Now I am a software engineer at Google, developing deep learning models for computer vision tasks. Part of my work is open-sourced at TensorFlow Model Garden.
Previously, I was a Ph.D. student in Computer Science from 2017 tp 2022 at the University of Texas at Arlington, USA. I have received my Ph.D. degree in 2022. My supervisor is Dr. Junzhou Huang.
I received my master's degree from the Institute of Automation, Chinese Academy of Sciences(CASIA) in 2017. I worked on 3D computer vision for my master in Robot Vision Group, National Laboratory of Pattern Recognition(NLPR). In 2014, I got my bachelor's degree from the Huazhong University of Science and Technology(HUST).
Email: chaochao.yan at mavs.uta.edu
Worked with Shun Miao and Adam Harrison on Chest X-rays abnormalities classification and lesions localization using weakly supervised deep learning models.
Ads images classification with deep convolutional neural networks.
Working on mobile object detection with Marco Fornoni, Yin Cui, Andrew Howard, and Boqing Gong at Google Research, remotely from Texas due to the COVID-19.
Working on universal lesion detection in CT volume with Ke Yan, Youbao Tang, and Jinzheng Cai at PAII, remotely from Texas due to the COVID-19.
May 2020. We propose a template-free deep learning framework for the retrosynthesis prediction, which is a key component of drug discovery. The proposed model achieves the state-of-the-art retrosynthesis performance and scales well to the large real-world dataset.
June 2018. We propose a weakly-supervised deep learning framework for classifying common thoracic diseases as well as localizing suspicious lesion regions on chest X-rays. The comprehensive experiments are performed on ChestX-ray14 dataset. The proposed model achieves 0.832 in average AUC score, which is the new state-of-the-art.
Master thesis: Mobile 6-DOF Localization Technique for Outdoor Scene.