Scholar
Mu Chen
Google Scholar ID: eyBlZUUAAAAJ
University of Technology Sydney (UTS)
Citations & Impact
Citations
127
H-index
5
i10-index
4
Publications
7
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Thesis titled 'Towards Comprehensive Visual Understanding via Deep Neural Networks' as part of Ph.D. studies; 'DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation' accepted by CVPR 2025; 'GvSeg: General and Task-Oriented Video Segmentation' accepted by ECCV 2024; 'Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation' selected for oral presentation at ACM Multimedia 2024 (acceptance rate 3.97%); 'PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation' presented at ACM Multimedia 2023; 'UAHOI: Uncertainty-aware robust interaction learning for HOI detection' accepted by CVIU 2024.
Research Experience
- Involved in multiple research projects, including DiffVsgg, DCF, GvSeg, UAHOI, and PiPa, with publications accepted at CVPR'25, ACM MM'24, ECCV'24, among other top international conferences.
Education
- Ph.D. student at the University of Technology Sydney (UTS), affiliated with ReLER Lab and Australian Artificial Intelligence Institute (AAII), advised by Prof. Yi Yang. Obtained B.Eng from Monash University in 2021.
Background
- Research interests lie in the intersection of computer vision and human visual reasoning. Initially focused on enhancing generalization capabilities of deep models for scene understanding tasks such as image/video segmentation, then applied cutting-edge techniques like diffusion models and LLMs to advance high-level scene understanding tasks including Video Scene Graph Generation. Recently, has been pursuing research in hierarchical scene-layout modeling for navigation robotics and exploring LLM-driven multi-agent systems with applications in computer vision and social simulation.
Miscellany
- Feel free to contact him via email or Google Scholar.
Co-authors