We study a wide range of pressing tasks in visual anomaly and outlier detection, not only for natural images solely, but extending our attention also to the scenarios in industrial inspection, medical imaging, and open-world video anomalies and related understanding.
Z. Liu, S. Chen, J. Yu, C. Wang, K. Li, and J. Lu, “VUOD: A Versatile Unsupervised Outlier Detection Framework for Natural, Industrial, Medical Images and Beyond ,” European Conf. Computer Vision (ECCV), Malmo, Sweden, Sep. 2026. (Project page)
Z. Liu, K. Zhou, C. Wang, W.-Y. Lin, and J. Lu, “FlexUOD: The Answer to Real-World Unsupervised Image Outlier Detection,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Nashville, TN, Jun. 2025. (PDF)
J. Tang, H. Lu, R. Wu, X. Xu, K. Ma, C. Fang, B. Guo, J. Lu, Q. Chen, and Y.-C. Chen, “HAWK: Learning to Understand Open-World Video Anomalies,” Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec. 2024. (PDF)