Hangzhou Dianzi University, China
Prof. Jinkai Zheng is a Distinguished Associate Researcher at Hangzhou Dianzi University, Director of the Scientific Research Management Department at the Hangzhou Dianzi University Lishui Research Institute, and an active member of the Multimedia and Biometric Recognition Professional Committees of the China Society of Image and Graphics. His research focuses on artificial intelligence, computer vision, and multimedia analysis, with a particular emphasis on gait recognition and human-centered intelligent analysis. He has published over 40 academic documents, including multiple first-author and corresponding-author papers in top-tier venues such as CVPR, ACM Multimedia, and IEEE Transactions on Multimedia, accumulating more than 900 citations with an h-index of 16 (Google Scholar, 2025). His contributions include the Gait3D dataset, now a widely adopted benchmark by over 300 prestigious institutions worldwide, including Columbia University, University of Pennsylvania, Johns Hopkins University, and NUS. He has received notable accolades, such as the Special Prize of the 2024 Wu Wenjun Artificial Intelligence Science and Technology Progress Award, the Outstanding Paper Award at the 2023 CSIG Youth Scientists Conference, and the Best Paper Award-Honorable Mention at IEEE ISCAS 2021. With four authorized invention patents, long-term service as a reviewer for leading journals and conferences, and significant participation in national R&D projects, Prof. Zheng has become a recognized young leader in advancing AI-driven multimedia understanding.
Profiles: Scopus | Orcid | Google Scholar
Featured Publications
Zheng, J., Liu, X., Gu, X., Sun, Y., Gan, C., Zhang, J., Liu, W., & Yan, C. (2022). Gait recognition in the wild with multi-hop temporal switch. Proceedings of the 30th ACM International Conference on Multimedia, 6136–6145.
Zheng, J., Liu, X., Wang, S., Wang, L., Yan, C., & Liu, W. (2023). Parsing is all you need for accurate gait recognition in the wild. Proceedings of the 31st ACM International Conference on Multimedia, 116–124.
Zheng, J., Liu, X., Yan, C., Zhang, J., Liu, W., Zhang, X., & Mei, T. (2021). Trand: Transferable neighborhood discovery for unsupervised cross-domain gait recognition. 2021 IEEE International Symposium on Circuits and Systems (ISCAS), 1–5. IEEE.
Zheng, J., Liu, X., Zhang, B., Yan, C., Zhang, J., Liu, W., & Zhang, Y. (2024). It takes two: Accurate gait recognition in the wild via cross-granularity alignment. Proceedings of the 32nd ACM International Conference on Multimedia, 8786–8794.
Yuan, S., Zheng, J., Li, X., Sun, Y., Li, W., Gao, R., Omar, M. H., & Zhang, J. (2025). Noisy label learning for gait recognition in the wild. Electronics, 14(19), 3752.
Zhang, S., Zheng, J., Zhu, S., & Yan, C. (2025). TrackletGait: A robust framework for gait recognition in the wild. arXiv preprint arXiv:2508.02143.
Zheng, J., Liu, X., Liu, W., He, L., Yan, C., & Mei, T. (n.d.). Supplementary material for “Gait recognition in the wild with dense 3D representations and a benchmark.”