Hang Dai

Masdar City, Building 1B, 2nd Floor, Abu Dhabi, UAE. hang.dai@mbzuai.ac.ae

I am an Assistant Professor in the Computer Vision department at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). My research interests include geometric deep learning, deepfake detection, 3D computer vision, vision and language, medical image analysis.


News

One paper accepted in CVPR 2021, congrats to Shujie Luo. M3DSSD: Monocular 3D Single Stage Object Detector.

One paper accepted in ISBI 2021, FocusNet++: Attentive Aggregated Transformations for Efficient and Accurate Medical Image Segmentation.

Congratulations! Dr. Hang Dai and Intern. Shujie Luo won 1st and 2nd place in ECCV 2020 Challenge.


Group

Group Page

Postdoc Researcher

Xuebin Qin

Research Students

Ahmed Adel Gomaa Elhagry, Asma Ahmed Hashmi, Ahmed Said Mohamed Al Mahrooqi, Bao Yunqing, Dmitrii Medvedev, Hussam Osama Azzuni, Kevin Michael Toner, Li Zhiyuan, Zakaria Sebaitre, Zangir Iklassov

Alumni

Shujie Luo (horizon.ai)

Awards

  • 2020, 1st and 2nd in ECCV Commands for Autonomous Vehicles Challenge
  • 2019, Orator in graduation ceremony, University of York, UK
  • 2015-2018, Overseas Research Scholar, University of York, UK
  • 2017, Best student paper, University of York, UK

Research

Autonomous Driving, Image Segmentation, Object Detection, Vision and Language, 3D Reconstruction from Single Image, Deepfake Detection, Medical Image Analysis.


Publications

  • M3DSSD: Monocular 3D Single Stage Object Detector, Shujie Luo, Hang Dai, Ling Shao, Yong Ding. CVPR 2021.
  • A Human Ear Reconstruction Autoencoder, Hao Sun, Nick Pears, Hang Dai. VISAPP 2021.
  • FocusNet++: Attentive Aggregated Transformations for Efficient and Accurate Medical Image Segmentation, Chaitanya Kaul, Nick Pears, Hang Dai, Roderick Murray-Smith, Suresh Manandhar. ISBI 2021.
  • Penalizing small errors using an Adaptive Logarithmic Loss. C. Kaul, N. Pears, H. Dai, R. Murray-Smith, and S. Manandhar. ICPR-W 2020.
  • Commands for autonomous vehicles by progressively stacking visual-linguistic representations. H. Dai, Luo, S., Ding, Y., Shao, L. In: Commands for Autonomous Vehicles (C4AV)Workshop, ECCV (2020).
  • Cross-modal representations from transformer. Luo, S.,H. Dai, Shao, L., Ding, Y.. In: Commands for Autonomous Vehicles (C4AV) Workshop, ECCV (2020)
  • 3D Morphable Models: The Face, Ear and Head, 3D Imaging, Analysis and Applications. H Dai, N Pears, P Huber, WAP Smith. 463-512, 2020, Spinger. (Book Chapter)