Hao Ding
Hao Ding’s Personal Website
Welcome to my personal website! I am a Ph.D. candidate at the Department of Computer Science, Johns Hopkins University. My work focuses on computer vision and surgical robotics. Feel free to explore my research, projects, and publications!
About Me
I am currently Ph.D. candidate at the Department of Computer Science, Johns Hopkins University. My research interests include:
- [Robust low-level processing of surgical videos]
- [Robust high-level analysis of surgical videos]
- [Robust Surgical Automation]
My mission is to develop a digital twin-based framework that relies on robust low-level processing of vision perceptions to ensure the robustness of high-level surgiacl analysis and automation.
Publications & Ongoing Projects
Below are some of my selected publications and ongoing projects. For a full list, visit my Google Scholar profile.
Digital Twin-based Robust Surgical Automation
Towards Robust Automation of Surgical Systems via Digital Twin-based Scene Representations from Foundation Models
Submitted to ICRA 2025, paper link.
Digital Twin-based Robust Surgical Video Analysis
Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin-based Scene Representation
Submitted to IPCAI 2025, paper link.
Neural Finite-State Machine for Surgical Phase Recognition
Robust Low-level Processing of Surgical Videos
Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentation
Accepted by SPIE2025, paper link.
SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions – An EndoVis’24 Challenge
MICCAI2024 EndoVis Challenge, paper link and challenge website.
Rethinking causality-driven robot tool segmentation with temporal constraints
Published in IPCAI2023, paper link.
Carts: Causality-driven robot tool segmentation from vision and kinematics data
Published in MICCAI2022, paper link.
Digital twins as a unifying framework for surgical data science: the enabling role of geometric scene understanding
Published in Artificial Intelligence Surgery, paper link.
Influence selection for active learning
Published in ICCV2021, paper link.
Deeply shape-guided cascade for instance segmentation
Published in CVPR2021, paper link.
Contact
Feel free to reach out to me via:
- Email: hding15@jhu.edu
- LinkedIn: Hao Ding
- GitHub: hding2455
Acknowledgments
Thank you for visiting my website. For feedback or inquiries, don’t hesitate to contact me!