Hello,
a bit about me:

I'm a PhD student in Computer Science at Brown University. I'm very happy to work with Prof. Srinath Sridhar at Brown Visual Computing Group. My research interests are in Computer Vision, Graphics, Machine Learning, and Robotics. Besides that, I enjoy reading about Cognitive Science.

Previously, I received my Bachelor degree from the University of the Chinese Academy of Sciences. I also had a wonderful time at the University of Southern California, the University of California San Diego, and Microsoft Research Asia.

You Found
a Secret!
...and more about me:
cv_button

CV/
Resume

google_button

Google
Scholar

lkin_icon

LinkedIn
Profile

ucas_button

B.E.@
UCAS

brown_button

Ph.D.@
Brown

art_button

Arts
Todo...

Research Paper

click image for details

HRFormer: High-Resolution Transformer for Dense Prediction.
Y.H. Yuan, R. Fu, L. Huang, W.H. Lin, C. Zhang, X.L. Chen, J.D. Wang.
NeurIPS 2021
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost. We demonstrate the effectiveness of the High-Resolution Transformer on both human pose estimation and semantic segmentation tasks, e.g., HRFormer outperforms Swin transformer by 1.3 AP on COCO pose estimation with 50% fewer parameters and 30% fewer FLOPs.
[paper] [github]

click image for details

RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval.
R. Fu, J. Yang, J.W. Sun, F.L. Zhang, Y.K. Lai, L. Gao.
CoRR
We introduce a novel deep architecture, RISA-Net, which learns rotation invariant 3D shape descriptors that are capable of encoding fine-grained geometric information and structural information, and thus achieve accurate results on the task of fine-grained 3D object retrieval. We also build and publish a new 3D shape dataset with sub-class labels for validating the performance of fine-grained 3D shape retrieval methods.
[paper] [github] [dataset]
Education
BROWN UNIVERSITY Sept.2021 – Jun.2026(expected)
  • Title: Computer Science Ph.D. Student
  • Concentration: Vision, Graphics and Robotics
UNIVERSITY OF CHINESE ACADEMY OF SCIENCES Sept. 2017-Jul. 2021
  • Degree: Bachelor of Computer Science.
  • GPA: 3.72/4.00.
  • Core GPA: 3.82/4.00.
  • Outstanding Thesis Awards.
  • National Inspirational Scholarship(5%).
UNIVERSITY OF SOUTHERN CALIFORNIA Jan. 2020-May. 2020
  • Title: Visiting Student.
  • GPA: 4.00/4.00.
Internship
Research intern: Microsoft Research, Asia Mar. 2021 – July. 2021

Group: Speech Group, Visual Computing GroupBeijing, China
  • Proposed a transformer-based neural network for dense prediction tasks.
  • Achieved state-of-the-art performance on COCO human pose estimation benchmark.
Research intern: University of California, San Diego May. 2020 – Nov. 2020

Advisor: Prof. Hao Su.San Diego, CA, USA
  • Studied the problem of geometric based manipulation for efficient exploration.
  • Proposed a novel neural network architecture that predicts grasp proposals efficiently and effectively
Research intern: Institute of Computing Technology, CAS. Jul. 2019 – Nov. 2020

Advisor: Prof. Lin Gao Beijing, China
  • Fine-grained 3D Shape Retrieval: Proposed a deep architecture for rotation-invariant fine-grained 3D shape retrieval.
  • Talking Head Generation: Designed a pipeline that generates high-quality speech-driven talking head video with expressive emotion.
Contact me:

Email: rao_fu@brown.edu

Mail: Brown University Box 1910, Providence, RI 02912

Buy me a Boba:

If you like my homepage and think it's useful, welcome to buy me a Boba! Tips via Wechat or Paypal down here: