World's Best Scientists 2026 revealed!
Award Badge
Computer Science
China
2026

D-Index & Metrics

Computer Science

D-Index
91
Citations
40853
World Ranking
573
National Ranking
80

Research.com Recognitions

  • 2026 - Research.com Computer Science in China Leader Award
  • 2025 - Research.com Computer Science in China Leader Award

Overview

Hongsheng Li is affiliated with the Chinese University of Hong Kong in China. Their research primarily spans computer science, with a focus on computer vision and pattern recognition, and artificial intelligence. Their work also covers aerospace engineering, computational mechanics, and radiology, nuclear medicine, and imaging.

The scientist's recent publications include:

  • From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network (2020, IEEE Transactions on Pattern Analysis and Machine Intelligence)
  • CLIP-Adapter: Better Vision-Language Models with Feature Adapters (2023, International Journal of Computer Vision)
  • UniFormer: Unifying Convolution and Self-Attention for Visual Recognition (2023, IEEE Transactions on Pattern Analysis and Machine Intelligence)
  • PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection (2022, International Journal of Computer Vision)
  • Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (2020, arXiv (Cornell University))

Frequent co-authors in their research include Xiaogang Wang, Yu Qiao, Jifeng Dai, Guanglu Song, and Aojun Zhou.

Hongsheng Li has published extensively in several venues, notably:

  • arXiv (Cornell University)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • International Journal of Computer Vision

The scientist's research interests focus on the following topics:

  • Advanced Neural Network Applications
  • Multimodal Machine Learning Applications
  • Domain Adaptation and Few-Shot Learning
  • Advanced Image and Video Retrieval Techniques
  • Human Pose and Action Recognition
  • Advanced Vision and Imaging
  • Robotics and Sensor-Based Localization

Best Publications

  • PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud

    Shaoshuai Shi;Xiaogang Wang;Hongsheng Li

  • StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

    Han Zhang;Tao Xu;Hongsheng Li

  • PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

    Shaoshuai Shi;Chaoxu Guo;Li Jiang;Zhe Wang

  • StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

    Han Zhang;Tao Xu;Hongsheng Li;Shaoting Zhang

  • Cross-scene crowd counting via deep convolutional neural networks

    Cong Zhang;Hongsheng Li;Xiaogang Wang;Xiaokang Yang

  • StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

    Han Zhang;Tao Xu;Hongsheng Li;Shaoting Zhang

  • Saliency detection by multi-context deep learning

    Rui Zhao;Wanli Ouyang;Hongsheng Li;Xiaogang Wang

  • Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

    Tong Xiao;Hongsheng Li;Wanli Ouyang;Xiaogang Wang

  • InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

    Unknown

  • From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network

    Shaoshuai Shi;Zhe Wang;Jianping Shi;Xiaogang Wang

  • Group-Wise Correlation Stereo Network

    Xiaoyang Guo;Kai Yang;Wukui Yang;Xiaogang Wang

  • T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos

    Kai Kang;Hongsheng Li;Junjie Yan;Xingyu Zeng

  • Learning Feature Pyramids for Human Pose Estimation

    Wei Yang;Shuang Li;Wanli Ouyang;Hongsheng Li

  • DeepID-Net: Deformable deep convolutional neural networks for object detection

    Wanli Ouyang;Xiaogang Wang;Xingyu Zeng;Shi Qiu

  • Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

    Xinge Zhu;Hui Zhou;Tai Wang;Fangzhou Hong

  • Object Detection from Video Tubelets with Convolutional Neural Networks

    Kai Kang;Wanli Ouyang;Hongsheng Li;Xiaogang Wang

  • Person Search with Natural Language Description

    Shuang Li;Tong Xiao;Hongsheng Li;Bolei Zhou

  • 3D Human Pose Estimation in the Wild by Adversarial Learning

    Wei Yang;Wanli Ouyang;Xiaolong Wang;Jimmy Ren

  • Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification

    Feng Zhu;Hongsheng Li;Wanli Ouyang;Nenghai Yu

  • Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

    Yixiao Ge;Dapeng Chen;Hongsheng Li

  • Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism

    Qi Chu;Wanli Ouyang;Hongsheng Li;Xiaogang Wang

  • Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification

    Zhongdao Wang;Luming Tang;Xihui Liu;Zhuliang Yao

Frequent Co-Authors

Xiaogang Wang
Xiaogang Wang Chinese University of Hong Kong
Wanli Ouyang
Wanli Ouyang Shanghai AI Lab
Xiaolei Huang
Xiaolei Huang Pennsylvania State University
Jianping Shi
Jianping Shi SenseTime
Junjie Yan
Junjie Yan SenseTime
Shaoting Zhang
Shaoting Zhang University of Electronic Science and Technology of China
Dimitris N. Metaxas
Dimitris N. Metaxas Rutgers, The State University of New Jersey
Junzhou Huang
Junzhou Huang The University of Texas at Arlington
Yu Qiao
Yu Qiao Chinese Academy of Sciences
Jian Cheng
Jian Cheng Chinese Academy of Sciences

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

As the demand for technology skills continues to grow, there are many flexible online study options and career pathways for those interested in computer science and related fields. Pursuing an online master’s in electrical engineering degree can be an excellent way to broaden your expertise, especially if you’re interested in hardware, robotics, or advanced system design.

Short on time? You might consider the shortest online masters degree programs, which allow you to earn a graduate credential in as little as one year. Additionally, there are easy certifications to get online that provide valuable skills and can boost your employability in specialized tech roles or adjacent industries.

To maximize your career potential, it’s also smart to explore the most useful graduate degrees that are currently in high demand. Whether you opt for a full degree, a fast-track program, or a targeted certification, online learning offers the flexibility to advance your tech career on your terms.

Best Scientists Citing Hongsheng Li

Trending Scientists