Publications
$^\dagger$: Corresponding author.
Journals
Feature Hallucination for Self-supervised Action Recognition L Wang$^\dagger$, P Koniusz NA | Under revision | 2024 |
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal‑Viewpoint Alignment L Wang$^\dagger$, J Liu, L Zheng, T Gedeon, P Koniusz International Journal of Computer Vision (IJCV), 1-32 | (IJCV special issue on our ACCV'22) [IF: 19.5] Code | 2024 |
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), 4783-4797 | [IF: 14.255] Code | 2021 |
Tensor Representations for Action Recognition P Koniusz, L Wang, A Cherian IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 44 (2), 648-665 | [IF: 24.314] | 2020 |
A Comparative Review of Recent Kinect-based Action Recognition Algorithms L Wang$^\dagger$, DQ Huynh, P Koniusz IEEE Transactions on Image Processing (TIP) 29 (1), 15-28 | [IF: 11.041] Dataset & Code | 2020 |
Conferences
Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion D Ding, L Wang$^\dagger$, L Zhu, T Gedeon, P Koniusz International Conference on Learning Representations (ICLR) | [A*] | 2025 |
TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps A Raj, L Wang$^\dagger$, T Gedeon IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) | [B] Code, Project website | 2025 |
Advancing Video Anomaly Detection: A Concise Review and a New Dataset L Zhu, L Wang$^\dagger$, A Raj, T Gedeon, C Chen NeurIPS 2024 Datasets and Benchmarks Track (NeurIPS D&B Track) | [A*] Code, Project website, Poster | 2024 |
Motion meets Attention: Video Motion Prompts Q Chen, L Wang$^\dagger$, P Koniusz, T Gedeon Asian Conference on Machine Learning (ACML) | [Long presentation, 26% overall acceptance rate, 5.67% for long presentations] Code, Project website, Poster | 2024 |
SATO: Stable Text-to-Motion Framework W Chen*, H Xiao*, E Zhang*, L Hu, L Wang, M Liu, C Chen ACM Multimedia (ACM-MM) (* denotes equal contribution.) | [A*] Code, Project website | 2024 |
Adaptive Multi-head Contrastive Learning L Wang$^\dagger$, P Koniusz, T Gedeon, L Zheng European Conference on Computer Vision (ECCV) | [A*] Code, Poster | 2024 |
Taylor Videos for Action Recognition L Wang$^\dagger$, X Yuan, T Gedeon, L Zheng International Conference on Machine Learning (ICML) | [A*] Code, Poster | 2024 |
High-order Tensor Pooling with Attention for Action Recognition L Wang, K Sun, P Koniusz IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 3885-3889 | (An extension of our TPAMI'20) [B, oral] Code (preprocessing) Appendix, Slides | 2023 |
Flow Dynamics Correction for Action Recognition L Wang, P Koniusz IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 3795-3799 | [B] Poster | 2023 |
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition L Wang, P Koniusz Computer Vision and Pattern Recognition (CVPR), 5620-5631 | [A*] Poster | 2023 |
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition L Wang, P Koniusz Asian Conference on Computer Vision (ACCV), 307-326 | [B, oral, 4.9% acceptance rate, Best Student Paper Award] Award certificate | 2022 |
Uncertainty-DTW for Time Series and Sequences L Wang, P Koniusz European Conference on Computer Vision (ECCV), 176-195 | [A*, oral, 2.7% acceptance rate] Code | 2022 |
Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors L Wang, P Koniusz ACM International Conference on Multimedia (ACM-MM), 4324-4333 | [A*] Code | 2021 |
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), 8698-8708 | [A*] | 2019 |
Loss Switching Fusion with Similarity Search for Video Classification L Wang, DQ Huynh, MR Mansour 26th IEEE International Conference on Image Processing (ICIP), 974-978 | [B, industrial research + 1 AU patent] Our dataset | 2019 |
Workshops
The Journey of Action Recognition X Ding, L Wang$^\dagger$ Companion Proceedings of the ACM Web Conference 2025 (WWW Companion '25) | Oral Code | 2025 |
Do Language Models Understand Time? X Ding, L Wang$^\dagger$ Companion Proceedings of the ACM Web Conference 2025 (WWW Companion '25) | Oral Code | 2025 |
Evolving Skeletons: Motion Dynamics in Action Recognition J Qiu, L Wang$^\dagger$ Companion Proceedings of the ACM Web Conference 2025 (WWW Companion '25) | Poster | 2025 |
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 |
Theses
Robust Human Action Modelling L Wang PhD thesis*, The Australian National University | Nov 2023 |
Analysis and Evaluation of Kinect-based Action Recognition Algorithms L Wang Master’s thesis, The University of Western Australia | Nov 2017 |
*: I would like to extend my heartfelt gratitude to three esteemed PhD thesis examiners, namely Dr. Lingqiao Liu (University of Adelaide) and Dr. Peng Wang (University of Electronic Science and Technology of China), as well as an anonymous examiner, for their invaluable insights, meticulous examination, and constructive feedback on my research work.
*: The 1st chapter of my thesis is an invited talk ("Action Recognition: Past, Present and Future") for 'The Next Generation of International Chinese Young Students Face to Face', Issue 21 of the International Cooperation and Exchange Program Series Activities at Harbin Institute of Technology (Shenzhen). Chapters 2 through 8 comprise published works presented at TIP'20, ICCV'19, ACMMM'21, TPAMI'20, CVPR'23, ECCV'22 (oral), and ACCV'22 (oral, recipient of the Best Student Paper Award). Chapter 9 provides a summary and outlines future work. Other works completed during my PhD, such as contributions to the IJCV special issue on ACCV'22 and presentations at ICASSP (x2, 1 oral), are not included in this thesis.
arXiv preprints
Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight X Ding, L Wang$^\dagger$ arXiv preprint arXiv:2412.18298 | Xi Ding, a Research Assistant with the Temporal Intelligence and Motion Extraction (TIME) Lab at ANU, contributed to this work. TIME Lab is a dynamic research team comprising master’s and honours students focused on advancing video processing and motion analysis. This research was conducted under the supervision of Lei Wang. [Code] | 2024 |
When Spatial meets Temporal in Action Recognition H Chen, L Wang$^\dagger$, Y Chen, T Gedeon, P Koniusz arXiv preprint arXiv:2411.15284 | Huilin Chen conducted this research under the supervision of Lei Wang for her final year honors research project at ANU. This work was supported by the National Computational Merit Allocation Scheme 2024 (NCMAS 2024), with computational resources provided by NCI Australia, an NCRIS-enabled capability supported by the Australian Government. | 2024 |
SignLLM: Sign Languages Production Large Language Models S Fang, L Wang, C Zheng, C Sui, M Zhao, Y Tian, C Chen arXiv preprint arxiv:2405.10718 | Research report. [Project website] | 2024 |
Optimizing Calibration by Gaining Aware of Prediction Correctness Y Liu, L Wang, Y Zou, J Zou, L Zheng arXiv preprint arXiv:2404.13016 | Research report. [Code] | 2024 |
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] and has been awarded the Sang Uk Lee Best Student Paper Award. The further extension of ACCV'22 has been accepted for publication by the IJCV special issue. | 2021 |
AI in Software Engineering: Case Studies and Prospects L Wang arXiv preprint arXiv:2309.15768 | Technical Report. The author conducted this work while enrolled as a master's student at UWA, specifically for the CITS5502 Software Processes unit in 2017. | 2017 |
Light cyan highlights the research works during my PhD candidature and light yellow highlights my industrial research works. My theses are in misty rose color and other collaborative research works are in platinum color. Last updated: 04/05/2024.