Research interests

Lu’s research focuses on computer vision and sensing, image and video analytics, and deep learning. He has been working on scene text detection and recognition for years, contributing to a number of impactful benchmarking datasets as well as innovative detection and recognition techniques. In recent years, Lu has been studying how to tackle data collection and data annotation challenges in deep network training.

Bio

Lu is currently an associate professor (tenured) in the School of Computer Science and Engineering, Nanyang Technological University (NTU). He has held an adjunct position at MBZUAI since late 2021. Before joining NTU in 2017, he took a number of leadership roles in the Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*SATR) in Singapore, including head of the Visual Attention Lab, deputy head of the Satellite Department, co-chair of the Image and Pervasive Access Laboratory (a CNRS overseas laboratory hosted by A*STAR in Singapore). Lu’s research focuses on computer vision and sensing, image and video analytics, and deep learning. He won a number of international benchmarking competitions such as DIBCO2009, H-DIBCO2010, DIBCO2013, RRC2013, ANWRESH-2014, etc.

Education

• Ph.D. in electrical and computer engineering from the National University of Singapore
• Master’s degree in electrical engineering from the Xi’an Jiaotong University, China

Research

Lu has authored or co-authored more than 200 academic papers, and has filed up to 10 patents in the US and EU. His developed technology has been successfully licensed to industry and deployed in daily operations.

• Guan, D., Huang, J., Xiao, A., & Lu, S. (2022). Unbiased subclass regularization for semi-supervised semantic segmentation. CVPR.
• Zhan, F. Z., Zhang, J., Yu, Y., Wu, R., & Lu, S. (2022). Modulated contrast for versatile image translation. CVPR.
• Zhang, G., Luo, Z., Yu, Y., Cui, K., & Lu, S. (2022). Accelerating DETR convergence via semantic-aligned matching. CVPR.
• Zhang, J., Huang, J., Tian, Z. T., & Lu, S. (2022). Spectral unsupervised domain adaptation for visual recognition. CVPR.
• Zhou, C., Luo, Z. L., Luo, Y., Liu, T., Pan, L., Cai, Z., Zhao, H., & Lu, S. (2022). PTTR: Relational 3d point cloud object tracking with transformer. CVPR.
• Xue, C., Tian, Z., Zhan, F., Lu, S., & Bai, S. (2022). Fourier document restoration for robust document dewarping and recognition. CVPR.

Accolades

• Senior Program Committee (SPC) of the International Joint Conference on Artificial Intelligence (IJCAI18 – IJCAI21)
• Senior Program Committee (SPC) of the AAAI Conference on Artificial Intelligence (AAAI18 – AAAI21)
• Area Chair of 15th International Conference on Document Analysis and Recognition (ICDAR-19)
• Area Chair of IEEE Winter Conference on Applications of Computer Vision (WACV-17 and WACV-18)
• Area Chair of 14th IAPR International Conference on Document Analysis and Recognition (ICDAR-17) 
• Top winner of the ICFHR2014 Competition on Word Recognition from Historical Documents
• Top winner of the ICDAR 2013 Robust Reading Competition (1^st in the scene text segmentation task)
• Top winner of the ICDAR 2013 Document Image Binarization Contest (DIBCO 2013)
• Top winner of the H-DIBCO 2010 – Handwritten Document Image Binarization Competition
• Top winner of the ICDAR 2009 Document Image Binarization Contest (DIBCO 2009)

Dr. Pengtao Xie joined MBZUAI as an Assistant Professor (Adjunct) in the Department of Machine Learning. is an assistant professor at UC San Diego. He received his PhD from the Machine Learning Department at Carnegie Mellon University in 2018. His research interests are machine learning inspired by humans’ learning skills (especially classroom learning skills), such as learning by progressive examination, interleaving learning, small-group learning, learning by teaching, etc., and their applications in healthcare. He serves as area chair for ICML, CVPR, ICCV, NAACL, etc. His PhD thesis was selected as a top-5 finalist for the AMIA Doctoral Dissertation Award. He is the recipient of the Amazon AWS Faculty Award, Tencent AI-Lab Faculty Award, Tencent WeChat Faculty Award, the Innovator Award presented by the Pittsburgh Business Times, the Siebel Scholars award.

Dr. Zhiqiang was a senior research scientist with Baidu Research at China. He holds the PhD from the school of computer engineering, Nanyang Technological University, Singapore.

Dr. Zhiqiang research interests lie at the intersection of numerical computation, stochastic optimization, and Riemannian optimization. He is also interested in deep learning, clustering, community detection, topic modeling, etc. His recent ongoing works are about faster alternating least-squares for CCA, comprehensively tight analysis of gradient descent for PCA, accelerated inexact power methods, and Riemannian search for eigenvector computation.

Dr. Zhiqiang was serving as a reviewer for several academic activities of IJCAI, AAAI, ICLR, ICML, NeurIPS in various years. He also has industrial experiences about automatic optical inspection (AOI) for TFT-LCD panels and solar wafers, data analytics for airlines and insurances.

Dr. Yuanzhi Li is joining MBZUAI as an Affiliated Assistant Professor in the Computer Vision department. He is an Assistant Professor at CMU, Machine Learning Department. Previously, he was a postdoctoral researcher at Stanford. He did his Ph.D. at Princeton under the advise of Sanjeev Arora (2014-2018) and his undergraduate study at Tsinghua university (2010-2014).

His primary research area is deep learning theory, focusing on (1). Understanding the hierarchical feature learning process in neural networks and how its better than shallow learning methods. (2). How the choice of optimization algorithms affects the training speed of different types of neural networks, and how it influences the generalization of the learned solution. (3). How to use pre-trained neural networks in downstream applications more effectively.

Dr. Min Xu is an Affiliated Assistant Professor in Computer Vision Department at MBZUAI. He is also an Assistant Professor at the Computational Biology Department within the School of Computer Science at Carnegie Mellon University, USA. His career has centered on developing AI methods for the analysis of biomedical images and other biomedical data, in particular, Cellular Cryo-Electron Tomography (Cryo-ET) 3D image data. Dr. Xu has published over 70 research papers in prestigious peer-reviewed conferences and journals, such as CVPR, ICCV, ISMB, MICCAI, PNAS, Bioinformatics, PLOS Computational Biology, Structure, and JSB.

Dr. Xu received a B.E. in Computer Science from the Beihang University, M.Sc from the School of Computing at the National University of Singapore, M.A. in Applied Mathematics from the University of Southern California (USC), and Ph.D. in Computational Biology and Bioinformatics from USC. He was a postdoctoral researcher at USC.

Dr Shangsong was an associate professor at the Sun Yat-sen University since 2018. Prior to that he was an research scientist at the King Abdullah University of Science and Technology from January 2018 to December 2018. He received his Ph.D. degree from the University of Amsterdam, The Netherlands, in 2014, supervised by Prof. dr. Maarten de Rijke, the Academician of the Royal Netherlands Academy of Art  and Sciences, in the field of computer science.

Dr Shangsong’s research interests lie in the field of Information Retrieval, Data Mining, Artificial Intelligence, and Machine Learning (especially, Deep Learning). He has published over 60 peer-reviewed papers, most of which are in top-tier venues such as SIGIR, KDD, NeurIPS, WWW, AAAI, IJCAI, WSDM, CIKM, TKDE, TOIS, and TKDD. He is an editor member of the journal of Information Processing & Management since 2016 and a Young Associate Editor-in-Chief of the Journal of Computer Science and Technology since 2021. He is PC member and reviewer in a number of conferences and journals such as SIGIR 2017-2021, KDD 2021, ICML 2021, NeurIPS 2020-2021, WWW 2018-2021, IJCAI 2018-2021 (IJCAI 2021 SPC), AAAI 2019-2021, TKDE, TKDD, and TOIS.

Dr Shangsong has received various awards/honors such as the SIGIR 2017 Outstanding Reviewer Award, Outstanding Contribution for instructing Data Mining course from the International Petroleum Engineers, the Kingdom of Saudi Arabia Section. He has been teaching a number of courses such as Introduction to Data Mining, Machine Learning and Data Mining, and Introduction to Information Retrieval.

Dr Mohammad Yaqub is an Assistant Professor in the Computer Vision department at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). He is also an honorary research fellow at the Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK.

Prior to joining MBZUAI, Dr Yaqub spent 12 years in Oxford, UK. He received his DPhil (PhD) in Biomedical Engineering from the University of Oxford in 2011. During his PhD, he was supervised by Prof Alison Noble, Dr Kassim Javaid and Prof Cyrus Cooper. He worked on developing machine learning solutions to real-world medical problems. After his PhD, he was a research fellow (2011 - 2016) at the Institute of Biomedical Engineering, University of Oxford and a lecturer (2010 - 2020) in the IT Services, University of Oxford.

He worked on several problems including fetal brain structure detection and segmentation in 2D and 3D ultrasound, fusion of 4D echocardiographic images, automatic categorization and quality checking of images from routine fetal anomaly scans. He has co-supervised PhD and master students during his work at Oxford.

Dr Yaqub was also the Vice President of Engineering (2016 - 2020) at Intelligent Ultrasound limited where he led a team to build AI-based medical device products. Dr Yaqub has taken his research ideas from its early days at the University of Oxford all the way to the integration of a medical product (ScanNav) into the ultrasound machines of a world-leading manufacturer.

Dr Yaqub’s research interests include medical image analysis (e.g, ultrasound, MRI and CT), deep learning, machine learning, and medical image registration. He has published over 35 peer-reviewed articles in top conferences and journals such as IEEE TMI, Medical Image Analysis, MICCAI and Ultrasound in Medicine and Biology. He has been granted multiple research grants and two patents. He is co-organizing the 24^th Medical Image Understanding and Analysis (MUIA) in summer 2020 at Oxford University.

Bin Gu is an Assistant Professor in the Machine Learning department at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). Prior to joining MBZUAI, he was a full professor of Nanjing University of Information Science and Technology. He received the B.S. and Ph.D. degrees in computer science from the Nanjing University of Aeronautics and Astronautics, in 2005 and 2011, respectively. He was a Post-Doctoral Fellow with the University of Western Ontario from 2013 to 2015, with the University of Texas at Arlington from 2016 to 2017, and the University of Pittsburgh from 2017 to 2018. His research interests focus on large scaling optimization in machine learning and data mining. He has published 40 more papers, with over 2,000 citations according to Google Scholar.  He served as a program committee member or reviewer for several leading machine learning and data mining conferences and journals such as NIPS, ICML, KDD, AAAI, TPAMI, JMLR, and a senior program committee member of IJCAI 2019 and 2020.