I am a PhD candidate, supervised by Prof. Alex Kot, in Rapid-Rich Object Search (ROSE) Lab, NTU-PKU Joint Research Institute, Nanyang Technology University (NTU), Singapore.
I also work as a Research Project Manager in ROSE Lab, as the role of manager and researcher, managing several industrial projects. The projects mainly require computer vision technqiues, such as neural network compression, object detection, image processing, image generation, etc.
My research interests include generalized face anti-spoofing, domain generalization, and application of computer vision algorithms.
[Email: [email protected]] [Google Scholar Profile] [Linkedin] [GitHub] [Research Gate]
Currently, I thesis topic is face presentation/spoofing detection, a.k.a face anti-spoofing. I am interested in using domain generalization techniques to improve face anti-spoofing. In my research projects and experience, I am also interested in neural network compression, and image generation.
I server as reviewers for several top journals or conferences in the field of machine learning and computer vision: IEEE T-IP, IEEE T-IFS, IEEE T-CSVT, IEEE Access, IJCV, ICME, AAAI, ICCV etc.
I was as an invited speaker in 13th IEEE International Workshop on Information Forensics and Security (2021).
Learning Meta Pattern for Face Anti-Spoofing, IEEE Transactions on Information Forensics and Security, 17, pp.1201-1213. Rizhao Cai, Zhi Li., Renjie Wan, Haoliang Li, Yongjian Hu, Alex Kot
Comments: Paper available on [IEEE] [ArXiv] [GitHub] [Research Gate]
Toward domain generalized pruning by scoring out-of-distribution importance, 36th Neural Information Processing Systems (NeurIPS 2022) Workshop on Distribution Shift
Rizhao Cai, Haoliang Li, Alex Kot
Comments: Source in [ArXiv]
Image Inpainting Detection via Enriched Attentive Pattern with Near Original Image Augmentation, ACM Multimedia (ACM MM) 2022
Wenhan Yang, Rizhao Cai, Alex Kot
Comments: 30th ACM International Conference on Multimedia. Paper available on [ResearchGate]
One-Class Knowledge Distillation for Face Presentation Attack Detection, IEEE Transactions on Information Forensics and Security 17, 2137-2150
Zhi Li, Rizhao Cai, Haoliang Li, KY Lam, Yongjian Hu, Alex Kot Comments: Paper available on [IEEE] [ArXiv] [GitHub]
DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing, IEEE Transactions on Information Forensics and Security, vol. 16, pp. 937-951, 2021, doi: 10.1109/TIFS.2020.3026553. Rizhao Cai, Haoliang Li, Shiqi Wang, Changsheng Chen and Alex C. Kot
Comments: Paper available on [IEEE] [ArXiv] [Research Gate]
A Copy-Proof Scheme Based on the Spectral and Spatial Barcoding Channel Models, IEEE Transactions on Information Forensics and Security 15, 1056-1071 Changsheng Chen, Mulin Li, A Ferreira, Jiwu Huang, Rizhao Cai Comments: source code and datasets are available in OneDrive.
Towards More Efficient Security Inspection via Deep Learning: A Task-Driven X-ray Image Cropping Scheme, Micromachine
HD Nguyen, Rizhao Cai, Heng Zhao, Alex Kot, Bihan Wen Comments: This work is as a paper output from one of my industrial projects. Paper available on [MDPI].
Automatic Facial Skin Feature Detection for Everyone, Electronic Imaging (EI) 2022
Qian Zheng, Ankur Purwar, Heng Zhao, Guang Liang Lim, Ling Li, Debasish Behera, Qian Wang, Min Tan, Rizhao Cai, Jennifer Werner, Dennis Sng, Maurice van Steensel, Weisi Lin, Alex C Kot Comments: This work is as a paper output from one of my industrial projects. Paper available on [ArXiv] [About EI 2022]
Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues, arXiv:2208.05401v1 [cs.CV] 10 Aug 2022
Zitong Yu, Rizhao Cai, Zhi Li, Wenhan Yang, Jingang Shi and Alex C. Kot
Comments: submitted to IEEE TIFS. Preprint available on [ArXiv]
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing, arXiv:1910.03850v1 [cs.CV] 9 Oct 2019
Rizhao Cai, Changsheng Chen Comments: this is my final year project (B.Eng thesis). [[ArXiv](https://arxiv.org/abs/1910.03850#:~:text=9 Oct 2019]-,Learning deep forest with multi-scale Local Binary,features for face anti-spoofing&text=Face Anti-Spoofing (FAS),and have achieved competitive performance.)]