Hongsheng Li

Chinese University of Hong Kong, University of Hong Kong, Xidian University, Wuhan University of Technology, Shanghai Artificial Intelligence Laboratory, ShangHai JiAi Genetics & IVF Institute, XLAB (Slovenia)

Papers

13

Total Citations

383

H-Index

9

About

No biography available yet.

Research Focus

Computer science13 · 383 citations
Artificial intelligence13 · 383 citations
Computer vision7 · 240 citations
Pattern recognition (psychology)3 · 130 citations
Human–computer interaction5 · 106 citations
Video tracking2 · 102 citations
Object (grammar)2 · 102 citations
Tracking (education)2 · 102 citations
Conditional random field1 · 90 citations
Robot2 · 83 citations
Data mining2 · 82 citations
Frame (networking)2 · 82 citations

Key Achievements

9
H-Index
13
Papers
383
Total Citations
29
Avg Citations/Paper
🏆 Most Cited Paper
Deep Continuous Conditional Random Fields With Asymmetric Inter-Object Constraints for Online Multi-Object Tracking
90 citations · 2018
📈 Most Prolific Year: 2018 (3 Papers)
🤝 Key Collaborators: 62
🏛 Institutions: Chinese University of Hong Kong, University of Hong Kong, Xidian University, Wuhan University of Technology, Shanghai Artificial Intelligence Laboratory, ShangHai JiAi Genetics & IVF Institute

Top Papers

  1. 1
    Deep Continuous Conditional Random Fields With Asymmetric Inter-Object Constraints for Online Multi-Object Tracking
    90 citations · 2018
  2. 2
    MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
    79 citations · 2022
  3. 3
    VS-Net: Voting with Segmentation for Visual Localization
    48 citations · 2021
  4. 4
    Towards Optimal Platform-Based Robot Design for Ankle Rehabilitation: The State of the Art and Future Prospects
    45 citations · 2018
  5. 5
    A three-stage trajectory generation method for robot-assisted bilateral upper limb training with subject-specific adaptation
    38 citations · 2018
  6. 6
    Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
    30 citations · 2023
  7. 7
    ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models
    18 citations · 2024
  8. 8
    TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
    12 citations · 2023
  9. 9
    Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation
    10 citations · 2023
  10. 10
    CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection
    5 citations · 2024

Key Collaborators

ZJZhengkai Jiang3 shared papersXCXuesong Chen3 shared papersKCKa Chun Cheung3 shared papersBZBenjin Zhu3 shared papersPGPeng Gao2 shared papersHDHao Dong2 shared papersQMQing Miao2 shared papersMZMingming Zhang2 shared papersHCHaonan Chang2 shared papersSHSiyuan Huang2 shared papersSSShaoshuai Shi2 shared papersSHSiyuan Huang2 shared papersAMAndrew McDaid1 shared papersPGPeng Gao1 shared papersYYYi Yang1 shared papersABAbdeslam Boularias1 shared papersGZGuofeng Zhang1 shared papersZLZhen Li1 shared papersXLXin Li1 shared papersYLYuhan Liu1 shared papers
Not generated yet