Cong Wu | Jiangnan University

About Me

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’m currently a Lecturer at the School of Artificial Intelligence and Computer Science, Jiangnan University.

The focus of my works is on deep learning approaches for Action Understanding. Particularly, I have focused on Video Understanding (Spatial Temporal Reasoning, Visual Scene Understanding), Vision-Language Modeling, Low Resource Learning (Transfer Learning/ Few-Shot Learning/ Self-Supervised Learning).

News

[Jul. 2024] Our paper about Few-Shot Action Recognition is accepted to ECCV 2024!
[Dec. 2023] Our paper about Self-Superivised 3D Human Action Recognition is accepted to AAAI 2024!

Publications

ECCV

Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning

Cong Wu, Xiao-Jun Wu, Linze Li, Tianyang Xu, Zhenhua Feng, Josef Kittler

European Conference on Computer Vision (ECCV), 2024.

Code Conditionally Accepted

AAAI

SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-Supervised Skeleton-Based Action Recognition

Cong Wu, Xiao-Jun Wu, Josef Kittler, Tianyang Xu, Sara Ahmed, Muhammad Awais, Zhenhua Feng

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024.

PDF Code

CVIU

Scene Adaptive Mechanism for Action Recognition

Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler

Computer Vision and Image Understanding (CVIU), 2024.

PDF Code

TCSVT

Motion Complement and Temporal Multifocusing for Skeleton-Based Action Recognition

Cong Wu, Xiao-Jun Wu, Tianyang Xu, Zhongwei Shen, Josef Kittler

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.

PDF Code

TMM

I Know How You Move: Explicit Motion Estimation for Human Action Recognition

Zhongwei Shen, Xiao-Jun Wu, Hui Li, Tianyang Xu, Cong Wu

IEEE Transactions on Multimedia (TMM), 2022.

PDF Code

TCSVT

Graph2Net: Perceptually-Enriched Graph Learning for Skeleton-Based Action Recognition

Cong Wu, Xiao-Jun Wu, Josef Kittler

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022.

PDF Code

IVC

Dynamic information enhancement for video classification

Rong-Chang Li, Xiao-Jun Wu, Cong Wu, Tianyang Xu, Josef Kittler

Image and Vision Computing (IVC), 2021.

PDF Code

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)

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