Ivica Kopriva | Pattern Recognition | Best Researcher Award

Published on by Database Scientist

Dr. Ivica Kopriva | Pattern Recognition | Best Researcher Award

Rudjer Boskovich Institute | Croatia

Dr. Ivica Kopriva is a distinguished Senior Scientist at the Ruđer Bošković Institute, Croatia, internationally recognized for his pioneering contributions to signal processing, machine learning, and blind source separation. Dr. Ivica Kopriva’s interdisciplinary research integrates statistical learning, low-rank sparse modeling, and nonlinear decomposition methods to address complex challenges in biomedical imaging, remote sensing, and hyperspectral data analysis. His highly influential publications, including “Multi-view Low-Rank Sparse Subspace Clustering” (Pattern Recognition, 2018) and “l₀-Motivated Low-Rank Sparse Subspace Clustering” (IEEE Transactions on Cybernetics, 2018), have significantly advanced subspace clustering and unsupervised learning, with the former ranked among the top 1% of highly cited papers in Engineering. Dr. Ivica Kopriva’s research further encompasses image co-segmentation, tumor detection, and signal demixing, contributing to innovations in medical imaging and AI-based diagnostics. With over 2,546 citations, an h-index of 21, and an i10-index of 50, Dr. Ivica Kopriva’s scholarly impact extends across multiple disciplines of computational and biomedical sciences. His exceptional achievements have been recognized through numerous awards, including the State Award of the Republic of Croatia for Scientific Achievement (2009), multiple Director’s Awards for Scientific Excellence (2010–2021), and MICCAI Outstanding Reviewer Awards. As a Senior Member of IEEE and OSA and an affiliated faculty member at Virginia Commonwealth University, Dr. Ivica Kopriva continues to contribute extensively to international scientific communities, shaping the global research landscape in computational imaging, data-driven signal analysis, and intelligent biomedical systems.

Profiles: Google Scholar | Scopus | Orcid

Featured Publications

  • Brbić, M., & Kopriva, I. (2018). Multi-view low-rank sparse subspace clustering. Pattern Recognition, 73, 247–258.

  • Huang, T. M., Kecman, V., & Kopriva, I. (2006). Kernel based algorithms for mining huge data sets: Supervised, semi-supervised, and unsupervised learning. Springer Berlin Heidelberg.

  • Ju, W., Xiang, D., Zhang, B., Wang, L., Kopriva, I., & Chen, X. (2015). Random walk and graph cut for co-segmentation of lung tumor on PET-CT images. IEEE Transactions on Image Processing, 24(12), 5854–5867.

  • Brbić, M., & Kopriva, I. (2020). l₀-Motivated low-rank sparse subspace clustering. IEEE Transactions on Cybernetics, 50(4), 1711–1725.

  • Tolić, D., Antulov-Fantulin, N., & Kopriva, I. (2018). A nonlinear orthogonal non-negative matrix factorization approach to subspace clustering. Pattern Recognition, 82, 40–55.

Yang Liu | Pattern Recognition | Innovative Research Award

Published on by Database Scientist

Assist. Prof. Dr. Yang Liu | Pattern Recognition | Innovative Research Award

Assistant professor at Zhejiang University | China

Assistant Professor Dr. Yang Liu is an emerging scholar specializing in computer vision, machine learning, and remote sensing, with a strong research focus on unsupervised representation learning, facial modeling, and multimodal image translation. His work integrates deep learning and generative modeling to advance intelligent visual understanding systems. Notably, his 2025 paper “Adaptive Sparse Contrastive Learning for Unsupervised Object Re-identification” in Pattern Recognition introduces an innovative sparse contrastive framework for improved feature discrimination in object re-identification. His 2024 studies in Knowledge-Based Systems and Remote Sensing present significant contributions to multi-objective reinforcement learning through dynamic preference inference and to SAR-to-multispectral image translation via S2MS-GAN, enhancing cross-modal synthesis and efficiency. Earlier works in IEEE Signal Processing Letters and IEEE Access showcase his expertise in fine-scale 3D face reconstruction, texture fusion, and photorealistic head modeling. Collaborating with international teams from leading universities such as Zhejiang University and Northwestern Polytechnical University, Assistant Professor Dr. Yang Liu continues to drive innovation at the intersection of computer vision and AI. His ongoing research aims to develop more adaptive, interpretable, and sustainable AI-driven visual intelligence systems that can bridge the gap between human perception and machine understanding in complex, real-world environments.

Profile

Featured Publications

  • Zheng, D., Liu, Y., Zhou, D., Xiao, J., Zhang, B., & Chen, L. (2025). Adaptive sparse contrastive learning for unsupervised object re-identification. Pattern Recognition, 157, 112604.

  • Liu, Y., Zhou, Y., He, Z., Yang, Y., Han, Q., & Li, J. (2024). Dynamic preference inference network: Improving sample efficiency for multi-objective reinforcement learning by preference estimation. Knowledge-Based Systems, 305, 112512.

  • Liu, Y., Han, Q., Yang, H., & Hu, H. (2024). High-resolution SAR-to-multispectral image translation based on S2MS-GAN. Remote Sensing, 16(21), 4045.

  • Liu, Y., Fan, Y., Guo, Z., Zaman, A., & Liu, S. (2023). Fine-scale face fitting and texture fusion with inverse renderer. IEEE Signal Processing Letters, 30, 139–143.

  • Fan, Y., Liu, Y., Lv, G., Liu, S., Li, G., & Huang, Y. (2020). Full face-and-head 3D model with photorealistic texture. IEEE Access, 8, 188041–188051.