Summary
Chengeng Liu is a PhD candidate at Nanyang Technological University with eight years of industry experience bridging research and product engineering in computer vision and multimedia. He has driven state-of-the-art work in video anomaly and violence detection using MIL, 3D convolutions and attention-based fusion, and has deployed models for semantic segmentation on Triton for production-ready inference. His background spans backend systems, REST APIs, and full-stack tooling from earlier roles, giving him a pragmatic systems view alongside deep-learning expertise. Trained in software engineering at the University of Melbourne and currently focused on 3D reconstruction and image processing, he blends rigorous academic research with hands-on deployment experience. Notably, he has reproduced and extended multiple VAD studies on real-world datasets like UCF-Crime and XD-violence, emphasizing reproducibility and practical impact.
8 years of coding experience
1 year of employment as a software developer
Master of Engineering - MEng, Software engineering, Master of Engineering - MEng, Software engineering at 澳大利亚墨尔本大学
The University of Melbourne
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Nanyang Technological University Singapore
Chinese, English