EUVIMEDEUVIMED entdecken
Crossref

LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation

Yuntao Li, Chunfu Jia, Mingyue Li, Guanxiong Ha, Ruizhong Du

IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 22590-22604

DOI: 10.1109/tmc.2026.3724186 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Yuntao Li und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: Beijing-Tianjin-Hebei Natural Science Cooperation Project, Tianjin Science and Technology Major Special Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of multimodal data in cloud-based applications creates an increasing demand for efficient cross-modal retrieval while protecting sensitive information from untrusted servers. Existing privacy-preserving cross-modal retrieval schemes often suffer from limited accuracy or high search overhead. To address these limitations, this paper proposes LMCR, which integrates lossless encrypted scoring with multi-probe hybrid indexing. LMCR uses CLIP to map image and text samples into a shared semantic space and further applies Cross-Modal Consistency-Aware Density Refinement (CMDR) to construct semantic partitions jointly supported by image and text neighborhoods. Based on these partitions, semantic inverted lists and cluster-specific KD-Trees are built to reduce the encrypted search space through multi-probe retrieval. In addition, an orthogonal-LWE-based mechanism preserves plaintext ranking during encrypted linear search. Experiments on four benchmark datasets demonstrate that LMCR achieves high retrieval accuracy and substantial search efficiency.

Förderung

  • Beijing-Tianjin-Hebei Natural Science Cooperation Project
  • Tianjin Science and Technology Major Special Project

Zitieren

APA

Li, Y., Jia, C., Li, M., Ha, G., & Du, R. (2026). LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation. IEEE Transactions on Mobile Computing, 25(12), 22590-22604. https://doi.org/10.1109/tmc.2026.3724186

Vancouver

Li Y, Jia C, Li M, Ha G, Du R. LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation. IEEE Transactions on Mobile Computing. 2026;25(12):22590-22604. doi:10.1109/tmc.2026.3724186

BibTeX
@article{Li2026,
  author = {Li, Yuntao and Jia, Chunfu and Li, Mingyue and Ha, Guanxiong and Du, Ruizhong},
  title = {LMCR: Lossless Multi-Probe Cross-Modal Retrieval With Privacy Preservation},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {12},
  pages = {22590--22604},
  doi = {10.1109/tmc.2026.3724186}
}
Kostenlos starten →