On 23 FA, I will be a master student of Information Processing Lab at University of Washington, advised by Professor Jenq-Neng Hwang. I am currently working on human perception model, generative model, video understanding, and multi-modality learning.

When I am not doing research, I like photography, traveling, and singing.

• Aug 2023: Our paper Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement is accepted by BMVC 2023.


• July 2023: Our paper Sequential Affinity Learning for Video Restoration is accepted by ACM MM 2023.


• July 2023: Our paper PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Enhanced 3D Human Pose Estimation is accepted by ACM MM 2023.


• July 2023: Our project MovieChat: From Dense Token to Sparse Memory in Long Video Understanding is released at website.


• July 2023: Our paper StableVideo: Text-driven Consistency-aware Diffusion Video Editing is accepted by ICCV 2023.


• July 2023: Our paper Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation is accepted by ICCV 2023.


• Apr 2023: The short version of our paper DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models is accepted by CVPR 2023 6th Workshop on Computer Vision for Fashion, Art, and Design.


• Mar 2023: Our paper Deep Learning Methods for Small Molecule Drug Discovery: A Survey is accepted by IEEE T-AI.