Lu Shijian

Lu Shijian is an Associate Professor (tenured) at the School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore. He holds a PhD in Electrical and Computer Engineering from the National University of Singapore and leads the Visual Intelligence Lab (VILab), focusing on humanlike visual perception, understanding, and creation.

• University: Nanyang Technological University
• School: School of Computer Science and Engineering
• Academic Rank: Associate Professor (tenured)
• Email: Shijian.Lu@ntu.edu.sg
• Office: N4-02C-101, NTU, Singapore

His research spans computer vision, deep learning, image and video analytics, visual intelligence, and machine learning, with key topics including scene text detection, unsupervised domain adaptation, image synthesis, satellite image analytics, and facial expression recognition. His work integrates supervised, semi-supervised, and self-supervised learning across 2D images, 3D point clouds, and multi-spectral data.

The recent publications highlight a strong trend in domain adaptation, generative modeling, 3D vision, and multimodal AI. His lab produces high-impact work accepted at top venues like CVPR, ICCV, ECCV, NeurIPS, and TPAMI, with applications in autonomous systems, image editing, and robust AI.

• Top winner of ICFHR2014 Competition on Word Recognition from Historical Documents
• Top winner of ICDAR 2013 Robust Reading Competition (scene text segmentation)
• Top winner of ICDAR 2013 Document Image Binarization Contest (DIBCO 2013)
• Top winner of H-DIBCO 2010 – Handwritten Document Image Binarization Competition
• Top winner of ICDAR 2009 Document Image Binarization Contest (DIBCO 2009)

Lu advises several PhD students and serves as an Associate Editor for Pattern Recognition and Neurocomputing. He has held leadership roles in top conferences as Senior Program Committee member (IJCAI, AAAI) and Area Chair (ICDAR, WACV). His lab, the Visual Intelligence Lab, is actively recruiting PhD students and conducting cutting-edge research in visual intelligence, with recent work on 3D Gaussian splatting, backdoor attacks, and vision-language models.