Haidong Zhu

I am a Ph.D. student in the Computer Science Department at the University of Southern California. I received my Bachelor's Degree from the Department of Electronic Engineering, Tsinghua University in the year of 2019. In summer 2019, I was an visiting undergraduate research assistant at Visual Computing Group. I'm working as a RA/TA in USC IRIS Computer Vision Lab, under the supervision of Prof. Ram Nevatia.

My research interests lies at computer vision and deep learning, especially 3D vision, multi-modal analysis, weakly and self-supervised learning method.

Email   /    CV   /    Github   /    Google Scholar

Education
University of Southern California, LA, USA
Ph.D. • Aug. 2019 to Jun. 2024 (expected)
Department of Computer Science
Tsinghua University, Beijing, China
B.Eng. • Sep. 2015 to Jul. 2019
Department of Electronic Engineering
Research Experiences
IRIS Computer Vision Lab, University of Southern California, USA
Research Assistant • Aug. 2019 to present
Advisors: Professor Ram Nevatia
Visual Computing Group, Harvard University, USA
Undergraduate Research Intern • July. 2018 to Sept. 2018
Advisors: Professor Hanspeter Pfister
Multimedia Signal and Intelligent Information Processing Laboratory, Tsinghua University, China
Research Assistant • Nov. 2018 to Jun. 2019
Advisors: Professor Ji Wu

i-Vision Group, Tsinghua University, China
Research Assistant • Feb. 2018 to Apr. 2019
Advisors: Assoc. Professor Jiwen Lu

Information Cognition & Intelligent System Lab, Tsinghua University, China
Research Assistant • May 2017 to Feb. 2018
Advisors: Assoc. Professor Jiansheng Chen
Manuscripts
Unsupervised 3D Feature Learning by Point Cloud Completion
Yueqi Duan, Haidong Zhu, Chaojian Li, Jiwen Lu, and Jie Zhou
Under review
PARR: Predicate Analysis for Referring Relationships
Chuanzi He, Haidong Zhu, Jiyang Gao, Kan Chen, and Ram Nevatia
Under review
Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation
Haidong Zhu, Jialin Shi, and Ji Wu
In Proceedings of the International Conf. on Medical Image Computing and Computer Assisted Intervention (MICCAI), LNCS 11769, pp. 576-584, 2019.
Biologically-Constrained Graphs for Global Connectomics Reconstruction
Brian Matejek, Daniel Haehn, Haidong Zhu, Donglai Wei, Toufiq Parag, and Hanspeter Pfister
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2089-2098, 2019.
Selected Projects
Deep Learning Based Target Delineation System
• Bachelor's thesis, Tsinghua University, 2019.
Structural Relational Reasoning for Point Clouds
• Introduced structural relational network (SRN) for reasoning.
• Improved the results on public point cloud datasets.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 949-958, 2019.
Online Big Data Face Recognition System
• Real time face recognition with data from Internet.
• Big data management policy for renewing database.
• Predicting relationship between the people in the image.
Visual-audio Similarity Evaluation System
• Evaluating similarity between given audio and visual fragments.
• Sequence feature extraction and similarity evaluation.
Competition & Lecture Management System
• Lecture management system with wechat and website version.
• Organizing information according to user's habit and need.

Website source from Jon Barron and Xingyuan Sun.