Tel: +65 6499 4542
Building 1, Level 5, 1.502-17
8 Somapah Road, Singapore 487372
Research Interest: Image and Signal Processing/Analysis, Computer Vision, Machine Learning, AI
[09/2022: NeurIPS-2022] Yunqing Zhao (*), Keshigeyan Chandrasegaran (*), Milad Abdollahzadeh (*), Ngai-Man Cheung, "Few-shot Image Generation via Adaptation-aware Kernel Modulation," in Proc. NeurIPS 2022. (*) Equal contribution.
[09/2022: ECCV-2022 (Oral)] K Chandrasegaran, NT Tran, A Binder, NM Cheung, "Discovering Transferable Forensic Features for CNN-generated Images Detection," in Proc. ECCV 2022 (Oral) [PDF]
[06/2022: ICML-2022] K Chandrasegaran, NT Tran (*), Y Zhao (*), NM Cheung, "Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?" in Proc. ICML-2022 [PDF]. (*) Equal contribution.
[06/2022: CVPR-2022] Y Zhao, H Ding, H Huang, NM Cheung, "A Closer Look at Few-shot Image Generation," in Proc. CVPR-2022 [PDF]
[02/2022: AAAI-2022 (Oral)] Thilini Cooray, Ngai-Man Cheung, "Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning," in Proc. AAAI-2022 (Oral) [PDF]
[10/2021: NeurIPS-2021] Milad Abdollahzadeh, Touba Malekzadeh, Ngai-Man Cheung, "Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning," in Proc. NeurIPS-2021 [PDF]
[06/2021: TPAMI paper] Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita, "Shell Theory: A Statistical Model of Reality" IEEE Transactions on Pattern Analysis and Machine Intelligence 2021.
[06/2021] Outstanding Reviewer Award. IEEE Transactions on Multimedia.
[04/2021: CVPR-2021 (Oral)] Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Ngai-Man Cheung, "A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection," in Proc. CVPR-2021 (Oral) [PDF] [Project and code]
[04/2021: Signal Processing] R Liu, NM Cheung, "Joint estimation of low-rank components and connectivity graph in high-dimensional graph signals: application to brain imaging" Signal Processing 2021
[01/2021: TIP paper] NT Tran, VH Tran, NB Nguyen, TK Nguyen, NM Cheung, "On data augmentation for GAN training" IEEE Transactions on Image Processing 30, 1882-1897
[01/2021: WACV-2021 (Oral)] KS Lee, NT Tran, NM Cheung, "InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning" IEEE Winter Conference on Applications of Computer Vision 2021
[12/2020: IJCAI-2020] T Hoang, TT Do, TV Nguyen, NM Cheung, "Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks" IJCAI-2020. International Joint Conference on Artificial Intelligence
[12/2020: TIP paper] T Hoang, TT Do, TV Nguyen, NM Cheung, "Unsupervised Deep Cross-modality Spectral Hashing" IEEE Transactions on Image Processing 29, 8391-8406
[06/2020: CVPR-2020] Y Guo, NM Cheung, "Attentive Weights Generation for Few Shot Learning via Information Maximization" CVPR-2020
[06/2020: CVPR-2020] T Cooray, NM Cheung(*), W Lu, "Attention-Based Context Aware Reasoning for Situation Recognition" CVPR-2020. (*) Corresponding author
[12/2019: ICCV-2019] L Yang, NM Cheung(*), J Li, J Fang, "Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph Embedding" ICCV 2019. (*) Corresponding author
[12/2019: TMM Paper] TT Do, T Hoang, DK Le Tan, AD Doan, NM Cheung, "Compact hash code learning with binary deep neural network" IEEE Transactions on Multimedia 22 (4), 992-1004
[12/2019: NeurIPS-2019] Trung Tran, Hung Tran, Ngoc Nguyen, Linxiao Yang, Ngai-Man Cheung, "Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game," in Proc. NeurIPS-19 (NIPS-19) (Total 6743 submissions. 21.1% acceptance rate) [PDF]
[06/2019: CVPR-2019 Best Paper Finalist] H Le, TT Do, T Hoang, NM Cheung, "SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR-19) (Oral) (Total 5160 submissions) [PDF]
Ngai-Man (Man) Cheung is an Associate Professor with Singapore University of Technology and Design (SUTD). He receives his Ph.D. degree in Electrical Engineering from University of Southern California (USC), Los Angeles, CA. His Ph.D. research focused on image and video coding, and the work was supported in part by NASA-JPL. He was a postdoctoral researcher with the Image, Video and Multimedia Systems group at Stanford University, Stanford, CA. He has also held research positions with IBM T. J. Watson Research Center, Hong Kong University of Science and Technology (HKUST), and Mitsubishi Electric Research Labs (MERL).
His research has resulted in 14 U.S. patents granted with several pending. Two of his inventions have been licensed to companies. One of his research results has led to a SUTD spinoff on AI for wound care. His research has also been featured in the National Artificial Intelligence Strategy.
He has received several research recognitions, including recently the Best Paper Finalist at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019, the Finalist of Super AI Leader (SAIL) Award at the World AI Conference (WAIC) 2019 at Shanghai, China, and the Excellence in Research Award from SUTD.
His research interests are Image and Signal Processing, Computer Vision and AI.