World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
30
Citations
122646
World Ranking
13793
National Ranking
5469

Overview

Tsung-Yi Lin is affiliated with Nvidia in the United States. Their research encompasses fields primarily within Computer Science and Engineering, with a substantial focus on Computer Vision and Pattern Recognition as well as Artificial Intelligence. Additional subfields include Computational Mechanics, Aerospace Engineering, and Geology.

The scientist's work covers a variety of topics including Advanced Neural Network Applications, Domain Adaptation and Few-Shot Learning, Multimodal Machine Learning Applications, Advanced Vision and Imaging, 3D Shape Modeling and Analysis, Robotics and Sensor-Based Localization, and Advanced Image and Video Retrieval Techniques.

Among their recent research outputs are:

  • RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection, 2024, published by Leibniz-Zentrum für Informatik (Schloss Dagstuhl)
  • Rethinking Pre-training and Self-training, 2020, published on arXiv (Cornell University)
  • iNeRF: Inverting Neural Radiance Fields for Pose Estimation, 2021, presented at the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • Open-vocabulary Object Detection via Vision and Language Knowledge Distillation, 2021, published on arXiv (Cornell University)
  • Revisiting ResNets: Improved Training and Scaling Strategies, 2021, appeared on arXiv (Cornell University)

Tsung-Yi Lin collaborates frequently with several researchers, including Anelia Angelova, Weicheng Kuo, Yin Cui, Golnaz Ghiasi, and Barret Zoph. These partnerships have contributed to multiple publications in leading venues.

Their work is published notably in arXiv (Cornell University), accounting for a significant number of contributions, alongside appearances in conferences such as the 2021 IEEE/CVF International Conference on Computer Vision (ICCV) and the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Other publication venues include Lecture Notes in Computer Science and IEEE Robotics and Automation Letters.

Best Publications

  • Microsoft COCO: Common Objects in Context

    Tsung-Yi Lin;Michael Maire;Serge J. Belongie;James Hays

  • Feature Pyramid Networks for Object Detection

    Tsung-Yi Lin;Piotr Dollar;Ross Girshick;Kaiming He

  • Focal Loss for Dense Object Detection

    Tsung-Yi Lin;Priya Goyal;Ross Girshick;Kaiming He

  • Focal Loss for Dense Object Detection

    Tsung-Yi Lin;Priya Goyal;Ross Girshick;Kaiming He

  • Microsoft COCO: Common Objects in Context

    Tsung-Yi Lin;Michael Maire;Serge Belongie;Lubomir Bourdev

  • Class-Balanced Loss Based on Effective Number of Samples

    Yin Cui;Menglin Jia;Tsung-Yi Lin;Yang Song

  • Microsoft COCO Captions: Data Collection and Evaluation Server

    Xinlei Chen;Hao Fang;Tsung-Yi Lin;Ramakrishna Vedantam

  • NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

    Golnaz Ghiasi;Tsung-Yi Lin;Quoc V. Le

  • Bottleneck Transformers for Visual Recognition

    Aravind Srinivas;Tsung-Yi Lin;Niki Parmar;Jonathon Shlens

  • Learning to Refine Object Segments

    Pedro Oliveira Pinheiro;Pedro Oliveira Pinheiro;Tsung-Yi Lin;Tsung-Yi Lin;Ronan Collobert;Piotr Dollár

  • Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

    Golnaz Ghiasi;Yin Cui;Aravind Srinivas;Rui Qian

  • DropBlock: A regularization method for convolutional networks

    Golnaz Ghiasi;Tsung-Yi Lin;Quoc V. Le

  • Collaborative Metric Learning

    Cheng-Kang Hsieh;Longqi Yang;Yin Cui;Tsung-Yi Lin

  • Learning Data Augmentation Strategies for Object Detection

    Barret Zoph;Ekin D. Cubuk;Golnaz Ghiasi;Tsung-Yi Lin

  • NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

    Golnaz Ghiasi;Tsung-Yi Lin;Ruoming Pang;Quoc V. Le

  • Learning deep representations for ground-to-aerial geolocalization

    Tsung-Yi Lin;Yin Cui;Serge Belongie;James Hays

  • Rethinking Pre-training and Self-training

    Barret Zoph;Golnaz Ghiasi;Tsung-Yi Lin;Yin Cui

  • iNeRF: Inverting Neural Radiance Fields for Pose Estimation

    Lin Yen-Chen;Pete Florence;Jonathan T. Barron;Alberto Rodriguez

  • Cross-View Image Geolocalization

    Tsung-Yi Lin;Serge Belongie;James Hays

  • Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

    Xiuye Gu;Tsung-Yi Lin;Weicheng Kuo;Yin Cui

  • Learning Deep Representations for Ground to Aerial Geolocalization (Open Access)

    Tsung-Yi Lin;Yin Cui;Serge Belongie;James Hays

Frequent Co-Authors

Barret Zoph
Barret Zoph Google (United States)
Serge Belongie
Serge Belongie University of Copenhagen
Piotr Dollar
Piotr Dollar Facebook (United States)
Ekin D. Cubuk
Ekin D. Cubuk Google (United States)
Anelia Angelova
Anelia Angelova Google (United States)
Jonathon Shlens
Jonathon Shlens Google (United States)
Ross Girshick
Ross Girshick Facebook (United States)
James Hays
James Hays Georgia Institute of Technology
Quoc V. Le
Quoc V. Le Google (United States)
Kaiming He
Kaiming He Facebook (United States)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Studying Computer Science in the USA opens the door to a variety of related online degrees and career paths. Many students choose to specialize further or boost their credentials with additional qualifications.

Those interested in data-driven careers may explore the cheapest data science degree programs, which offer budget-friendly opportunities to build in-demand analytical skills. For technology enthusiasts, the best online electrical engineering programs USA provide a practical route to careers in hardware, robotics, and innovation.

If fast career advancement is your goal, you may want to consider certifications that pay well, which can be completed quickly and boost your earning potential without a long-term commitment. Similarly, the shortest masters degree programs empower professionals to earn a graduate credential in less time, making them an efficient way to stand out in the job market.

Exploring these options can help you create a flexible and future-proof career pathway in technology.

Best Scientists Citing Tsung-Yi Lin

Trending Scientists

Recently Published Articles