Hongda Liu

I am currently a Ph.D. student at the NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Zhenan Sun. Prior to that, I received my bachelor's degree in Computer Science and Technology from Jilin University in 2020, working with Prof. Shuai Lyu.

My research interests revolve around human-centric action understanding, video recognition, and multi-modality learning. If you are interested in my work, please feel free to reach out for discussions or collaborations!

Email / Google Scholar / Github

Publications

	Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition Hongda Liu, Yunfan Liu, Min Ren, Hao Wang, Yunlong Wang, Zhenan Sun CVPR, 2025 [paper] [code] ProtoGCN, a novel graph prototype learning method that amplifies subtle distinctions for accurate differentiation of similar actions.
	Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition Hongda Liu, Yunlong Wang, Min Ren, Junxing Hu, Zhengquan Luo, Guangqi Hou, Zhenan Sun Machine Intelligence Research (MIR), 2025 [paper] [code] BRL, a method to address the long-tailed problem in action recognition.

Honors and Awards

First prize, Excellent Undergraduate Scholarship of Jilin University, 2018, 2019.
Second Price in China National Mathematical Contest in Modeling, 2018.
Excellent Student of Jilin University, 2017.
National Scholarship, 2017.

Teaching Assistant

Biometrics, 081104M06011H, UCAS. (Spring, 2022, 2023, and 2024)

Website Template