Yulu Pan

I'm a second year Master's student at the University of North Carolina at Chapel Hill in the Department of Computer Science.

I'm currently working with Prof. Gedas Bertasius on fine-grained skill analysis and AI for sports. I'm also a research assistant at Zylka lab on developing computer vision models for spontaneous pain measurement from mouse.

I graduated May 2023 from UNC with a B.S. in Computer Science and a B.A. in Mathematics. I worked with Prof. Roni Sengupta on computer vision during my undergraduate studies.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Research

I'm broadly interested in Computer Vision and Video Understanding. My current focus is on fine-grained video understanding, particularly in the areas of sports analytics and neuroscience. I’m also interested in AI security, especially for video data. I view video as a rich and valuable large-scale training source of knowledge, but I believe it must be utilized with careful attention to security and safety considerations.

Publication
Basket GIF
BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation
Yulu Pan, Ce Zhang, Gedas Bertasius
Accepted to CVPR 2025
Project Page / Paper / Code & Data

We present BASKET, a large-scale basketball video dataset for fine-grained skill estimation. BASKET contains more than 4,400 hours of video capturing 32,232 basketball players from all over the world. We benchmark multiple SOTA video recognition models and reveal that these models struggle to achieve good results on our benchmark.

Motion Matters: Neural Motion Transfer for Better Camera Physiological Sensing
Akshay Paruchuri, Xin Liu, Yulu Pan, Shwetak Patel, Daniel McDuff*, Soumyadip Sengupta*
WACV, 2024, Oral, Top 2.6%
Project Page / Paper / Code

Neural Motion Transfer serves as an effective data augmentation technique for PPG signal estimation from facial videos. We devise the best strategy to augment publicly available datasets with motion augmentation, improving up to 75% over SOTA techniques on five benchmark datasets.

semi Image
Semi-Supervised Semantic Segmentation with Multi-Reliability and Multi-Level Feature Augmentation
JianJian Yin, Zhichao Zheng, Yulu Pan, Yanhui Gu, Yi Chen*
Expert Systems with Applications, Volume 233, 15 December 2023, 120973
Paper / Code

Introducing a multi-reliability and multi-level feature augmentation framework for semi-supervised semantic segmentation, effectively utilizing labeled and unlabeled images and improving segmentation performance on benchmark datasets.

Misc

I am enthusiastic in helping other students succeed in computer science. I have shared my knowledge and support students' learning journey in the following course:

University of North Carolina at Chapel Hill, Undergraduate Learning Assistant:

  • COMP 301: Foundations of Programming
  • COMP 116: Introduction to Scientific Programming

Brandeis University, Teaching Assistant:

  • COSI 21A: Data Structures and the Fundamentals of Computing

Cloned from Jon Barron.