About ME
Zhaofan Qiu (邱钊凡)
Google Scholar
zhaofanqiu@gmail.com
I am currently a Researcher in HiDream.ai - a pioneer Generative Artificial Intelligence company in China. My research interests include image/video generation, multi-modality understanding and deep architecture designs. I has authored or co-authored 50+ papers in top-notch Journals and Conferences, with about 6,000+ citations and an hindex of 26, according to Google Scholar. My works have also led to many awards, including Excellence Award of CAS Dean's Scholarship 2020 and Microsoft Research Asia Fellowship 2017.
I received B.E. and Ph.D. degrees from the University of Science and Technology of China, Hefei, China, in 2015 and 2020, respectively. My seminal work on Pseudo-3D network has become one of standard 3D convolution neural networks for spatiotemporal data analysis. I am the key architect of the top-performing multimedia analytic systems in worldwide competitions such as ActivityNet Large Scale Activity Recognition Challenge 2021 & 2019 & 2017 & 2016, Visual Domain Adaptation Challenge 2018 & 2017, and THUMOS Action Recognition Challenge 2015. I am the co-organizer of Identity-Preserving Video Generation Challenge in ACM MM 2025, Pre-training for Video Understanding Challenge in ACM MM 2021 & 2022.