Prof. Xinzheng Xu

China University of Mining and Technology, China

Email: [email protected]

Qualifications

2012 Ph.D., China University of Mining and Technology, China

Publications (Selected)

1. Han, R., Peng, T., Zhu, B., et al. (2026). Document-level relation extraction with entity type constraints. Neural Networks, 197, 108469.
2. Li, Z., Chen, L., Xu, Y., et al. (2026). Human-corrected labels learning: Enhancing labels quality via human correction of VLMs discrepancies. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2026) (pp. 23346–23354).
3. Sun, T., Yang, H., Li, Z., et al. (2025). Adversarial domain adaptation with CLIP for few-shot image classification. Applied Intelligence, 55(1), 59.
4. Zhao, Z., Miao, X., Liu, L., et al. (2025). Sparse-guided partial dense for cross-modal remote sensing image-text retrieval. IEEE Transactions on Geoscience and Remote Sensing, 63, 1–13.
5. Wei, L., Pang, C., & Xu, X. (2025). SDP-DETR: End-to-end detection of aircraft skin defects via dynamic multi-scale aware mechanism. In Proceedings of the IEEE International Conference on Big Data (IEEE Big Data 2025) (pp. 1232–1237).
6. Wei, M., Li, Z., Ying, P., et al. (2025). Determined multi-label learning via similarity-based prompt. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2025) (pp. 1–6).
7. Wei, M., Xu, X., Ying, P., et al. (2025). Learning from stochastic labels. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2025) (pp. 1–6).
8. Li, Z., Xu, J., Ying, P., et al. (2025). Learning from true-false labels via multi-modal prompt retrieving. In Proceedings of the International Conference on Machine Learning (ICML 2025).
9. Ying, P., Li, Z., Wei, M., & Xu, X. (2025). Reversible privacy preserving on vision-language models via adversarial multimodal key. In Proceedings of the ACM International Conference on Multimedia (ACM Multimedia 2025) (pp. 3380–3389).
10. Wei, M., Li, Z., Ying, P., & Xu, X. (2025). Seeing the undefined: Chain-of-action for generative semantic labels. In Proceedings of the ACM International Conference on Multimedia (ACM Multimedia 2025) (pp. 3702–3711).
11. Li, Z., Wei, M., Ying, P., & Xu, X. (2025). ESA: Example sieve approach for multi-positive and unlabeled learning. In Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM 2025) (pp. 439–447).
12. Li, Z., Xu, M., Xu, X., & Zhang, D. (2024). Complementary labels learning with augmented classes. Knowledge-Based Systems, 290, 111570.
13. Wei, M., Li, Z., Zhou, Y., & Xu, X. (2024). Learning from reduced labels for long-tailed data. In Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR 2024) (pp. 111–119).
14. Li, Z., Ying, P., Wei, M., et al. (2024). Prompt expending for single positive multi-label learning with global unannotated categories. In Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR 2024) (pp. 561–569).
15. Li, Z., Wei, M., Ying, P., et al. (2024). Learning from concealed labels. In Proceedings of the ACM International Conference on Multimedia (ACM Multimedia 2024) (pp. 7220–7228).
16. Xu, X., Zhang, J., & Li, Z. (2023). Learning from hybrid labels with partial labels via hybrid-grained contrast regularization. Applied Soft Computing, 144, 110533.
17. Xu, X., Guo, Y., & Wang, X. (2023). Human pose estimation model based on DiracNets and integral pose regression. Multimedia Tools and Applications, 82(23), 36019–36039.
18. Wang, H., Zhou, S., Xu, X., & Zhang, G. (2023). TPN: Triple parts network for few-shot instance segmentation. Multimedia Tools and Applications, 82(30), 46439–46455.
19. Wei, M., Zhou, Y., Li, Z., & Xu, X. (2023). Class-imbalanced complementary-label learning via weighted loss. Neural Networks, 166, 555–565.

Profile Details
https://www.researchgate.net/profile/Xinzheng-Xu

WOS ResearcherID: JVE-1745-2024