SUN, Pengzhan |
I'm currently a Ph.D. student at National University of Singapore from 2024 Spring, a member of CVML@NUS.
I received B.S. degree (with Highest Honor) in Mathematics-Physics Fundamental Science from Yingcai Honors College at University of Electronic Science and Technology of China in 2022, supervised by Prof. Wen Li and Prof. Lixin Duan. I received Master of Computing in Artificial Intelligence from School of Computing, National University of Singapore in 2024, supervised by Prof. Angela Yao.
I focus on problems in machine learning and computer vision, where beautiful theory and practical methodology meet. My current research interests include but are not limited to 1) trustworthy VQA, 2) video understanding, and 3) pose estimation.
University of Electronic Science and Technology of China (UESTC), China Honours Bachelor Degree in Mathematics-Physics Fundamental Science (AI Specialization). Yingcai Honors College. • Sep. 2018 - Jun. 2022Lab: Data Intelligence Group Supervisors: Prof. Wen Li and Prof. Lixin Duan Collaborated with Dr. Bo Wu | |
King Abdullah University of Science and Technology (KAUST), Saudi Arabia Visiting Student Research Program. Computer, Electrical and Mathematical Sciences and Engineering. • Apr. 2022 - Aug. 2022Lab: Vision-CAIR Supervisor: Prof. Mohamed Elhoseiny Collaborated with Prof. Li Erran Li | |
National University of Singapore (NUS), Singapore Graduate Student (with Dissertation Option). School of Computing. • Aug. 2022 - Jan. 2024PhD Student. School of Computing. • Jan. 2024 - Present Lab: CVML@NUS Supervisor: Prof. Angela Yao Collaborated with Prof. Linlin Yang and Dr. Junbin Xiao |
[JAN 2024] I was excited to join CVML@NUS as a 2024 Spring PhD student.
Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition |
ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment |
|
Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers |
|
HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models |
|
Counterfactual Debiasing Inference for Compositional Action Recognition. |
Conference Reviewer: