Dr. Xiao Li | School of Computer Science, Xidian University | China
Dr. Xiao Li is an accomplished researcher and Associate Professor at the School of Computer Science and Technology, Xidian University, Xi’an, China, where he also serves as a Master’s Supervisor. He obtained his Ph.D. in Computer Science from Xidian University in 2017. His research focuses on AI for Science, biomedical intelligent diagnosis, radar signal recognition, and cryptographic intelligence analysis, with a strong emphasis on advancing artificial intelligence for complex real-world applications. Dr. Li has made significant contributions to machine learning and signal processing, particularly through the development of pseudo-supervised contrastive learning frameworks and unknown sample generation algorithms that enhance classification accuracy for both known and unknown classes in open-set visual recognition. He has also designed innovative visual prototype generation networks and asymmetric variational autoencoder (VAE) models to improve cross-modal distribution alignment, yielding notable progress in RGB-D transfer learning and fine-grained image recognition. His interdisciplinary research extends to biomedical and engineering domains, including ECG-based cardiomyopathy detection, EEG-based emotion recognition, radar emitter identification, and cryptanalysis. Dr. Li has led multiple research projects funded by the National Natural Science Foundation of China (NSFC), the China Postdoctoral Science Foundation, and the Shaanxi Provincial Natural Science Fund, and has participated in several national and provincial collaborative projects. With an impressive academic record of over 60 peer-reviewed publications, his work has garnered more than 1,200 citations and an h-index of 18, reflecting his growing influence in artificial intelligence and computational intelligence research.
Featured Publications
Zhao, Z., Li, X., & Chang, Z., & Hu, N. (2025). Multi-view contrastive learning with maximal mutual information for continual generalized category discovery. Expert Systems with Applications, 259, 125994.
Zhao, Z., Li, X., Zhai, Z., & Chang, Z. (2024). Pseudo-supervised contrastive learning with inter-class separability for generalized category discovery. Knowledge-Based Systems, 287, 111477.
Zhao, Z., Jiang, M., Guo, J., Yang, X., Hu, Y., & Zhou, X. (2022, October 9). Raindrop removal for in-vehicle camera images with generative adversarial network. 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 9945304. IEEE.