About me

I am a full professor in the School of Computer Science at Wuhan University and an honorary research fellow at University of Glasgow. Prior to that, I was a Lecturer in Machine Learning at University of Glasgow and an Assistant Professor at MBZUAI. I was awarded a PhD in Computer Science (2019) at University of York, where I received the Overseas Research Scholarship.

News

📢We are recruiting! Multiple Postdoc, PhD, and MSc positions are open in autonomous driving, robotic vision, and embodied AI. Applicants with CVPR/ICCV/ECCV/NIPS publications are preferred. Please email me with your CV and highlight your interest area.🚀

📢I serve as an Area Chair and an Industrial/Keynote Chair for BMVC 2024.🚀

Research Interests

Autonomous Driving: Occupancy Network, 3D Object Detection, 3D Semantic Segmentation, End-to-End AD Network;
Robotic Vision: 3D Reconstruction, Dichotomous Image Segmentation, Camouflaged Object Detection;
Embodied AI: Vision-Language Models, Command for Robotics.

Challenge Awards

🥈The 2nd place in CVPR 2022 Waymo Open Challenge on the task of 3D Semantic Segmentation
🥉The 3rd place in CVPR 2022 Waymo Open Challenge on the task of 3D Object Detection
🥇The 1st place in ECCV 2020 Commands for Autonomous Vehicles Challenge
🥈The 2nd place in ECCV 2020 Commands for Autonomous Vehicles Challenge

🔥3D Perception in Autonomous Driving(Seg, Det, Occ): the ability of an autonomous system to collect 3D information and extract relevant knowledge from the environment.

🔥Dichotomous Image Segmentation (DIS): accurately segmenting objects with details and different structure complexities, regardless of their characteristics.

🔥Headspace Dataset: a set of 3D images of the human head, consisting of 1519 subjects wearing tight fitting latex caps to reduce the effect of hairstyles. (Image reproduced from Nick’s website)

🔥Liverpool-York Head Model (LYHM): build 3D models of human face and cranium variation in order to support clinical planning and surgical intervention evaluation tools for craniofacial surgeons.

📝MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving. J Li, H Dai, H Han, Y Ding. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, pp. 21694-21704. [PDF] [Arxiv] [Code]
📝Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformer. Z Huang, H Dai, TZ Xiang, S Wang, HX Chen, J Qin, H Xiong. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, pp. 5557-5566. [PDF] [Arxiv] [Code]
📝Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection. Y Hong, H Dai, Y Ding. Proceedings of European Conference on Computer Vision (ECCV) 2022, 13670, pp. 87-104. [PDF] [Arxiv] [Code]
📝Highly accurate dichotomous image segmentation. X Qin, H Dai, X Hu, DP Fan, L Shao, L Van Gool. Proceedings of European Conference on Computer Vision (ECCV) 2022, pp. 38-56. [PDF] [Arxiv] [Code] [Dataset]

Teaching Courses

📚COMPSCI5103 - Deep Learning For MSc (M), University of Glasgow
📚COMPSCI5012 - Internet Technology (M), University of Glasgow
📚CV701 - Human and Computer Vision, MBZUAI
📚CV702 - Vision and Geometry, MBZUAI
📚TA Courses @ University of York: COM00005C - Mathematical Foundations of Computer Science, COM00007C - Theory and Practice of Programming, COM00009I - Vision and Graphics, COM00027H - Computer Vision, COM00006C - Numerical Analysis, COM00005I - Principles of Programming Languages

Acknowledgments

🧡I would like to thank my supervisors, students, collaborators, and funding resources during my academic career.