Multi-Similarity Preserving Semantic-Aware Hashing for Cross-Modal Retrieval
IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 11593-11606
DOI: 10.1109/tcsvt.2026.3680156 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Long Zheng und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Hashing-based methods have gained widespread attention in cross-modal retrieval due to their significant potential for spatiotemporal efficiency and query accuracy, driving significant progress. However, most existing algorithms extract similarity information solely from labels, overlooking the consistent semantic similarities embedded in features. Additionally, some algorithms underutilize label semantics, neglecting inherent category relationships and their interplay with feature semantics, which compromises algorithmic effectiveness. Furthermore, current methods often suffer from weak discriminative power and semantic misalignment when embedding similarity information into hash codes, leading to learning biases. To address these shortcomings, a Multi-similarity Preserving Semantic-aware Hashing (MPSH) algorithm is proposed. MPSH first learns a shared semantic space from heterogeneous features to generate dynamic feature fusion similarity. Subsequently, it explores label distributions to construct category vectors, which are collaboratively associated with isomorphic feature representations to form a semantic-aware space. Finally, manifold embedding is employed to effectively preserve multi-similarity and data distribution, yielding semantically rich hash representations. Moreover, a non-relaxed discrete optimization algorithm is introduced to accelerate hash code iteration. Extensive experiments on multiple benchmark datasets, comparing MPSH with leading algorithms, demonstrate its superior efficiency and performance.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zheng, L., Chen, H., Xiang, B., Horng, S., & Li, T. (2026). Multi-Similarity Preserving Semantic-Aware Hashing for Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 11593-11606. https://doi.org/10.1109/tcsvt.2026.3680156
Vancouver
Zheng L, Chen H, Xiang B, Horng S, Li T. Multi-Similarity Preserving Semantic-Aware Hashing for Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):11593-11606. doi:10.1109/tcsvt.2026.3680156
BibTeX
@article{Zheng2026,
author = {Zheng, Long and Chen, Hongmei and Xiang, Biao and Horng, Shi-Jinn and Li, Tianrui},
title = {Multi-Similarity Preserving Semantic-Aware Hashing for Cross-Modal Retrieval},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {8},
pages = {11593--11606},
doi = {10.1109/tcsvt.2026.3680156}
}
EUVIMED