zhanggy0903[at]gmail[dot]com

Fudan University, Shanghai, China Advisor: Prof. Yan Qiu Chen

• PhD in Computer Science Sep. 2013 – Oct. 2018

• Thesis: Human Detection and Tracking with Depth Camera

University of Maryland, College Park, Maryland, United States Advisor: Prof. Larry S. Davis

• PhD Visiting in Computer Science Aug. 2016 – Sep. 2017

• Main Topic: Action Proposals and Detections, Style Transfer

East China University of Science and Technology, Shanghai, China

• BEng. in Computer Science Sep. 2009 – Jun. 2013

• Thesis: Plane Detection in Point Cloud with Kinect

• Computer Vision, Machine Learning, and Artificial Intelligence

Senior Researcher in Zhejiang Institution of Standardization

Hangzhou, Zhejiang, China Dec. 2020 – Present

Senior Research Fellow in Research Center for Healthcare Data Science

Zhejiang Lab, Hangzhou, Zhejiang, China Sep. 2020 – Nov. 2020

• Research on epilepsy detection.

Senior Research Scientist in R&D Group

PingAn Health Tech Center, Shanghai, China Nov. 2018 – Aug. 2020

• Integrated multi segmentation tasks (brain skulls, midlines, and brain sulcus) and classification (slice-based) task into one network as preprocessing for intracranial hemorrhage (ICH) detection on CT scans.

• Using partial convolution network as image inpainting to decrease the impact of hemorrhage to the segmentation results of brain lobes.

• Intracranial hemorrhage synthesis by partial convolution for data augmentation especially microbleeds.

• Working on abdominal segmentation (subcutaneous adipose tissue, muscle, visceral adipose tissue, visceral fat-free tissue and bone) of CT scans for body composition analysis.

• Subcortical segmentation on CT and MR images.

PhD Researcher in Computer Vision Lab Advisor: Dr. Larry S. Davis

University of Maryland, College Park, Maryland, United States Aug. 2016 – Sep. 2017

• Worked on temporal action localizations and action detections and presented Temporal Context Network (TCN) which outperformed state-of-the-art methods on ActivityNet and THUMOS14 dataset.

• Worked on style transfer system with Generative Adversarial Network (GAN). Utilized local and global discriminators to focus more on structure translation with hierarchical cycle GAN.

PhD Student in Computer Vision Lab Advisor: Dr. Yan Qiu Chen

Fudan University, Shanghai, China Sep. 2013 – Oct. 2018

• Integrated appearance, shape and motion information for RGB-D based human detection and head pose estimation. Proposed scale-invariant proposals for depth data, and built a multi-stream network with contextual ROI pooling.

• Utilized LSTM with multi-scale contextual information (color and depth CNN features) to promote human detection performance. Proposed a feature fusion strategy based on multi-LSTM networks.

• Proposed several effective methods of human detection and tracking in 3D space. Designed and implemented a cascade-structured method for mobile platform with extremely fast speed (80-140 fps on a single CPU core without GPU acceleration) and high accuracy.

Reviewed over 110 papers

• International Joint Conference on Artificial Intelligence (IJCAI)

• IEEE Transactions on Image Processing (TIP)

• Transactions on Multimedia (TMM)

• Computer Vision and Image Understanding (CVIU)

• Neurocomputing

• IEEE Signal Processing Letter (SPL)

• IEEE Access

• Sensors, Signal, Image and Video Processing (SIVP)

• Journal of Experimental & Theoretical Artificial Intelligence (JETAI)

• The Visual Computer(TVC)

• Journal of Electronic Imaging (JEI)

• 目标检测方法、装置及计算机可读存储介质（章古月） No. CN201911256499.1

• 图像分割方法、装置电子设备及计算机可读存储介质（章古月） No. CN202010431606.6

• 一种图像数据的生成方法及装置（卓柏全、周鑫，陈凯星、章古月） No. CN202010138075.1

• Chinese Government Scholarship of China Scholarship Council, 2016

• First Academic Scholarship in Fudan University, 2014, 2015, 2016

• Excellent School Graduation Thesis, 2013

• Excellent Graduate in East China University of Science and Technology, 2013