Cong Wu
About Me
I’m currently a Lecturer at the School of Artificial Intelligence and Computer Science, Jiangnan University. I received my Ph.D. degree from Jiangnan University in 2024 under the supervision of Prof. Xiao-Jun Wu and Prof. Josef Kittler, and Bachelor degree from Jiangnan University in 2018. I was a visiting Ph.D. student at the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom, from 2022 to 2023.
I am looking for motivated master’s students to join my group in Fall 2027. Current research topics mainly include Video/Motion Understanding and Generation, Representation Learning, Trustworthy Artificial Intelligence. Feel free to contact me with a brief introduction of your background, research interests, and CV.
News
- [Sep. 2026] We won the second and third place in ChaLearn UDIVA-HHOI Challenge @ ECCV 2026! Congrats, Linze.
- [Jul. 2026] One paper about Self-Superivised 3D Human Action Recognition is accepted to TPAMI!
- [Jun. 2026] One paper about Zero-Shot Skeleton-Based Action Recognition is accepted to ECCV 2026! Congrats, Xuan.
- [Jun. 2025] Our paper about Human Action Recognition is accepted to ICCV 2025! Congrats, Youwei.
- [Sep. 2024] We won the second place in Temporal sound localisation of ECCV 2024 Perception Test Challenge! Congrats, Linze.
- [Jul. 2024] One paper about Few-Shot Action Recognition is accepted to ECCV 2024!
- [Dec. 2023] One paper about Self-Superivised 3D Human Action Recognition is accepted to AAAI 2024!
Selected Publications
Conference
- Cong Wu, Xiao-Jun Wu, Linze Li, Tianyang Xu, Zhenhua Feng, Josef Kittler. Efficient Few-Shot Action Recognition via Multi-level Post-reasoning. European Conference on Computer Vision, 2024. code
- Cong Wu, Xiao-Jun Wu, Josef Kittler, Tianyang Xu, Sara Ahmed, Muhammad Awais, Zhenhua Feng. Scd-net: Spatiotemporal clues disentanglement network for self-supervised skeleton-based action recognition. Proceedings of the AAAI conference on artificial intelligence, 2024. code
- Youwei Zhou, Tianyang Xu, Cong Wu, Xiaojun Wu, Josef Kittler. Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections. International Conference on Computer Vision, 2025. code
- Xuan Liu, Cong Wu, Wei Fang, Zhenhua Feng. Beyond Alignment: A Generative Matching Paradigm via Flow Matching for Zero-Shot Skeleton-based Action Recognition. European Conference on Computer Vision, 2026.
Journal
- Cong Wu, Tianyang Xu, Zhenhua Feng, Xiao-Jun Wu, Josef Kittler. Toward Stronger 3D Human Action Representation Learning Via Efficient Spatiotemporal Decoupling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. code
- Cong Wu, Tianyang Xu, Zhenhua Feng, Xiao-Jun Wu, Josef Kittler. Interactive Image-to-Video Transfer Learning. Neural Networks, 2025. code
- Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler. Adaptive Pooling with Dual-Stage Fusion for Skeleton-Based Action Recognition. Neural Networks, 2025. code
- Cong Wu, Xiao-Jun Wu, Tianyang Xu, Zhongwei Shen, Josef Kittler. Motion complement and temporal multifocusing for skeleton-based action recognition. IEEE transactions on circuits and systems for video technology, 2024. code
- Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler. Scene adaptive mechanism for action recognition. Computer Vision and Image Understanding, 2024. code
- Cong Wu, Xiao-Jun Wu, Josef Kittler. Graph2Net: Perceptually-Enriched Graph Learning for Skeleton-Based Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2021. code
- Jie Liu, Chongben Tao, Zhongwei Shen, Cong Wu, Tianyang Xu, Xizhao Luo, Feng Cao, Zhen Gao, Zufeng Zhang, Sai Xu. Dual Attention Focus Network for Few-Shot Skeleton-Based Action Recognition. Knowledge-Based Systems, 2025.
- Rui Wang, Jiayao Jin, Ziheng Chen, Cong Wu, Xiao-Jun Wu and Nicu Sebe. Structural Topology Refinement Network for Skeleton-Based Action Recognition). IEEE Transactions on Instrumentation and Measurement, 2025. code
- Zhongwei Shen, Xiao-Jun Wu, Hui Li, Tianyang Xu, Cong Wu. I know how you move: Explicit motion estimation for human action recognition. IEEE Transactions on Multimedia, 2022. code
(You can also find my publication lists on my Google Scholar.)
Awards
- 1st-Place, Multi-Modal Video Reasoning and Analyzing Competition-Skeleton-based Action Recognition (ICCV 2021)
- 1st-Place, Multi-Modal Video Reasoning and Analyzing Competition-Fisheye Video-based Action Recognition (ICCV 2021)
- 2nd-Place, AI City Challenge-Naturalistic Driving Action Recognition (CVPR 2023)
- 2nd-Place, Multi-Modal Video Reasoning and Analyzing Competition-Person Reidentification (ICME 2024)
- 2nd-Place, Multi-Modal Video Reasoning and Analyzing Competition-Skeleton-based Action Recognition (ICME 2024)
- 2nd-Place, The Second Perception Test Challenge-Temporal Sound Localisation (ECCV 2024)
- 2nd-Place, ChaLearn UDIVA-HHOI Challenge-Multimodal Exocentric Event Recognition (ECCV 2026)
- 3rd-Place, ChaLearn UDIVA-HHOI Challenge-Multimodal Exocentric Causal Event Grounding (ECCV 2026)
Education
- 2020.09-2024.06, Ph.D., Control Science and Engineering, Jiangnan University, China
- 2022.09-2023.09, Visiting Ph.D., University of Surrey, United Kingdom
- 2018.09-2020.06, M.E., Computer Science and Technology, Jiangnan University, China
- 2014.09-2018.06, B.S., Information and Computing Science, Jiangnan University, China
Teaching
- Data Visualization (2025 Spring)
- Freshman Seminar (Artificial Intelligence Major) (2025 Spring; 2026 Spring)
- Comprehensive Practice in Artificial Intelligence (2025 Spring; 2026 Spring)
- Pattern Recognition and Machine Learning (2026 Spring)
- Python Programming (2026 Fall)
- Computer Vision (2026 Fall)
Services
- Invited as Reviewer for conferences, including CVPR, ICCV, ECCV, AAAI, ACM MM, PRCV, BMVC, WACV, ACCV, etc.
- Invited as Reviewer for journals, including IEEE Trans, PR, Chinese Journal of Computers, etc.
Powered by Jekyll and Minimal Light theme.