Zhihua Liu

Greetings! My name is Zhihua Liu (Chinese: 刘志华). I am a Ph.D. student supervised by Prof. Huiyu Zhou at the Biomedical Image Processing Lab (BIPL), School of Computing and Mathematical Sciences, University of Leicester. I am funded by the Graduate Teaching Assistantship (GTA), College of Science and Engineering, University of Leicester.

Previously, I served as an algorithm engineer in JD Logistics, JD.com. I received my M.Sc. in Artificial Intelligence from the University of Edinburgh in 2016, my B.Eng. in Internet of Things from University of Science and Technology Beijing in 2015. I spent my undergraduate final year at the School of Computing in University of Dundee, supervised by Prof. Stephen McKenna, Dr. Sebastian Stein and Prof. Jianguo Zhang.

I am looking for research intern (also visiting student) position for year 2024, please find related links below and feel free to contact / chat! (I am looking forward to your feedback and suggestions!!)

CV  /  Research Statement  /  Google Scholar  /  Twitter  /  Github

Research Intern Interests: Medical Shape Analysis > Visual Motion Modeling > Other Medical Imaging > Other Vision >>> LLM (I am not a LLM guy. Never trained a LLM before. I do not want to lie things like I am a quick learner and I can learn LLM in days.)

To be honest, I do not have specific salary expectations, but I do have preferences regarding the research topic and quality. If you have time, we can chat this further. It's particularly relevant to my situation, considering that I come from an under-represented research group (I have a "theory" on this called "The LASSO Way ⚽").

Email: ZL208 at leicester<dot>ac<dot>uk

profile photo
Frameless London, 2023
News
  • Jan 2023: Check our recent manuscript of LSDM! Effectively minimize ultrasound landmark tracking position margin using long-short diffeomorphic motion with high generalization capability.
  • Mar 2022: Two co-authored paper has been accepted by IEEE Trans. on Neural Networks and Learning Systems and IEEE Trans. on Affective Computing respectively.
  • Nov 2021: We have finished the extensive revision on "Deep Learning based Brain Tumor Segmentation: A Survey" and opensouced the github repo.
  • Oct 2021: It is a great honor for me to invite Dr.Yannis Kalantidis from NAVER LABS Europe to give a CMS research seminar.
  • July 2021: I am very honored to be selected to participate in The PRAIRIE / MIAI Artificial Intelligence Summer School (P.A.I.S.S.) organized by INRIA and the institutes PRAIRIE and MIAI.
  • Mar 2021: 1 paper has been accepted by IEEE Trans. on Medical Imaging.
  • July 2020: I am very honored to be selected to participate in The Medical Image Computing Summer School (MedICSS) at University College London (UCL) London, United Kingdom.
Research

My research is focusing on computer vision and machine learning, especially in medical image analysis, unsupervised learning and deep learning.

Boundary_png LSDM: Long-Short Diffeomorphic Motion for Weakly-Supervised Ultrasound Landmark Tracking
Zhihua Liu, Bin Yang, Yan Shen, Xuejun Ni, Sotirios Tsaftaris, Huiyu Zhou
arXiv, 2023
arXiv / Poster

Accurate tracking of an anatomical landmark over time has been of high interests for disease assessment such as minimally invasive surgery and tumor radiation therapy. In this paper, we propose a long-short diffeomorphic motion network, which is a multi-task framework with a learnable deformation prior to search for the plausible deformation of landmark.

Boundary_png Deep Learning Based Brain Tumor Segmentation: A Survey
Zhihua Liu, Lei Tong, Zheheng Jiang, Long Chen, Feixiang Zhou, Qianni Zhang, Xiangrong Zhang, Yaochu Jin, Huiyu Zhou
Complex & Intelligent Systems, 2022
arXiv / code

Considering stateof-the-art technologies and their performance, the purpose of this paper is to provide a comprehensive survey of recently developed deep learning based brain tumor segmentation techniques.

Boundary_png Detecting and Tracking of Multiple Mice Using Part Proposal Networks
Zheheng Jiang, Zhihua Liu, Long Chen, Lei Tong, Xiangrong Zhang, Xiangyuan Lan, Danny Crookes, Ming-Hsuan Yang, Huiyu Zhou
IEEE Trans. on Neural Networks and Learning Systems, 2022
arXiv / code

A novel method to continuously track several mice and individual parts without requiring any specific tagging.

Boundary_png Cost-sensitive Boosting Pruning Trees for depression detection on Twitter
Lei Tong, Zhihua Liu, Zheheng Jiang, Feixiang Zhou, Long Chen, Jialin Lyu, Xiangrong Zhang, Qianni Zhang, Abdul Sadka, Yinhai Wang, Ling Li, Huiyu Zhou
IEEE Trans. on Affective Computing, 2022
arXiv / code / Media

A novel classifier, namely, Cost-sensitive Boosting Pruning Trees (CBPT), which demonstrates a strong classification ability on two publicly accessible Twitter depression detection datasets..

Boundary_png CANet: Context Aware Network for Brain Glioma Segmentation
Zhihua Liu, Lei Tong, Long Chen, Feixiang Zhou, Zheheng Jiang, Qianni Zhang, Yinhai Wang, Caifeng Shan, Ling Li, Huiyu Zhou
IEEE Trans. on Medical Imaging, 2021
arXiv / code

A novel approach named Context-Aware Network (CANet) for brain glioma segmentation.

Boundary_png Structured Context Enhancement Network for Mouse Pose Estimation
Feixiang Zhou, Zheheng Jiang, Zhihua Liu, Fang Chen, Long Chen, Lei Tong, Zhile Yang, Haikuan Wang, Minrui Fei, Ling Li, Huiyu Zhou
IEEE Trans. on Circuits and Systems for Video Technology, 2021
arXiv / code

A novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GMSCENet), quantifies mouse pose estimation from videos.

Boundary_png MPhil Thesis: Medical Image Analysis using Deep Relational Learning
Zhihua Liu
MPhil Thesis, 2020
arXiv / Poster

Benefited from deep learning techniques, remarkable progress has been made within the medical image analysis area in recent years. However, it is very challenging to fully utilize the relational information (the relationship between tissues or organs or images) within the deep neural network architecture. Thus in this thesis, we propose two novel solutions to this problem called implicit and explicit deep relational learning. We generalize these two paradigms of deep relational learning into different solutions and evaluate them on various medical image analysis tasks.

Boundary_png Perceptual underwater image enhancement with deep learning and physical priors
Long Chen, Zheheng Jiang, Lei Tong, Zhihua Liu, Aite Zhao, Qianni Zhang, Junyu Dong, Huiyu Zhou
IEEE Trans. on Circuits and Systems for Video Technology, 2020
arXiv / code

In this paper, we propose two perceptual enhancement models, each of which uses a deep enhancement model with a detection perceptor. The detection perceptor provides coherent information in the form of gradients to the enhancement model, guiding the enhancement model to generate patch level visually pleasing images or detection favourable images.

Boundary_png Underwater object detection using Invert Multi-Class Adaboost with deep learning
Long Chen, Zhihua Liu, Lei Tong, Zheheng Jiang, Shengke Wang, Junyu Dong, Huiyu Zhou
International Joint Conference on Neural Networks (IJCNN), 2020
arXiv / code

Sample-WeIghted hyPEr Network (SWIPENet) for underwater small object detection.

Boundary_png BEng Thesis: Multi-Classes Training and Testing in Food Preparation Recognition Tasks
Zhihua Liu
BEng Thesis, 2015
PDF / Poster / Dataset

The recognition of human action is widely applied in video surveillance, virtual reality and in some human-computer interaction areas such as user experience designing tasks. Pattern recognition becomes a hot topic in the field of computer vision. In this report, I summarize human behavior recognition problem as a problem of acquiring computing data through motion detection and symbolic acting information. Then extract and understand the behavior of the action features to achieve classification target. On this basis, I review the moving object detection, motion feature extraction and movement characteristics to understand the technical analysis, the correlation method classification, and discuss the difficulties and research directions of this project.

Projects
Smart distribution grid: a market driven approach for the next generation of advanced operation models and services (DOMINOES)

December 2020-June 2021
3D Reconstruction and Video Mosaicking with Applications to Fetoscopy

July 2020

Group project during UCL Medical Image Computing Summer School (MedICSS) 2020.

Presentation Slide / Related Paper / Related Dataset
Automated analysis of housing construction progress through remote sensing

April 2020-April 2021

Collabrative work with Stevenson Astrosat Ltd.
Object detection in 3D point cloud

Jan 2017-Sep 2018

Industrial research and engineering work at JD Logistics, JD.com.Focused on vehicle, bicycle and pedestrian detection from 3D point cloud generated from LiDAR. Also focused on engineering work within point cloud data storge, data retrival, data access authentication development.
Teaching Assistant
2020-2023
CO1104 Computer Architecture
CO3102 Mobile and Web Applications
CO4105 Advanced C++ Programming

CO3002 Analysis and Design of Algorithms
CO3099 Foundations of Cybersecurity
CO1109 Business and Financial Computing
CO7218 Financial Services Information Systems
2019-2020
FS0023 STEM Foundation Year Lab-Physics
CO3091 Computational Intelligence and Software Engineering
Others
I like traveling and photography. Here is my instagram.

I also like sports, especially football ⚽ and table tennis 🏓. I started to receive professional table tennis training from the age of 5, got into the school team, and gave up training in high school because of the college entrance examination.

Website template is from Jon Barron.