World's Best Scientists 2026 revealed!
Liang-Chieh Chen

Liang-Chieh Chen

D-Index & Metrics

Computer Science

D-Index
42
Citations
97571
World Ranking
8127
National Ranking
1071

Overview

Liang-Chieh Chen is affiliated with ByteDance in China and has a substantial publication record primarily focused on computer science. Their research is concentrated in the subfields of Computer Vision and Pattern Recognition, Artificial Intelligence, Electrical and Electronic Engineering, Radiology, Nuclear Medicine and Imaging, and Biomedical Engineering.

The scientist has published extensively, with frequent contributions to venues such as arXiv (Cornell University), where they have authored 31 papers. Additionally, they have published work in the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) and the International Journal of Computer Vision, as well as a contribution to TIB Data Manager.

Key research topics covered in their work include:

  • Advanced Neural Network Applications
  • Advanced Image and Video Retrieval Techniques
  • Domain Adaptation and Few-Shot Learning
  • Video Surveillance and Tracking Methods
  • Multimodal Machine Learning Applications
  • Visual Attention and Saliency Detection
  • Human Pose and Action Recognition

Recent publications by Liang-Chieh Chen include:

  • DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution, 2020, arXiv (Cornell University)
  • CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation, 2020, arXiv (Cornell University)
  • DeepLab2: A TensorFlow Library for Deep Labeling, 2021, arXiv (Cornell University)
  • MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers, 2024, TIB Data Manager

The scientist frequently collaborates with other researchers. Their most common co-authors are Qihang Yu, Hartwig Adam, Alan Yuille, Huiyu Wang, and Siyuan Qiao.

Best Publications

  • MobileNetV2: Inverted Residuals and Linear Bottlenecks

    Mark Sandler;Andrew Howard;Menglong Zhu;Andrey Zhmoginov

  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

    Liang-Chieh Chen;George Papandreou;Iasonas Kokkinos;Kevin Murphy

  • Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

    Liang-Chieh Chen;Yukun Zhu;George Papandreou;Florian Schroff

  • Rethinking Atrous Convolution for Semantic Image Segmentation

    Liang-Chieh Chen;George Papandreou;Florian Schroff;Hartwig Adam

  • Searching for MobileNetV3

    Andrew Howard;Ruoming Pang;Hartwig Adam;Quoc Le

  • Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

    Liang-Chieh Chen;George Papandreou;Iasonas Kokkinos;Kevin Murphy

  • Attention to Scale: Scale-Aware Semantic Image Segmentation

    Liang-Chieh Chen;Yi Yang;Jiang Wang;Wei Xu

  • Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

    George Papandreou;Liang-Chieh Chen;Kevin P. Murphy;Alan L. Yuille

  • Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

    Chenxi Liu;Liang-Chieh Chen;Florian Schroff;Hartwig Adam

  • DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

    Siyuan Qiao;Liang-Chieh Chen;Alan Yuille

  • Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation

    Andrew Howard;Andrey Zhmoginov;Liang-Chieh Chen;Mark Sandler

  • Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

    Huiyu Wang;Yukun Zhu;Bradley Green;Hartwig Adam

  • Searching for MobileNetV3.

    Andrew Howard;Mark Sandler;Grace Chu;Liang-Chieh Chen

  • Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

    Bowen Cheng;Maxwell D. Collins;Yukun Zhu;Ting Liu

  • PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

    George Papandreou;Tyler Zhu;Liang-Chieh Chen;Spyros Gidaris

  • MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers

    Huiyu Wang;Yukun Zhu;Hartwig Adam;Alan Yuille

  • Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

    George Papandreou;Liang-Chieh Chen;Kevin Murphy;Alan L. Yuille

  • FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation

    Paul Voigtlaender;Yuning Chai;Florian Schroff;Hartwig Adam

  • MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features

    Liang-Chieh Chen;Alexander Hermans;George Papandreou;Florian Schroff

  • Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform

    Liang-Chieh Chen;Jonathan T. Barron;George Papandreou;Kevin Murphy

Frequent Co-Authors

Hartwig Adam
Hartwig Adam Google (United States)
Alan L. Yuille
Alan L. Yuille Johns Hopkins University
Jonathon Shlens
Jonathon Shlens Google (United States)
Barret Zoph
Barret Zoph Google (United States)
Mark Sandler
Mark Sandler Google (United States)
Peng Wang
Peng Wang Baidu (China)
Jasper Uijlings
Jasper Uijlings Google (United States)
Ekin D. Cubuk
Ekin D. Cubuk Google (United States)
Bastian Leibe
Bastian Leibe RWTH Aachen University
Raquel Urtasun
Raquel Urtasun University of Toronto

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

If you’re considering studying Computer Science in the USA, a variety of online degrees and credentials can open doors to high-paying tech careers. Entry-level professionals often start with online associate degree programs. These programs cover computer fundamentals and can be completed quickly, providing a cost-effective pathway to the workforce or further study.

Another popular option is pursuing easy licenses and certifications to get. These certifications focus on practical, in-demand skills like cybersecurity, cloud computing, or programming, and can rapidly boost employability even for those who already have a degree.

For those looking to advance their expertise, the shortest master degree programs offer a way to quickly upskill and become competitive in a growing job market. Speed and flexibility are key, as these programs are designed for working professionals.

It’s also crucial to choose degrees that offer a strong return on investment. Focus on masters degrees that are worth it—such as those in artificial intelligence, data science, or information technology—to maximize your career potential.

Best Scientists Citing Liang-Chieh Chen

Trending Scientists