I am a fourth-year Ph.D. student of Computer Science and Engineering at University at Buffalo. I am fortunate to be supervised by Prof. Junsong Yuan. Prior to UB, I obtained my M.D. from Peking University, where I was initially trained as a physician. My current research interest lies in vision-language learning and visual reasoning. On the medical domain, my goal is to harness these capabilities to enhance medical practices for optimal healthcare provision.

Contact: nanxi [at] buffalo dot edu

Research Interest and Highlights

Video Human-Object Interaction Detection

1. [*New*]

   Nan Xi, Jingjing Meng, Junsong Yuan. “Open Set Video HOI detection from Action- centric Chain-of-Look Prompting”. in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2023

Surgical Scene Understanding

1. [*New*]

   Nan Xi, Jingjing Meng, Junsong Yuan. “Chain-of-Look Prompting for Verb-centric Surgical Triplet Recognition in Endoscopic Videos”, in Proc. ACM International Conf. on Multimedia (ACM MM), 2023

2. Nan Xi, Jingjing Meng, Junsong Yuan. “Forest Graph Convolution Network for Sur- gical Action Triplets Recognition in Endoscopic Videos”, in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022