Hu Wang
Github : http://github.com/billhhh
CSDN Tech Blog : https://huwang.blog.csdn.net/
I am currently a research fellow at AIML, University of Adelaide, working with Prof. Gustavo Carneiro. I received my Ph.D. degree under the supervision of Prof. Chunhua Shen and Dr. Qi Wu. Before that I was honored to have worked with Prof. Steven Hoi at the Singapore Management University on Computer Vision research. In August 2023, our Imagendo project was awarded the Eureka Prize.

Google scholar

My research interests lie in Medical Machine Learning, Multi-modal Learning, Computer Vision, Security of AI Models, Reinforcement Learning, Machine Learning Theory, etc.

News

  • Mar 2024, a multi-document summarization paper has been accepted by WCCI-IJCNN 2024 Paper.
  • Mar 2024, a Prunning-based model privacy protection paper has been accepted by IEEE S&P 2024 Paper.
  • Feb 2024, an Image Quality Assessment for Transvaginal Ultrasound Scans paper has been accepted by ISBI 2024 Paper.
  • Nov 2023, a Human-Computer Interaction (HCI) with multi-modal learning paper has been accepted by AAAI 2024 Paper.
  • Aug 2023, a great pleasure to be awarded as the winner of Eureka Prize for Innovative Use of Technology Website.
  • Jul 2023, a Noisy Chest X-ray Classification paper has been accepted by ICCV 2023 Paper.
  • Jun 2023, a Multi-modal Learning with Missing Modality paper has been accepted by MICCAI 2023 Paper.
  • Jun 2023, a Multi-modal Learning with Missing Modality paper will be presented at CVPR 2023 Paper.
  • Apr 2023, a MRI and Ultrasound Image analysis paper has been accepted by ISBI 2023, and received *Best Oral Paper Award Paper.
  • Apr 2023, a MRI Image reconstruction with MAE paper has been accepted by EMBC 2023 Paper.
  • Apr 2023, a Robust Digital Watermarking survey paper has been accepted by IEEE Transactions on Computational Social Systems (TCSS) Paper.
  • Apr 2023, a Robust Digital Watermarking paper has been accepted by International Journal of Intelligent Systems (IJIS) Paper.
  • Sep 2022, a Multi-modal inference attack paper has been accepted by NeurIPS 2022 Paper.
  • Sep 2022, a Multi-document Summarization paper has been accepted by WCCI-IJCNN 2022 Paper.
  • Sep 2022, a Crowd Counting by Reinforcement Learning paper has been accepted by TNNLS Paper.
  • Jul 2022, a Multi-modal Uncertainty Measurement paper has been accepted by ECCV 2022 Paper.
  • Jul 2022, a Multi-document Summarization paper has been accepted by PACLIC 2022 Paper.
  • Apr 2022, a Medical Image Processing paper has been accepted by MICCAI 2022 Paper.
  • Mar 2022, a Multi-document Summarization Survey paper has been accepted by ACM Computing Survey Paper.
  • Nov 2021, a Model Quantization Image Super-Resolution paper has been published by ACM Multimedia 2021 Paper Video.
  • Nov 2021, a Traffic Optimisation with Reinforcement Learning paper has been published on IEEE Open Journal of Intelligent Transportation System Paper.
  • Apr 2021, a AI security paper has been accepted by ACISP-2021 Paper.
  • Apr 2021, a Real-world Image Super-Resolution paper has been published on arXiv.
  • Jun 2020, a Reinforcement Learning on Vision-and-Language Navigation paper has been accepted by ECCV 2020, Video.
  • Apr 2020, a Unsupervised Representation Learning paper has been accepted by IJCAI 2020, Video.
  • Jul 2019, a Medical Image Processing paper has been accepted by MICCAI 2019.
  • Mar 2018, an Online Tensor Decomposition paper has been accepted by ICACI 2018.

Books

    A Guide for Advanced C++ Programming. link.

Tutorials

Teaching

Awards

  • Eureka Prize for Innovative Use of Technology 2023.
  • Robinson Research Institute 2023 Travel Grant, Early Career Researcher Award.
  • The University of Adelaide Ph.D. Scolarship 2018.
  • Samsung Scolarship 2015.

Selected Publications

Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
H Wang, C Ma, J Zhang, Y Zhang, J Avery, L Hull, G Carneiro
Medical Image Computing and Computer-Assisted Intervention 2023 (MICCAI 2023)
[PDF] [Code]
(I would like to release the code, but due to IP restrictions of the Imagendo project, the code is not allowed to be released at this stage. If you would like to consult the code release date in the future, please contact the Imagendo IP Team.)
Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling
H Wang, Y Chen, C Ma, J Avery, L Hull, G Carneiro
Computer Vision and Pattern Recognition 2023 (CVPR 2023)
[PDF] [Code]
(I would like to release the code, but due to IP restrictions of the Imagendo project, the code is not allowed to be released at this stage. If you would like to consult the code release date in the future, please contact the Imagendo IP Team.)
Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction
H Wang, J Zhang, Y Chen, C Ma, J Avery, L Hull, G Carneiro
European Conference on Computer Vision 2022 (ECCV 2022)
[PDF] [Code]
(I would like to release the code, but due to IP restrictions of the Imagendo project, the code is not allowed to be released at this stage. If you would like to consult the code release date in the future, please contact the Imagendo IP Team.)
Fully Quantized Image Super-Resolution Networks
H Wang, P Chen, B Zhuang, C Shen
ACM Multimedia 2021 (ACMMM 2021)
[PDF] [Code]
Unsupervised Representation Learning by Predicting Random Distances
H Wang, G Pang, C Shen, C Ma
International Joint Conference on Artificial Intelligence 2021 (IJCAI 2020)
[PDF] [Code]
Soft expert reward learning for vision-and-language navigation
H Wang, Q Wu, C Shen
European Conference on Computer Vision 2020 (ECCV 2020)
[PDF]
Robust Watermarking Using Inverse Gradient Attention
H Zhang*, H Wang*, Y Li, Y Cao, C Shen
International Journal of Intelligent Systems (IJIS)
[PDF] [Code]
Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline
H Wang, H Chen, Q Wu, C Ma, Y Li, C Shen
IEEE Open Journal of Intelligent Transportation System (OJ-ITS)
[PDF] [Code]
Kernel Adversarial Learning for Real-world Image Super-resolution
H Wang, C Ma, J Zhang, G Carneiro
[PDF] [Code]
Multi-document Summarization via Deep Learning Techniques: A Survey
C Ma, WE Zhang, M Guo, H Wang, QZ Sheng
ACM Computing Survey
[PDF]
Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
Z Wang, O Byrnes, H Wang, R Sun, C Ma, H Chen, Q Wu, M Xue
IEEE Transactions on Computational Social Systems (TCSS)
[PDF]
Segment Beyond View: Handling Partially Missing Modality for Audio-Visual Semantic Segmentation
R Wu, H Wang, F Dayoub, H Chen
Association for the Advancement of Artificial Intelligence 2024 (AAAI 2024)
[PDF] [Code]
M4I: Multi-modal Models Membership Inference
P Hu, Z Wang, R Sun, H Wang, M Xue
Neural Information Processing Systems 2022 (NeurIPS 2022)
[PDF] [Code]
A Closer Look at Audio-Visual Semantic Segmentation
Y Chen, Y Liu, H Wang, F Liu, C Wang, G Carneiro
[PDF]
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Y Chen, F Liu, H Wang, C Wang, Y Tian, Y Liu, G Carneiro
International Conference on Computer Vision 2023 (ICCV 2023)
[PDF]
Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation
Y Chen, H Wang, C Wang, Y Tian, F Liu, Y Liu, M Elliott, D J. McCarthy, H Frazer, G Carneiro
Medical Image Computing and Computer Assisted Interventions 2022 (MICCAI 2022)
[PDF]
The Effectiveness of Self-supervised Pre-training for Multi-modal Endometriosis Classification
D Butler, H Wang, Y Zhang, M To, J Avery, L Hull, G Carneiro
International Conference of the IEEE Engineering in Medicine and Biology Society 2023 (EMBC 2023)
[PDF]
Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images
Y Zhang, H Wang, D Butler, M To, J Avery, L Hull, G Carneiro
International Symposium on Biomedical Imaging 2023 (ISBI 2023, *Best Oral Paper Award)
[PDF]
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
L Chen, H Wang, B Zi Hao Zhao, M Xue, H Qian
Information Security and Privacy 2021 (ACISP 2021)
[PDF] [Code]
Counting Crowd by Weighing Counts: A Sequential Decision-Making Perspective
H Lu, L Liu, H Wang, Z Cao
IEEE Transactions on Neural Networks and Learning Systems (TNNLS 2022).
[PDF] [Code]
Multi-label thoracic disease image classification with cross-attention networks
C Ma, H Wang, SCH Hoi
Medical Image Computing and Computer Assisted Interventions 2019 (MICCAI 2019)
[PDF]
Randomized online CP decomposition
C Ma, X Yang, H Wang
International Conference on Advanced Computational Intelligence 2018 (ICACI 2018)
[PDF]
A Graphical Programming System (similar to Lego EV3)
H Wang, L Qin, H Liang, Z Wu, Y Pan, H Han
Patents have been published
[PDF] [Patents]

Patents & Copyrights

  • “A Graphical Programming Multithreading Synchronization Method.” 1 June 2017. Patent (201710405733.7). Software
  • “A Visual Programming Control and Store System.” 30 November 2016. Patent (201611092887.7). Certificate
  • “Dual Mode Video Masked-men Detection Based on Statistical Characteristics.” 20 December 2015. Patent (201510971527.3).
  • “Masked-men Detection Based on Color Features.” 7 July 2015. Patent (201510451280.2).
  • “Intelligent online CP decomposition system”, 16 March 2018, Software copyright (2018SR263150)
  • “Intelligent Masked-Men Detection system.” 26 September 2014. Software copyright (2015SR035707).
  • “ACM/ICPC Online Judge.” 26 March 2014. Software copyright (2015SR035709).

Paper Review Services

TPAMI, CVPR, ECCV, KDD, AAAI, MICCAI, ACL, EMNLP, TNNLS, TIP, ACCV, ECML/PKDD, DICTA, ICIG

© Hu Wang