<aside> 💸 Quantitive Researcher

</aside>

<aside> 🎓 Ph.D. Student at University of Rochester

</aside>

<aside> 📧 Email: i@[domain].me, where [domain] is wanzy.

</aside>

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/55e36aeb-94ba-4c2d-a1ca-0c07c52309ba/octcat_paddingsmall.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/55e36aeb-94ba-4c2d-a1ca-0c07c52309ba/octcat_paddingsmall.png" width="40px" /> Github: wanzysky

</aside>

Home

Research

Events

Blogs

I am a Ph.D. student at the University of Rochester, advised by Prof. Jiebo Luo, and a quantitive researcher at JQ Investments. Previously I worked as an algorithm researcher at Megvii since late 2017 to December 2020, leading the R&D of scene text comprehension algorithms in Face++/FaceID. My research interest lies in computer vision and deep learning. I received my B.S. degree in Software Engineering of Beihang University, 2016. My detailed CV is available here.

Research

Cloud2Sketch: Augmenting Clouds with Imaginary Sketches

Zhaoyi Wan, Dejia Xu, Zhangyang Wang, Jian Wang, and Jiebo Luo.

30th ACM International Conference on Multimedia (ACM MM).

Project Page / Code / Paper

Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion

Minghui Liao, Zhisheng Zou, Zhaoyi Wan, Cong Yao, and X Bai.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Paper Code

SparseDet: Towards End-to-End 3D Object Detection

Jianhong Han, Zhaoyi Wan, Zhe Liu, Jie Feng, and Bingfeng Zhou.

17th International Conference on Computer Vision Theory and Applications. (Best Student Paper Award)

Facial Attribute Transformers for Precise and Robust Makeup Transfer

Zhaoyi Wan, Haoran Chen, Wentao Jiang, Cong Yao, and Jiebo Luo.

IEEE Winter Conference of Applications on Computer Vision (WACV).

Paper

Slender Object Detection: Diagnoses and Improvements

Zhaoyi Wan, Yimin Chen, Sutao Deng, Cong Yao, and Jiebo Luo.

Paper Code

On Vocabulary Reliance in Scene Text Recognition