Embedded Files
About
About
I am pursuing doctoral degree (Medical Image Analysis) at Johns Hopkins University. I received my M.S. (Computer Vision track) at University of Michigan in 2021. I completed my B.E. degree in ECE (Automation) at Southeast University in 2019. My research interests lie primarily in the area of medical image analysis, and applied machine learning.
News
News
[Apr. 2023] Our work on motion estimation in tagged-MRI has been accepted to MIDL2023 as an oral. See you in Nashville.
[Feb. 2023] Our work won the Best Student Paper Runner-Up Award in SPIE Medical Imaging.
[Mar. 2022] Our work on self-supervised motion estimation has been accepted by CVPR'22. See you in New Orleans.
[Jan. 2022] Our work on CT-based aortic registration has been accepted by journal: Medical Physics.
[Oct. 2021] Our work on deep-learning based landmark localization has been accepted by SPIE Medical Imaging 2022. See you in San Deigo.
[Aug. 2021] Our paper (me as 2nd author) has been accepted by journal: Radiology.
Archived News
Archived News
[Jan. 2021] I am offered with MDP (Multidisciplinary Design Program) High Impact Fellowship by UMich.
[Oct. 2020] Two papers have been accepted by SPIE Medical Imaging 2021. See you in San Diego online due to COVID-19.
[Oct. 2019] One Paper has been accepted by 2019 IEEE International Conference on Bioinformatics and Biomedicine, Nov.18-21, San Diego, USA.
[July. 2019] I graduated as "Outstanding Graduate" from Southeast University. (supervised by Prof. Siyu Xia)
[Mar. 2018] I won Canada Mitacs scholarship. I will visit Concordia University (Montreal)
Publications
Publications
Zhangxing Bian, Allan Jabri, Alexei A Efros, Andrew Owens, "Learning Pixel Trajectories with Multiscale Contrastive Random Walks", CVPR 2022. [webpage]
Zhangxing Bian, Jiayang Zhong, Jeffrey Dominic, Gary E Christensen, Charles R Hatt, Nicholas S Burris, "Validation of a robust method for quantification of three‐dimensional growth of the thoracic aorta using deformable image registration", Medical Physics 2022.
Zhangxing Bian, Jiayang Zhong, Yanglong Lu, Chuck R Hatt, Nicholas S Burris, "LitCall: learning implicit topology for CNN-based aortic landmark localization", SPIE-MI 2022. [paper] [talk]
Zhangxing Bian, Jiayang Zhong, Charles R. Hatt c, Nicholas S. Burris, "A Deformable Image Registration Based Method to Assess Directionality of Thoracic Aortic Aneurysm Growth", SPIE-MI 2021. [paper][poster][talk]
Zhangxing Bian, Siyu Xia, Chao Xia, Ming Shao, “Weakly Supervised Vitiligo Segmentation in Skin Image through Saliency Propagation” , 2019 IEEE International Conference on Bioinformatics and Biomedicine, Nov.18-21, 2019, San Diego, USA. [slides] [talk] [paper]
Nicholas S Burris, Zhangxing Bian, Jeffrey Dominic, Jianyang Zhong, Ignas B Houben, Theodorus MJ van Bakel, Himanshu J Patel, Brian D Ross, Gary E Christensen, Charles R Hatt, "Vascular Deformation Mapping for CT Surveillance of Thoracic Aortic Aneurysm Growth", Radiology, 2022.
Jiayang Zhong, Zhangxing Bian, Charles R. Hatt c, Nicholas S. Burris, "Multi-part segmentation of the thoracic aorta using an attention-gated U-Net", SPIE Medical Imaging 2021. [paper]
Unpublished
Unpublished
Haozhu Wang, Zhangxing Bian, Rui Guo, Anthony Liang, Mingyu Yang, “Drift-Aware Predictive Coding for Adaptation in Changing Environments”, [report]
Zhangxing Bian*, Rui Guo*, Wallace Sui, Peihan Dou, Yupeng Ma, "Estimate 6D Pose from Single RGB Image with Backpropagatable PnP", [technical report]
Main Projects
Main Projects
Aorta: Image Registration and Deformation Analysis
Aorta: Image Registration and Deformation Analysis
Goal: Measure the deformable change of aorta over time.
Achievement: Propose a novel method to decompose the Jacobian into directional components; Apply the DL-based segmentation on CT.
Keywords: Deformable Registration, Directional Jacobian Component
>>> See more results: [paper][overview]
Weakly-supervised Segmentation in Skin Images
Weakly-supervised Segmentation in Skin Images
Goal: Perform weak-supervised segmentation for skin lesion images (vitiligo).
Achievement: Propose a dataset; Propose a weak-supervised segmentation for vitiligo images, and achieves IoU at 71.4 which is comparable with SOTA ( e.g. PRM, SEC-CRF.)
Keywords: CNN, Saliency Propagation, Weakly-supervised Segmentation
Side Projects
Side Projects
More about these side projects (click to expand)
More about these side projects (click to expand)
Estimate 6D Pose from Single RGB Image with Backpropagatable PnP (Technical Report)
Estimate 6D Pose from Single RGB Image with Backpropagatable PnP (Technical Report)
Goal: Estimate 6D pose from single RGB image.
Achievement: Our method achieves BOP score at 61.4 on YCB-V using only RGB images, which is 10.6 higher than original Pix2Pose’s performance.
Keywords: 6D pose, PnP, U-net, single RGB
>>> More: [report]
Highlight Removal in Facial Images
Highlight Removal in Facial Images
Goal: Remove specular highlight in facial images
Achievement: Our method generates highlight-free images with high-quality details and fewer artifacts by adopting CGAN and multi-scale discriminators.
Keywords: Highlight Removal, Facial Image, CGAN
Achievement: Improved the tracking robustness for planar object in the AR application, compared to AR-Toolkit framework; Developed an AR game based on improved framework.
Keywords: AR, Planar Object Tracking
Achievement: Implemented Double/Dueling DQN algorithm and Prioritised Experience method from scratch using Pytorch; and outperformed original Double DQN paper.
Keywords: Reinforcement Learning, Atari, Deep Q Learning ...
>>> See more results: [Github repo]
Synopsis: Keyframe Extraction and video condensation
Synopsis: Keyframe Extraction and video condensation
Achievement: Second Prize of National-level SRTP*; Implement a video condensation system from scratch using C++; Designed a novel motion-volume based keyframe extraction method;
* Student Research Training ProgramKeyword: K-means, Motion-volume, Graph-cut
RMDS COVID-19 Challenge, 2020
Project Goal: Apply LSTM and LR models for spatio-temporal COVID-19 risk prediction.
Keywords: COVID-19 risk score, LSTM, Linear Regression.
>>> See more results: [report]
Education
Education
University of Michigan, Ann Arbor, USA
University of Michigan, Ann Arbor, USA
M.S. in Electrical & Computer Engineering with track in Computer Vision| 2019-2021
GPA: 4.0/ 4.0
Main Coursework:
Probability and Random Processes by Sandeep Pradhan (EECS 501)
Deep Learning in Computer Vision by Justin Johnson (EECS 598-005)
Matrix Methods for Signal Processing & Machine Learning by Jeff Fessler (EECS 551)
Computer Vision by Andrew Owens (EECS 504)
Machine Learning by Honglak Lee (EECS545)
Advanced Computer Vision by David Fouhey (EECS 542)
Southeast University, Nanjing, China
Southeast University, Nanjing, China
(Ranked at 21 globally in Automation & Control according to ARWU.)
B.E. in Automation with concentration in Pattern Recognition and Intelligent Information| 2015.07-2019.06
Major GPA: 3.91/4.0 | GPA: 3.88/4.0
Main Coursework:
Math & Theory: Linear Algebra; Calculus; Numerical Computing Methods; Signal and Systems; Probability Theory; Automatic Control Theory; Discrete Math; .
Hardware: Fundamentals of Circuit; Digital and Logic Circuit; Analog Electronic Circuit; Microcomputer Systems and Interfaces; Embedded System.
Software: Data Structure; C++/Python programming; Database Fundamentals; Computer Networks.
Concentration courses: Data Mining; Statistic Analysis; Digital Signal Processing; Digital Image Processing; Introduction to Artificial IntelligenceI; Machine Learning; Operational Research and Optimization.
Academic Service
Academic Service
Reviewer for International Journals and Conferences
Reviewer for International Journals and Conferences
Image and Vision Computing (IVC) || ACM Multimedia (ACM-MM) || IEEE International Conference on Machine Learning and Applications (IEEE ICMLA)
Page updated
Report abuse