI including deep learning.

pluszero Inc.

Software Engineer

May 2016 - March 2023

Deep Learning application development.

Microsoft Development

Software Engineer Intern

August 2018 - September 2018

Worked with Rinna Team.

Awards

Kaggle Master

SIGNATE Grandmaster

MIRU Best Student Paper

July 2022

MIRU Best Student Paper

August 2019

Data Science Challenge by FUJIFILM AI Academy Brain(s) Champion

July 2019

An OCR competition.
Prize: X Series FUJIFILM X100F
[Detail]

The 1st Tellus Satellite Challenge Champion

December 2018

A landslide detection competition.
Prize: 1,000,000 JPY
[Detail]

AIST Satellite Image Analysis Contest Champion

April 2018

A golf course detection competition.
Prize: 300,000 JPY
[Detail] / [Slide]

JSAI Cup 2018 Champion

March 2018

A food ingredient image classification competition.
Prize: 500,000 JPY
[Detail] / [Slide]

Education

The University of Tokyo

PhD, Graduate School of Information Science and Technology

April 2020 - March 2023

The University of Tokyo

Master, Graduate School of Interdisciplinary Information Studies

April 2018 - March 2020

The University of Tokyo

Bachelor, Department of Information and Communication

April 2014 - March 2018

Gyosei International High School (Chiba, Japan)

October 2011 - March 2014

High School Affiliated to Fudan University (Shanghai, China)

September 2010 - October 2011

A Little More About Me

Alongside my research interests, some of my other interests and hobbies are:

  • Animation
  • Diving
  • Basketball
  • Movie
  • Dota2