Mr Lei Wang

Biography

Lei Wang is a Research Fellow with the School of Computing, ANU College of Engineering, Computing and Cybernetics under the supervision of Dr. Liang Zheng (ANU) and Prof. Tom Gedeon (Curtin University).

He is currently also a Computer Scientist with the Active Intelligence Australia Pty Ltd, Perth. He leads the research and development of commercial anomaly detection solutions, and the project has raised 1.2 million US dollars. Since then, he has been granted the Incentive Unit Award.

Since 2018, he has been a full-time Computer Vision Researcher with iCetana Pty Ltd. He was a Visiting Researcher in Machine Learning Research Group at Data61/CSIRO (former NICTA). He was also a Visiting Researcher with the Department of Computer Science and Software Engineering, UWA.

Before starting his PhD at ANU and Data61/CSIRO, he has been offered a number of competitive full PhD scholarships including ARC Industrial Transformation Training Centre Scholarship, UWA International Fee Scholarship, University Postgraduate Award, Data61 PhD Scholarship, Data61 Top-up Scholarship and ANU HDR Fee Remission Merit Scholarship.

He has published a large number of first-author papers during his PhD candidature in high quality venues (Rank A* conferences or journals with impact factor > 10.0) including CVPR, ICCV, ECCV, ACM MM, TPAMI and TIP under the supervision of Dr. Piotr Koniusz (Data61/CSIRO & ANU). He also received the Sang Uk Lee Best Student Paper Award from ACCV'22.

His research interests include action recognition in videos, anomaly detection, video image processing, one- and few-shot learning, deep learning, tensor learning and domain adaptation.

He is an IEEE Student Member and an ACM Student Member.

 

Education

  • Doctor of Philosophy - PhD, Computer Science, The Australian National University (22 July 2019 - present)
  • Master of Professional Engineering - MPE, Software Engineering, The University of Western Australia (Feb 2016 - March 2018)

 

Experience

Industry research

  • Active Intelligence Australia PTY Limited, Perth, Western Australia (WA)
    • Computer Scientist (contract), 5 July 2021 - present
    • Filed a patent [US provisional patent, SN 63/326,525]
    • Raised 1.2 million US dollars (~1.79 million Australian dollars)
    • Granted the Incentive Unit Award (09/09/2022-08/09/2032)
  • Ebenezer Technologies, Barranquilla, Colombia
    • Machine Learning Researcher, 28 Sep 2020 - 28 Jan 2021
    • Researched & delivered an anomaly detection system (Alice Guardian smart video surveillance)
  • iCetana Pty Ltd, Perth, WA
    • Computer Vision Research Intern (full-time), Research & Development (R&D), 2 July 2018 - 19 July 2019
    • Filed a provisional patent [AU Patent AU 2,019,900,316]
    • Machine Learning / Computer Vision Researcher (Casual Appointment, 20%), R&D, 22 July 2019 - 28 Sep 2020
    • Filed a provisional patent [AU Patent AU 2,019,903,775]

Academic research

  • The Australian National University (ANU)
    • Research Fellow (full-time), School of Computing, ANU College of Engineering, Computing and Cybernetics, 20 Feb 2023 - present
    • Grant: I am a Co-Investigator (Co-I) on 'Sharing early insights for more resilient communities'
  • The Commonwealth Scientific and Industrial Research Organisation (CSIRO)
    • Visiting Researcher, Machine Learning Research Group (MLRG), Data61/CSIRO (Floreat WA), 21 Sep 2018 - 19 July 2019
    • Postgraduate Research Student, MLRG, Data61/CSIRO (Acton & Black Mountain ACT), 22 July 2019 - present
    • One paper each published at CVPR, ICCV, ECCV, ACM-MM, TPAMI & TIP
    • Received the Sang Uk Lee Best Student Paper Award from ACCV’22
  • The University of Western Australia (UWA)
    • Visiting Researcher, CSSE/UWA, 10 Oct 2018 - 09 Oct 2019

 

Related Links

 

I would like to express my deepest appreciation to A/Prof. Du Huynh (UWA), Mr. Graeme Woods (now at FinClear), Dr. Moussa Reda Mansour (now at Alcoa), Dr. Piotr Koniusz (Data61/CSIRO & ANU) and Dr. Liang Zheng (ANU).

Research Interests

  • Action recognition
  • Anomaly detection
  • Video image processing
  • One- and few-shot learning
  • Deep learning
  • Tensor learning
  • Domain adaptation

Publications

3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
L Wang, P Koniusz
Computer Vision and Pattern Recognition (CVPR) [A*], 5620-5631
  2023
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition
L Wang, P Koniusz
Asian Conference on Computer Vision (ACCV) [B, oral, 4.9% acceptance rate, Best Student Paper Award], 307-326
  2022
Uncertainty-DTW for Time Series and Sequences
L Wang, P Koniusz
European Conference on Computer Vision (ECCV) [A*, oral, 2.7% acceptance rate], 176-195
  2022
Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition
Z Qin, Y Liu, P Ji, D Kim, L Wang, B McKay, S Anwar, T Gedeon
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) [IF: 14.255], (Early Access)
  2021
Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors
L Wang, P Koniusz
ACM International Conference on Multimedia (ACM-MM) [A*], 4324​-4333
  2021
Tensor Representations for Action Recognition
P Koniusz, L Wang, A Cherian
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 44 (2) [IF: 24.314], 648-665
  2020
A Comparative Review of Recent Kinect-based Action Recognition Algorithms
L Wang, DQ Huynh, P Koniusz
IEEE Transactions on Image Processing (TIP) 29 (1) [IF: 11.041], 15-28
  2020
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs
L Wang, P Koniusz, DQ Huynh
IEEE International Conference on Computer Vision (ICCV) [A*], 8698​​-8708
  2019
Loss Switching Fusion with Similarity Search for Video Classification
L Wang, DQ Huynh, MR Mansour
26th IEEE International Conference on Image Processing (ICIP) [B, industrial research+1 AU patent], 974-978
  2019

 

Patents

System and Method of Detecting Anomalies from Mass Data
L Wang
US patent (provisional, SN 63/326,525)
  2022
Method and System for Classifying Video Data
L Wang, G Woods
AU Patent AU 2,019,903,775
  2019
System and Method of Video Data Retrieval
L Wang, M Reda Mansour, G Woods
AU Patent AU 2,019,900,316
  2019

 

arXiv preprints

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve
L Wang, J Liu, P Koniusz
arXiv preprint arXiv:2112.12668 (an extended version has been accepted by ACCV'22 [oral])
  2021
High-order Tensor Pooling with Attention for Action Recognition
P Koniusz, L Wang, K Sun
arXiv preprint arXiv:2110.05216 (an extension of our TPAMI'20)
  2021

 

Master’s thesis

Analysis and Evaluation of Kinect-based Action Recognition Algorithms
L Wang
Master’s thesis, School of the Computer Science and Software Engineering, The University of Western Australia
  2017

 

Light cyan highlights the research works during my PhD candidature and light yellow highlights my industrial research works. My master's thesis is in misty rose color and other collaborative research works are in platinum color.

Paper Reviewing

I regularly review technical papers for the following journals, conferences & workshops.

I write high quality reviews for papers in my research interests, e.g., action recognition, anomaly detection, one- and few-shot learning, deep learning, tensor learning, domain adaptation, etc.

  • Journals:
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    • IEEE Transactions on Multimedia (T-MM), Pattern Recognition (PR), Computer Vision and Image Understanding (CVIU),
    • Neural Computing and Applications (NCAA), Journal of Visual Communication and Image Representation (JVCI), Signal, Image and Video Processing (SIVP),
    • The Visual Computer (TVCJ), IET Computer Vision, Electronics Letters
  • Conferences:
    • ICCV 2023, ICML 2023, CVPR 2023, ICLR 2023, AAAI 2023, NeurIPS 2022, CVPR 2022, AAAI 2022, ICML 2022, ECCV 2022 (outstanding reviewer),
    • BMVC 2022, BMVC 2021, BMVC 2020
    • IEEE Conference on Artificial Intelligence (IEEE CAI 2023)
  • Workshops:
    • Deep Vision Workshop (CVPR 2020),
    • Vision Datasets Understanding (1st VDU at CVPR 2022, 2nd VDU at CVPR 2023),
    • The AI City Challenge Workshop at CVPR 2023

 

Teaching

I am currently a research-intensive staff working on academic and industrial research projects, and I am not engaged in any teaching at this time.

Updated:  10 August 2021/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing