Semantic-Enhanced Graph Regularization Hashing for Large-Scale Cross-Modal Retrieval
Data Science and Engineering · 02.11.2026
DOI: 10.1007/s41019-026-00366-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data Science and Engineering, online erschienen am 02.11.2026. Verfasst von Qian Zhang und 7 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Young Scholars Program of Shandong University, Young Talent of Lifting Engineering for Science and Technology in Shandong.
Abstract (Originalsprache)
In the area of large-scale data, cross-modal hashing has attracted significant attention for fast similarity search task due to its low storage requirements and fast retrieval speed. Existing supervised cross-modal hashing learning methods have made extensive attempts to fully exploit supervisory information. Different from previous work, we propose a method named S emantic- E nhanced G raph R egularization H ashing ( SEGRH ), which contributes a new and novel exploration to this research domain. Specifically, our method consists of two core components: contrastive cross-modal fusion and robust semantic preservation. We adopt the pre-trained CLIP model as the backbone to extract modality-specific features, which are subsequently fused via a multimodal Transformer. Robust semantic preservation is designed to mine and integrate high-quality semantic information. SEGRH first leverages positive pointwise mutual information to convert label information into semantic association metrics. Second, the graph Laplacian is incorporated to absorb such semantic cues and further constrain the structure of the hash space. Our SEGRH is capable of performing high-quality multimodal learning and possesses strong semantic consistency modeling capabilities, thereby achieving satisfactory generalization performance. Experimental results on three standard datasets demonstrate that our approach significantly outperforms previous state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
- Young Scholars Program of Shandong University
- Young Talent of Lifting Engineering for Science and Technology in Shandong
- Natural Science Foundation of Shandong Province
- Taishan Scholar Project of Shandong Province
- Postdoctoral Fellowship Program of CPSF
Zitieren
APA
Zhang, Q., He, S., Jiang, H., Liu, X., Zhan, Y., Chen, Z., Luo, X., & Xu, X. (2026). Semantic-Enhanced Graph Regularization Hashing for Large-Scale Cross-Modal Retrieval. Data Science and Engineering. https://doi.org/10.1007/s41019-026-00366-6
Vancouver
Zhang Q, He S, Jiang H, Liu X, Zhan Y, Chen Z, et al. Semantic-Enhanced Graph Regularization Hashing for Large-Scale Cross-Modal Retrieval. Data Science and Engineering. 2026. doi:10.1007/s41019-026-00366-6
BibTeX
@article{Zhang2026,
author = {Zhang, Qian and He, Shu-Huan and Jiang, Hui-Han and Liu, Xiao-Qian and Zhan, Yu-Wei and Chen, Zhen-Duo and Luo, Xin and Xu, Xin-Shun},
title = {Semantic-Enhanced Graph Regularization Hashing for Large-Scale Cross-Modal Retrieval},
journal = {Data Science and Engineering},
year = {2026},
doi = {10.1007/s41019-026-00366-6}
}
EUVIMED