Multi-Granularity Semantic Complementarity Fusion Hashing for Cross-Modal Retrieval
IEEE Transactions on Multimedia · 2026 · 28 · 4771-4785
DOI: 10.1109/tmm.2026.3660164 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2026. Verfasst von Long Zheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Hashing techniques have attracted significant attention in cross-modal retrieval tasks due to their high query efficiency and low storage overhead. However, some methods map heterogeneous features and labels into the same semantic space, ignoring their complementary relationship, which leads to semantic loss. When leveraging pairwise similarity relationships, the affinity matrix incurs high computational costs, and the asymmetric proxy strategy lacks sufficient semantic degrading retrieval performance. Additionally, optimizing binary hash codes remains a challenging task. A novel algorithm, Multi-granularity Semantic Complementarity Fusion Hashing (MSCFH), is proposed to address these issues. First, it learns multi-granularity semantic representations from features and labels, then complements their semantics through a complementarity fusion strategy. Subsequently, an asymmetric semantic learning framework is constructed, guided by label similarities, to learn discriminative hash codes. Furthermore, an efficient discrete optimization algorithm is introduced to update the hash codes. Extensive experiments on three benchmark datasets show that the proposed MSCFH demonstrates the best retrieval accuracy and highly competitive training efficiency compared to state-of-the-art approaches.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zheng, L., Chen, H., Xiang, B., Horng, S., & Li, T. (2026). Multi-Granularity Semantic Complementarity Fusion Hashing for Cross-Modal Retrieval. IEEE Transactions on Multimedia, 28, 4771-4785. https://doi.org/10.1109/tmm.2026.3660164
Vancouver
Zheng L, Chen H, Xiang B, Horng S, Li T. Multi-Granularity Semantic Complementarity Fusion Hashing for Cross-Modal Retrieval. IEEE Transactions on Multimedia. 2026;28:4771-4785. doi:10.1109/tmm.2026.3660164
BibTeX
@article{Zheng2026,
author = {Zheng, Long and Chen, Hongmei and Xiang, Biao and Horng, Shi-Jinn and Li, Tianrui},
title = {Multi-Granularity Semantic Complementarity Fusion Hashing for Cross-Modal Retrieval},
journal = {IEEE Transactions on Multimedia},
year = {2026},
volume = {28},
pages = {4771--4785},
doi = {10.1109/tmm.2026.3660164}
}
EUVIMED