Dr. Xiaolin Zhu is a dynamic researcher and lecturer at the School of Automation and Electronic Information, Xiangtan University, China, specializing in advanced computer vision and deep learning. His scholarly pursuits focus on video understanding, group activity recognition, and multi-object tracking, with a strong commitment to developing intelligent algorithms that enhance human–machine perception and real-world visual interpretation. A prolific author, Dr. Zhu has published eight influential papers, including contributions in IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Circuits and Systems for Video Technology, and Expert Systems with Applications, one of which has garnered over one hundred citations. His innovative research has also led to five granted Chinese patents and one software copyright, demonstrating his skill in translating theoretical insights into practical applications. Dr. Zhu has collaborated with top institutions, including the University of Technology Sydney and Shanghai Jiao Tong University, advancing cross-disciplinary innovation and producing four notable joint publications. As a member of professional organizations such as IEEE, the Chinese Association of Automation, and the Chinese Institute of Electronics, he remains an active contributor to the scientific community. His recent comprehensive review on deep learning-based group activity recognition offers a refined taxonomy of methodologies from 2016 to 2024, mapping out the evolution of the field through supervision types, network architectures, modeling mechanisms, and input modalities. Recognized for his rigorous analytical approach and consistent academic excellence, Dr. Zhu represents the new generation of AI scholars pushing the boundaries of visual intelligence and autonomous systems, making significant strides toward the future of intelligent surveillance, human activity analysis, and video-based behavioral prediction.
Featured Publications
Zhang, X., & Zhu, X. (2019). Autonomous path tracking control of intelligent electric vehicles based on lane detection and optimal preview method.
Zhu, X., Zhou, Y., Wang, D., Ouyang, W., & Su, R. (2022). Mlst-former: Multi-level spatial-temporal transformer for group activity recognition.
Wu, D., Qu, Z. S., Guo, F. J., Zhu, X. L., & Wan, Q. (2019). Hybrid intelligent deep kernel incremental extreme learning machine based on differential evolution and multiple population grey wolf optimization methods.
Zhu, X., Wang, D., Li, J., Su, R., Wan, Q., & Zhou, Y. (2024). Dynamical attention hypergraph convolutional network for group activity recognition.
Zhu, X., Wang, D., & Zhou, Y. (2023). Hierarchical spatial-temporal transformer with motion trajectory for individual action and group activity recognition.